Oren Bochman’s Blog

ODSC - AI 2026 - Workshops

These are workshops and sessions that were not on the main track.

Thursday, April 30, 2026

ODSC AI 2026

Day 3

A detailed recap of the ODSC AI 2026 Day 3 sessions, covering keynotes, lectures, and workshops on topics such as trustworthy LLMs, clustering, reinforcement learning for…

Thursday, April 30, 2026

Talk topic: YK presents “the spectrum of agentic coding,” based on roughly three years of work with AI coding agents, including an early ChatGPT-plugin tool called Kaguya tha…

ODSC AI 2026 - Day 2

46 min

Wednesday, April 29, 2026

in Large-Scale Enterprise Systems

Agentic AI for Autonomous Root-Cause Analysis

A deep dive into multi-agent AI systems for autonomous root-cause analysis in large-scale enterprise IT environments.

Agentic LLMs in Practice

A deep dive into Naman Goyal’s keynote on agentic large language models,
exploring the challenges and strategies for building reliable and observable LLMs.

For Building and Governing Production-Grade Multi-Agent Systems

Architectural Patterns

A deep dive into Dr. Ali Arsanjani’s talk at ODSC AI 2026
on architectural patterns for building and governing production-grade multi-agent systems.

Interpretability of LLMs in Finance

Beyond the black box -

interpretability

A deep dive into Hariom Tatsat’s keynote on interpretability of large language models in finance, exploring the challenges and strategies for ensuring reliability and safety.

Building Effective Agents

agents

A deep dive into Sushant Mehta’s keynote on building effective large language model agents,
exploring the challenges and strategies for ensuring reliability and safety.

Building FSI Agents with Claude

A deep dive into Mikaela Grace and April Guo’s talk at ODSC
AI 2026 on building Claude-based agents for financial-services industry workflows,
exploring best…

Engineering Patterns for Real-World Performance

Deploying Multimodal AI at the Edge

A deep dive into Achyut Sarma Boggaram’s ODSC
AI 2026 talk on deploying multimodal AI at the edge,
focusing on engineering patterns for real-world performance.

Using Model Context Protocol to Support Agentic Behaviors in Your Application

From Intelligent to Agentic Applications

A deep dive into Kyle Stratis’s talk on using the Model Context Protocol to support agentic behaviors in applications.

A Blueprint for Safe & Compliant Healthcare Agents in Production

Governing Agentic AI

A deep dive into the challenges and best practices for governing agentic AI systems in healthcare, including risk assessment, continuous testing, and production monitoring.

Enhancing Clinical Reasoning with Knowledge Graphs, GNNs, and Agents

GraphRAG in Healthcare

healthcare

A deep dive into Giuseppe Futia’s keynote on GraphRAG in healthcare,
exploring the integration of knowledge graphs, GNNs, and agents for clinical reasoning.

Practical Patterns for Agent-First Software Development

Harness Engineering

A deep dive into Ryan Lopopolo’s talk at ODSC AI 2026
on Harness Engineering, exploring practical patterns for agent-first software development.

Kyle Stratis

A deep dive into Kyle Stratis’s talk at ODSC AI 2026
on AI Agents with MCP, exploring the practical implementation and best practices for building AI agents using the…

Meaningful Data Visualization

A deep dive into Janet Six’s talk at ODSC
AI 2026 on meaningful data visualization in the age of AI,
exploring how to make visualizations that truly support…

ODSC AI 2026

Audience: The talk is aimed at business owners, managers, team leaders, and employees who want to push AI adoption forward in their workplace.

Outclassing Frontier LLMs at Extracting Information

ocr

information extraction

A deep dive into NewMind CEO Etienne Bernard’s talk on building specialized small language models for document information extraction, exploring the advantages and…

Practical Foundations for Organization-Wide AI Adoption

A deep dive into Ivan Lourenço Gomes’s talk on practical strategies for organization-wide AI adoption, exploring how to implement AI effectively across teams and workflows.

using Kafka, Flink, and Apache Pinot

Real-Time Event-Time Consistent Analytics Pipelines

A deep dive into Deep Patel’s talk at ODSC AI 2026
on real-time event-time consistent analytics pipelines,
exploring the use of Kafka, Flink, and Apache Pinot for…

Reinforcement Learning for LLM

A recap of the talk “Reinforcement Learning for LLM” by Datta Nimmaturi at ODSC AI 2026 Day 3.

Tensor Logic

A deep dive into Pedro Domingos’s talk on Tensor Logic, exploring the unification of symbolic reasoning and neural computation in a single language for AI.

The AI Agent Memory Landscape

A deep dive into William Lyon’s talk on the AI agent memory landscape, exploring the challenges and solutions for structured, shared, and evolving memory in production AI…

The Good, The Bad and The Beautiful

The Art of Clustering

clustering

A deep dive into Seth Levine’s talk on clustering, exploring the techniques, challenges, and insights for effective data analysis.

From Monolithic Training to Continuous Adaptation

The Changing Shape of AI Systems

A deep dive into Cohere Labs’ Nouha Dziri’s
keynote on building trustworthy large language models,
exploring the challenges and strategies for ensuring reliability…

The Operational Transformation of Data Architecture

A deep dive into Andy Petrella’s talk on
the operational transformation of data architecture,
exploring the unification of symbolic reasoning and neural…

Turning Human Preferences into Production Agent Judgment

The Verifier–Compiler Loop

talk

A deep dive into Ruslan Belkin’s talk on the Verifier–Compiler Loop, exploring the unification of human preferences and production agent judgment in AI.

Understanding Limits, Advancing Capabilities, Ensuring Safety

Towards Trustworthy LLMs

A deep dive into Cohere Labs’ Nouha Dziri’s
keynote on building trustworthy large language models,
exploring the challenges and strategies for ensuring reliability…

Understanding Limits, Advancing Capabilities, Ensuring Safety

Towards Trustworthy LLMs

A deep dive into Cohere Labs’ Nouha Dziri’s
keynote on building trustworthy large language models,
exploring the challenges and strategies for ensuring reliability…

Understanding Limits, Advancing Capabilities, Ensuring Safety

Towards Trustworthy LLMs

A deep dive into Cohere Labs’ Nouha Dziri’s
keynote on building trustworthy large language models,
exploring the challenges and strategies for ensuring reliability…

A Getting Started Guide for Data Scientists

Using Model Context Protocol with Python

A deep dive into Ryan Day’s talk at ODSC
AI 2026 on Model Context Protocol (MCP), exploring how to provide data and functionality to AI agents using Python.

vLLM with the Transformers Modelling Backend

A deep dive into Harry Mellor’s talk on vLLM with the Transformers Modelling Backend, exploring the integration of vLLM with HuggingFace Transformers for efficient model…

A Practical Introduction to Agentic AI

workshop

A workshop on building agentic AI applications from scratch, covering tool use, task decomposition, self-correction, conditional routing, and human-in-the-loop review.

Building Responsible AI Agents

A workshop on building responsible AI agents using open source tools, with a focus on healthcare applications and privacy-preserving design.

A Practical Workshop on Context Engineering for Generative AI

Engineering the Harness

In this funky workshop, Rajiv Shah dives into the rabbit hole of harness engineering for AI agents. He covers the importance of coding harnesses, the key levers of harness…

From Theory to Application

Introduction to Machine Learning

workshop

An introduction to machine learning concepts and practical application using scikit-learn, covering topics such as regression, classification, decision trees, random…

Introduction to the Agent2Agent (A2A) Protocol

workshop

A workshop introducing the Agent-to-Agent (A2A) protocol, which enables interoperability and communication between independent AI agents across different frameworks and…

A Workshop on the Mathematics of Transformers and Large Language Models

Introduction to the Math Behind Transformers and LLMs

An accessible introduction to the mathematics behind transformers and large language models, covering key concepts such as attention mechanisms, self-attention, multi-headed…

ODSC AI 2026

These are workshops and sessions that took place before the start of the main track.

Why most Bayesians avoid Mixture Models

Mixture problems

mathematics

An exploration of the challenges associated with mixture models in Bayesian statistics, including identifiability, label switching, and computational complexity, along with…

Saturday, March 7, 2026

The challenges of filtering and smoothing for switching models

Smoothing problems

This is a follow up to the previous post in the same spirit of the post on Mixture problems. I’ve recently implemnted some switching models and was delighted to see how the…

mathematics

Saturday, March 7, 2026

A bayesian form of bravery

Being brave

personal

An exploration of the challenges associated with mixture models in Bayesian statistics, including identifiability, label switching, and computational complexity, along with…

Friday, March 6, 2026

In this talk, Valentin Vercovici and Callan Fox discuss the challenges of maintaining high KV cache hit rates in large-scale AI inference workloads and introduce the concept…

Monday, January 19, 2026

AI Performance Engineering Meetup

nvidia Nsight GPU profiling

In this talk, Chaim Rand revisits the NVIDIA Nsight profiling tools to augment the PyTorch Profiler, addressing critical issues in data transfer and batching for AI/ML…

Monday, January 19, 2026

Integrating Reinforcement Learning with Large Language Models for Advanced Reasoning and Planning

RL Agents Last All Summer Long

Exploring how Reinforcement Learning (RL) can enhance the reasoning and planning capabilities of Large Language Models (LLMs) by creating a hierarchical agent structure and…

Wednesday, January 14, 2026

Integrating Reinforcement Learning with Large Language Models for Advanced Reasoning and Planning

Rise of the agents

Exploring how Reinforcement Learning (RL) can enhance the reasoning and planning capabilities of Large Language Models (LLMs) by creating a hierarchical agent structure and…

Wednesday, January 14, 2026

A deep dive into the three modes of convergence for random variables: convergence in probability, almost sure convergence, and convergence in distribution. We explore their definitions, interpretations, geometric sketches, hierarchy, counterexamples, and applications in probability theory and statistics.

Three modes of convergence of random variables

12 min

probability

random-variables

A deep dive into the three modes of convergence for random variables: convergence in probability, almost sure convergence, and convergence in distribution. We explore their…

Friday, January 9, 2026

Making sense of the buzzwords around AI agents

Agentic Buzz

This is my guide for sorting out the fluff from the substance around AI agents. I want to track what people are most excited about so I can join in the fun.

Saturday, January 3, 2026

Convolutions, Fourier transforms, and the Fast Fourier Transform (FFT)

Convoluted Intuitions

Saturday, January 3, 2026

math

probability

Convolutions are a fundamental mathematical operation that arises in many areas of mathematics, physics, and engineering. In this post, we will explore the concept of…

Sick

Thursday, January 1, 2026

personal

I’ve been sick for about a week with the sniffles and a mild fever. It’s been a bit of a rough patch, but I’m starting to feel better now. I’ve been resting a lot and…

Anthropic’s Claude: Advancing AI with Safety and Scalability

Sunday, December 14, 2025

A detailed recap of the PyData Global 2025 talk on Anthropic’s Claude, covering its architecture, safety features, and applications in AI.

Causal Thinking in Machine Learning

Beyond Just Prediction

A comprehensive recap of the PyData Global 2025 talk on integrating causal thinking into machine learning, focusing on uplift modeling to enhance decision-making processes…

a fast and scalable HPC-based drop-in replacement for Pandas

Bodo DataFrames

A detailed recap of Scott Routledge talk at the PyData Global 2025 conference. In which he discusses Bodo DataFrames, a high-performance computing-based drop-in replacement…

Building a Lightweight Feature Store for Electricity Grid Forecasts with Polars

electricity grid forecasts

Get a firsthand look at how we built a lightweight feature store to accelerate electricity grid forecasting. We’ll cover our decision process, design choices, and…

Combining Zarr, HDF5, and TIFF into a single data format

A detailed recap of the PyData Global 2025 talk on combining Zarr, HDF5, and TIFF into a single data format, covering key components, performance considerations, and…

GPU Accelerated Zarr

A detailed recap of the PyData Global 2025 talk on GPU-accelerated Zarr, covering key components, performance considerations, and practical implementation tips.

GPU Python for the Real World: Practical Steps to GPU-Accelerated Python with RAPIDS

A detailed recap of the PyData Global 2025 talk on GPU-accelerated Python using RAPIDS, covering key components, common pitfalls, and practical implementation tips.

Building Compliant and Reproducible ML Pipelines

Garbage In: Lawsuit Out

A recap of Itai Gilo’s PyData Global 2025 talk on defensible, reproducible, and auditable machine learning pipelines, with a focus on data versioning and compliance controls.

How to Effectively use text embeddings in tree based models

A detailed recap of the PyData Global 2025 talk by Claudio Salvatore Arcidiacono on effectively using text embeddings in tree-based models, covering key concepts…

Scaling Data Processing for LLMs with NeMo Curator

A detailed recap of the PyData Global 2025 talk on building a transformer model from scratch using PyTorch, covering key components, common pitfalls, and practical…

Extending sparse computing in the Python ecosystem

Sparse & Finch

A detailed recap of the PyData Global 2025 talk by Mateusz Sokół and Willow Marie Ahrens
on implementing sparse computing in the Python ecosystem
using…

TinyTroupe: Enhancing Marketing Insights through LLM-Powered Multiagent Persona Simulation

A detailed recap of the PyData Global 2025 talk on building a transformer model from scratch using PyTorch, covering key components, common pitfalls, and practical…

Chernobyl Disaster Lessons for ML Systems in Production

When the Meter Maxes Out

A detailed recap of the PyData Global 2025 talk on lessons from the Chernobyl disaster applied to machine learning systems in production, highlighting common failure modes…

Automating ML with PyCaret: Train & Compare Multiple Models to Find the Best Performer

Thursday, December 11, 2025

A live demonstration of how PyCaret simplifies machine learning workflows by enabling users to train and compare multiple models with minimal code.

A Bayesian Approach to modelling the cold start problem

Enhancing Marketplace Competitiveness

recommendation systems

An exploration of how Bayesian statistical modeling can be applied to the cold start problem in recommendation systems, enabling efficient decision-making and risk…

Thursday, December 11, 2025

How Big are SLMs

Thursday, December 11, 2025

A recap of Jayita Bhattacharyya’s talk at PyData Global 2025 on Small Language Models (SLMs), exploring their capabilities, training techniques, and implications for AI…

Decisions Under Uncertainty: A Hands‑On Guide to Bayesian Decision Theory

bayesian decision theory

uncertainty

bayesian optimization

experimental design

A practical introduction to Bayesian decision theory, illustrating how to make optimal decisions under uncertainty with hands-on Python examples.

From Ideas to APIs: Delivering Fast with Modern Python

The modern Python ecosystem shortens the distance between idea and implementation. This talk presents a focused workflow to move from a business question to a working…

Hands-on with Blosc2: Accelerating Your Python Data Workflows

A practical tutorial on using Blosc2 to optimize data workflows in Python, focusing on out-of-core computations and efficient handling of large datasets.

Lessons in Decision Making from the Monty Hall Problem

Switch or stay, what do you say? And more importantly, why?

Optimal Variable Binning in Logistic Regression

A practical guide to optimal variable binning techniques for enhancing logistic regression models in regulated industries.

Optimizing AI/ML Workloads: Resource Management and Cost Attribution

A comprehensive framework for monitoring, analyzing, and optimizing AI/ML workloads to enhance resource utilization and cost attribution using Metaflow.

Realtime Financial Fraud Detection with Modern Python

pydata global 2025

A recap of the PyData Global 2025 talk on real-time financial fraud detection using modern Python tools and techniques.

Reviving Survival Analysis: Timeless, Yet Overlooked?

time-to-event modeling

python

A practical introduction to survival analysis, its core concepts, and applications using Python and R.

Time series analysis for coupled neurons.

mathematical modeling

A hands-on tutorial on time series analysis of coupled neuron models using Python.

Using MCP to turn Claude into a Football Opposition Analyst

A recap of Adam Cowley’s PyData Global 2025 talk on using Model Context Protocol (MCP) to transform Anthropic’s Claude into a football opposition analyst.

Building LLM-Powered Applications for Data Scientists and Software Engineers

A detailed recap of the PyData Global 2025 workshop on building LLM-powered applications, focusing on software engineering principles, prompt engineering, monitoring, and…

Designing a Fast, Offline-Capable Reverse Geocoder in Python: An Open Source Alternative to Big Geo APIs

A hands-on walkthrough of building a fast, offline-capable reverse geocoder in Python using open-source tools like cKDTree, shapely, and geopandas.

From Feature Engineering to Context Engineering for Agents

large language models

Exploring the transition from traditional feature engineering techniques to context engineering for large language model agents.

Harnessing Generative Models for Synthetic Non-Life Insurance Data

An in-depth exploration of using various generative models to create synthetic non-life insurance premium data, including validation techniques and model comparisons.

I Built a Transformer from Scratch So You Don’t Have To

A hands-on walkthrough of building the original Transformer architecture from scratch in PyTorch, demystifying attention mechanisms, positional encoding, and the…

LLMs, Chatbots, and Dashboards: Visualize Your Data with Natural Language

A recap of the PyData Global 2025 talk by Daniel Chen on integrating LLMs into data science workflows, using the Chatlas package and Shiny dashboards to create AI-powered…

Lessons learnt in optimizing a large-scale pandas application using Polars, FireDucks and cuDF: Go Smart and Save More!

performance optimization

polars

cudf

fireducks

A detailed exploration of optimizing large-scale pandas applications using high-performance alternatives like Polars, FireDucks, and cuDF, highlighting best practices and…

Smarter Workflows for Analysts and Data Teams

Python Meets Excel

A comprehensive overview of how Python can be effectively integrated with Excel to automate and enhance data workflows, focusing on practical tools and techniques for…

Python Worst Practices - Learn from the Expert

A humorous look at the worst practices in Python programming, presented by data and analytics comedian Evan Wimpey.

Scaling Fuzzy Product Matching with BM25: A Comparative Study of Python and Database Solutions

A practical guide to implementing BM25 for fuzzy product matching at scale using Python and DuckDB, complete with performance benchmarks and optimization tips.

The Lifecycle of a Jupyter Environment - From Exploration to Production-Grade Pipelines

A comprehensive overview of transitioning Jupyter notebooks from exploratory tools to production-grade pipelines, covering best practices, tools, and real-world challenges.

Using Traditional AI and LLMs to Automate Complex and Critical Documents in Healthcare

healthcare

large language models

document automation

A comprehensive overview of how traditional AI and large language models can be leveraged to automate the creation of complex and critical documents in healthcare, such as…

Understanding and Tackling Hallucinations

When AI Makes Things Up

In this talk, Aarti Jha presents a practical guide to understanding, detecting, and mitigating hallucinations in AI systems for building trustworthy applications.

Where Have All the Metrics Gone?

Exploring the challenges and strategies for defining and measuring metrics in modern AI systems, especially when traditional metrics are unavailable or inadequate.

Why Julia’s GPU-Accelerated ODE Solvers are 20x-100x Faster than Jax and PyTorch

performance benchmarking

An in-depth look at the architectural differences that make Julia’s GPU-accelerated ODE solvers significantly faster than their Python counterparts, based on the 2024…

projspec: what’s this project anyway?

A detailed recap of the PyData Global 2025 talk on projspec, a tool for introspecting and managing Python data projects.

torchTextClassifiers : Modernizing Text classification for French National Statistics

An in-depth look at how Insee modernized text classification by transitioning from fastText to a PyTorch-based model using the open-source torchTextClassifiers package…

Thursday, October 9, 2025

Stochastic gradient Descent – a Deep Dive

Updates to the github action

In the last few dates I made some updates to the blog, cleaning things up but it broke down.

Wednesday, October 1, 2025

A Wikipedian considers prompting strategies in the age of GPT 5

Vibe coding GPT5 Edition

Thursday, September 25, 2025

llm

prompting engineering

vibe coding

A few thoughts on how to get the most out of GPT-5 for coding and tough problems

Explanation of FlexAttention by the team that developed it.

FlexAttention: A Flexible Approach to Attention Mechanisms

Saturday, September 20, 2025

Explanation of FlexAttention by the team that developed it.

FlexAttention: A Flexible Approach to Attention Mechanisms

Saturday, September 20, 2025

Explanation of FlexAttention by the team that developed it.

FlexAttention: A Flexible Approach to Attention Mechanisms

Saturday, September 20, 2025

Probabilitic Modeling with Language Models

Ever since I learned about building LLM I’ve been asking myself now that I can get a probability distribution over a token given a context how can I use this in (bayesian)…

Sunday, September 14, 2025

Marketing Mix Model

Wednesday, September 10, 2025

models

A model for marketing mix

A Critical Look and Analysis

Allegations of War Crimes and the Palestinian Genocide

14 min

current affairs

A critical analysis of the allegations of war crimes and genocide in the context of the Israeli-Palestinian conflict, examining the evidence, legal standards, and the…

Sunday, September 7, 2025

My bag of tricks for the AI age

AI a bag of tricks

A collection of tools and techniques I use in the AI age.

Thursday, September 4, 2025

POC of a Mesa tutorial running in the browser with ShinyLive for Python

ShinyLive ❤️ Mesa Tutorial

This is my vibe coding guide on how I built a POC of concept for running Mesa app (their tutorial) in ShinyLive app so it can run in the browser without a front end.

Tuesday, September 2, 2025

Exploring GenAI-powered tools

Langtalks Resources # 43

generative ai

podcasts

Exploring GenAI-powered tools

Thursday, April 3, 2025

A baseline morphology and syntax for emergent languages

Base line Morphology Model

23 min

code

Some thoughts and code for a baseline morphology and syntax for emergent languages

Wednesday, April 2, 2025

Clarifying my research questions

Complex Lewis Signaling - The Research Questions

A list of clarified research questions regarding emergent languages, planning, and grounding in multi-agent systems.

Wednesday, April 2, 2025

Monday, September 22, 2025

The roles of Partial pooling and mixed strategies in the Lewis signaling game

a game theoretic perspective

An exploration of partial pooling equilibria and mixed strategies in the Lewis signaling game, shedding light on their implications for emergent languages and communication…

Tuesday, March 11, 2025

Emergent Languages

A Desiderata

14 min

information theory

linguistics

Tuesday, January 14, 2025

A working paper on emergent languages

Planning in the Complex Lewis Game

15 min

compositionality

Today I want to consider a couple of weak assumption about planning in the Complex Lewis game. Yet before I do I ought to revisit the basic form of the Lewis Signaling game…

transfer learning

information theory

linguistics

Tuesday, January 14, 2025

Back of the napkin complexity calculations

The Referential Lewis Signaling Game

When I read a few papers using the referential Lewis signaling game I thought, this should be much faster for complex signaling games I use in my research. But when I got to…

Tuesday, January 14, 2025

I’ve been thinking how to visualize learning the complex lewis games.

A garden of forking paths

10 min

Saturday, January 11, 2025

Complex Signals Questions

Research Notes

Some questions about planning in the Lewis Signaling Game and the stability of equilibria.

Monday, January 6, 2025

The Many Path To A Signaling System

11 min

signaling systems

lewis signaling game

bayesian reinforcement learning

bayesian games

information theory

game theory

The Garden of Forking Paths — Jorge Luis Borges

Sunday, January 5, 2025

Off-Policy Learning

For Dummies

RL is full of big words like “off-policy learning” and “importance sampling”. If big words scare you, you are not alone. But most of the ideas in RL are simple and…

off-policy learning

deep learning

machine learning

artificial intelligence

Saturday, January 4, 2025

Rethinking Signaling systems via the lens of compositionality

In (Skyrms 2010) the author discusses the evolution of signaling systems and the emergence of language as well as the role of compositionality in the emergence of language…

Thursday, January 2, 2025

Books, Courses Tools

An Introduction to Statistical Learning by Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani.

news

books

The above is a basic version of the Lewis Signaling Game implemented in PettingZoo. The game consists of a sender and one or more receivers.

Lewis Signaling Game for PettingZoo

Scar face Capone in the valentine’s day massacre

Villeny pure and simple

So much has been written about capone, and gangster movies here is a little note on character building in Noir. Noir characters were often minmal stereotypes, but some…

Thursday, December 12, 2024

Misbehavior of Markets and Scaling in financial prices 1-4

Four papers and a book

Review of Mandelbrot’s papers on scaling in financial prices and his popular science book The (Mis)behaviour of Markets.

Monday, December 2, 2024

Multifractal Concentration

Scaling in financial prices 4

“In the Brownian model, such a high level of concentration has a probability so minute that it should never happen. Unfortunately for the model, it happens every decade.”

Sunday, December 1, 2024

Cartoon Brownian Motions in Multifractal Time

Scaling in financial prices 3

In the paper “Scaling in financial prices: III. Cartoon Brownian Motions in Multifractal Time” (Mandelbrot 2001) Mandelbrot continus his exploration of fractal and…

Saturday, November 30, 2024

Multi-fractals and the star equation

Scaling in financial prices 2

Friday, November 29, 2024

Thursday, November 28, 2024

Scaling in financial prices 1

Adaptive Huffman coding for online learning of compositional languages

Vitter’s Algorithm

This article explores Vitter’s Algorithm and its application in online learning and communication within multi-agent systems.

Friday, October 11, 2024

TL-DR rethinking 💭 topological alignment

12 min

Recently, I’ve been revisiting an old idea about creating a topological model of alignment. The machine translation task has been solved largely by using deep learning…

Tuesday, October 1, 2024

An essay on the limitations of language models

LLM the good the bad and the ugly

Early when I saw the first text by gpt2 I was intrigued that some of the researchers that did not get access to the early model and had to re-create the model based on just…

Monday, September 30, 2024

The missing link is my name for a set of agents that should be able to edit wikipedia or at least to significantly reduce the effort needed to contribute to wikipedia.

LLM and the missing link

Saturday, September 28, 2024

NLP with RL

supervised and unsupervised models are great for most NLP tasks, yet both approaches have their limitations. Supervised models require labeled data, which is usually in…

Friday, September 27, 2024

goal create a deduction data-set for evaluating reasoning capabilities of a man and machine.

Deduction Evaluation

Thursday, September 26, 2024

Can we fine tune a state of the art LLM to improve the readability of text?

Fine-tune llm for Style and Grammar advice.

Wednesday, September 25, 2024

Can we fine tune a state of the art LLM to improve the readability of text?

Is compositionality overrated? The view from language emergence

Sunday, September 1, 2024

A review of Marco Baroni’s talk on the emergence of languages and the role of compositionality in language evolution.

Six quick tips to improve modeling

The following tips are from (Gelman and Hill 2007) Data Analysis Using Regression and Multilevel/Hierarchical Models by Andrew Gelman and Jennifer Hill.

Monday, August 26, 2024

Stumpy

Times Series Analysis

Stumpy (Law 2019) is a powerful and scalable library for computing a matrix profile which can be used for a variety of time series data mining tasks.

Thursday, August 8, 2024

replay buffer questions

we should aim to keep full options traces in the buffer

Tuesday, July 2, 2024

two ideas on generalization

The first idea comes from looking at regression and hyperparameter optimization tasks

Monday, July 1, 2024

Mesa & RL

Ifs we can store state, action, reward trajectories (to a file) this would facilitate

Tuesday, June 25, 2024

zero inflated data

Zero inflated data is a type of data that has a large number of zero values.

Sunday, June 23, 2024

readings in rl

9 min

A list of RL-papers and resources that I have read or plan to read.

Tuesday, June 18, 2024

Hyperparameter Optimization

one the idea is for a set of Hyperparameters to find the best one.

Thursday, June 13, 2024

Extending Sugarscape for Curriculum Learning

More Sugar please

sequential social dilemmas

In this post, I explore ideas for extending the Sugarscape environment to create a richer curriculum learning environment for multi-agent reinforcement learning, with a…

Tuesday, June 11, 2024

Risk-constrained Markov decision processes

decision-making under uncertainty

risk-constrained mdps

stochastic optimization

cvar

by Vivek Borkar and Rahul Jain

Tuesday, June 11, 2024

I’ve recently come across a book called “Evolutionary Games and Population Dynamics” by Josef Hofbauer and Karl Sigmund.

Evolutionary Games and Population Dynamics Summary

Sunday, May 12, 2024

Roth Erev learning in Lewis signaling games

44 min

lewis signaling games

I wish now to implement learning in the Lewis signaling game. In the book some reinforcement learning RL algorithms are presented in some detail and a few variations are…

Thursday, May 9, 2024

Signals Experiment

Leaning language games

16 min

some refactoring ideas:

Tuesday, May 7, 2024

ad hoc complex signaling systems

a review and proposal

A deep dive into the complex signaling systems

Sunday, May 5, 2024

emergent complex communications protocols

Shannon Game

12 min

compositionality

communication protocols

In this note I want to start to explore one of my notions of compositionality of Lewis games with another game. In my thinking currently consider at least three senses for…

Thursday, May 2, 2024

“There is a tendency in our planning to confuse the unfamiliar with the improbable. The contingency we have not considered seriously looks strange; what looks strange is…

Urn models using Numpy

Thursday, May 2, 2024

RAD REPL

TODO: 1. [x] basic REPL 2. [x] command based class 3. [x] add task command 4. [x] list tasks command 5. [x] set current task command 6. [x] complete task command

Wednesday, May 1, 2024

Lessons from implementing Sugarscape in Mesa

Mesa

In this post I share some of the lessons I learned from implementing Sugarscape in Mesa. I cover the design decisions I made and how they helped me to overcome some of the…

Sunday, March 31, 2024

Sugar Scapes

Agent movement rule M:

Sunday, March 31, 2024

OCR building blocks

Thursday, March 28, 2024

Agent Based Modeling With MESA

Bayesian Agent

A quick note about Bayesian Agents and how to implement them using the MESA framework in Python.

Thursday, March 21, 2024

For Artificial Intelligence

A definition by Patrick Henry Winston

rumpelstiltskin principle

Patrick Henry Winston provides a definition of AI. How he keeps expanding his definition as he goes along is thing of beauty. It expands organicaly to incorporate new ideas…

Sunday, March 3, 2024

Working of OCR articles by Susmith Reddy

OCR - Brain Dump

Sunday, February 25, 2024

I recently have been annotating speeches following up on the edx a course on Rhetoric.

Rhetoric NLP Tasks

Saturday, February 17, 2024

Some thoughts on the Lewis signaling game

Lewis Game from a Bayesian Perspective

lewis signaling games

Monday, February 12, 2024

Some thoughts on the Lewis signaling game

😁 Quarto 💖 Mermaid🧜 Mindmaps 🧠

Monday, February 12, 2024

Quarto at last supports Mindmap charts using Mermaid charts.

From Blogger to Jekyl and finaly to Quarto.

The Great Migration

some migration notes from Blooger to Jekyl to Quarto blog.

Tuesday, January 30, 2024

This is an obligatory post with executable code.

Post With Code

Sunday, January 28, 2024

Wednesday, February 14, 2024

Engineering Reinforcement Learning Algorithms

As I progressed though the RL specialization I came to realize that the research is mostly about coming up with a new algorithm that works better. This is tricky and so in…

Wednesday, January 10, 2024

Wednesday, January 10, 2024

SuperLearner

18 min

demos

code

SuperLearner is an ensambeleing library.

Understanding Emergent Languages

After a break, once again I’ve been rethinking the Lewis games and settings for emergence of a complex signaling system and their nature of the associated equilibria.

Thursday, January 4, 2024

So I’ve migrated my sample to Quarto – which supports d3.js via Observable and without the need for whack hacks

D3.js in in Quarto Observable

Tuesday, January 2, 2024

Beacuase auto-ml is a Superpower

AutoGluon Cheetsheets

Autogluon is a auto-ml framework, here are three cheetsheet for accellerating data science workloads

Wednesday, December 20, 2023

Dr. Thomas Wiecki’s PyData Global 2023 Recap

Bayesian Marketing Science - Solving Marketing’s 3 Biggest Problems

A recap of Dr. Thomas Wiecki’s talk at PyData Berlin 2023 on how Bayesian statistical modeling can help solve marketing’s biggest problems, enabling efficient…

Tuesday, June 20, 2023

https://stackoverflow.com/questions/30245180/what-do-the-numbers-on-the-progress-bar-mean-in-spark-shell#:~:text=This%20progress%20indicator%20means%20that,number%20of%20task…

Spark Tips: Understanding the Progress Bar

Thursday, June 1, 2023

Pseudocode for common MCMC algorithms

MCMC algorithms

bayesian statistics

mcmc

Pseudocode for common MCMC algorithms

Saturday, April 22, 2023

Quarto loves pseudocode

\begin{algorithm} \caption{Quicksort} \begin{algorithmic} \Procedure{Quicksort}{$A, p, r$} \If{$p < r$} \State $q = $ \Call{Partition}{$A, p, r$} \State…

Tuesday, April 11, 2023

New open-source tools for guiding mitigations in Responsible AI

Responsible AI Mitigations and Tracker

A recap of the Microsoft Responsible AI Toolbox webinar, which introduced two new open-source tools Responsible AI Mitigations, a Python library for implementing…

Wednesday, March 8, 2023

multi-label classification

Text2topic - Leverage reviews data for multi-label topics classification in Booking.com

active learning

streamlit

A recap of the NLP.IL talk by Moran Beladev and Elina Frayerman on building a multilingual multi-label topic classification model for reviews data in Booking.com, using…

Tuesday, February 28, 2023

Tuesday, February 28, 2023

Validating NLP data and models with deepchecks

A recap of the NLP.IL talk by Nir Hutnik on validating NLP data and models, discussing common issues such as data and prediction drift, sample outliers, and error analysis…

Transformations in Linguistic Representation

In computational linguistics, using different representations can shed light on the structure of language. I’m considering how sentences can be depicted using parse trees or…

linguistics

Wednesday, February 22, 2023

Thursday, February 16, 2023

event generator

fake data

Entropy to quantify uncertainty in probabilistic models

entropy for uncertainty quantification

Thursday, September 22, 2022

using entropy to quantify uncertainty in probabilistic models

Loss engineering and uncertainty for multi-task learning

Robust Regression

Monday, September 12, 2022

data science

Understanding the challenges and strategies in multi-task learning

Robust Regression

Monday, September 12, 2022

data science

robust regression

Robust Regression Techniques

Due to a kind grant by the WikiMedia Foundation I was able to attend Wikisym 2012 in Linz Austria what follows is my report on the event.

Wikisym 2012

Tuesday, July 26, 2022

Set Up M1 MacBooks for DS & ML

mac

Set Up M1 MacBooks for DS & ML

Thursday, May 5, 2022

command line cheat sheet macos + zsh + git

command line

21 min

productivity

mac

command line cheat sheet macos + zsh + git

Thursday, May 5, 2022

PDF extraction hacks

pdf

A collection of hacks and tips for extracting content from PDF files, including converting PDFs to images using the pdf2image library in Python, and other techniques for…

Sunday, April 10, 2022

memes a problem-solving approach

Meme bank

A meme is an idea, behavior, style, or usage that spreads from person to person within a culture. A meme bank would be a zoo for cataloging and breeding memes.

Thursday, December 30, 2021

digital marketing agencies.

Getting more from your agency ?

Getting more from your digital marketing agency, my five cents on picking your agency.

Monday, September 27, 2021

Friday, September 24, 2021

Attention for sensor fusion

Attention for sensor fusion

Friday, September 24, 2021

Excel 2019 for Marketing Statistics in pandas

Excel 2019 for Marketing Statistics in pandas

Friday, September 24, 2021

Language models and explainability

Language models and explainability

Advertising Models

Tuesday, September 14, 2021

intelligence

Marketing Research Models

CLV and Buy Till You Drop Models

Customer Lifetime Value - Pareto/NBD (BTYD) Model

Tuesday, September 14, 2021

intelligence

Customer Lifetime Value (CLV) models and Buy Till You Drop (BTYD) models are used to estimate the total value a customer brings to a business over their entire relationship.…

Thursday, September 2, 2021

Storytelling and other essentials

Storytelling and other essentials,

Python Graphs

intelligence

Python Graph Cookbook

WaveNet

The WaveNet paper is kind of old. Yet it seems to come up in various contexts. Some thoughts on this.

What is in a citation?

Creating Citation Web Components

Hackathon session link dumps & notes

Wikimania 2021 Hackathon

Wikipedia Hackathon notes

Friday, August 13, 2021

Inlining Citations for Wikipedia articles

An algorithm for Inlining Citations for Wikipedia articles.

Friday, August 13, 2021

Thursday, August 12, 2021

Transfer learning in NLP

Transfer learning in NLP

A type of Witness and an evolving Idiom

writing better code = writing more readable code.

Wednesday, July 14, 2021

Saturday, February 10, 2024

json-ld

metadata format for linked data

information science

I’ve been excited about JSON-LD, when it came out as it offered a much cleaner way to do SEO. Only later did I realize that it is also a great format to worked with linked…

Thursday, July 1, 2021

TensorFlow probability

In a recent google ai blog post an transformer based autoencoder is shown that can be used to learn and generate document layouts.

bijectors

auto regressive flows

Tuesday, June 1, 2021

A number of djvu docs collected over a long time need to be convert them into pdf.

Ebook Hacks

Saturday, May 29, 2021

Multilevel Models

Different Multilevel Models Types

Sunday, May 16, 2021

The classical Q&A task is fairly easy to solve. But how well does the IR system understand/model the data. The challenge to test this aspect of the system is to provide test…

Sunday, April 24, 2022

Q&A and the Winograd schemas

Tuesday, April 27, 2021

Automatic Summarization Task

automatic abstracting

sentence selection

document screening

sentence significance

comparative evaluation

Concepts, slide commentaries and Lecture notes on Automatic text Summarization by Masa Nekic

Saturday, April 24, 2021

sub-perfect bayesian equilibrium

Saturday, April 24, 2021

Bayesian agents

Let’s try to define a KR framework for a Bayesian agent.

Wednesday, April 14, 2021

Modeling Events

modelling

data science

Modeling Events.

Friday, April 9, 2021

10 Tips To Improve Your Workflow

How to blog like a life-hacker.

Wednesday, April 7, 2021

numpy and scipy break on macos

numpy meltdown

Just a rant at numpy and scipy breaking when I really needed them.

Sunday, November 29, 2020

Deep Learning Intuitions

A collection of intuitions and insights about deep learning, including the functional form of feedforward neural networks with RELU activation, and how they can be…

Sunday, October 25, 2020

brace expansion

A quick introduction to bash brace expansion, a powerful feature that allows you to generate multiple strings from a single pattern, making it easier to create lists of…

Friday, June 12, 2020

Pandas Productivity Challenge?

Just a little rant on Pandas various contexts

Wednesday, March 4, 2020

with the Jupyter local runtime for Colab

How to avoid cross site scripting (XSS) errors

A quick tip on how to avoid cross site scripting (XSS) errors when using the Jupyter local runtime with Google Colab, by configuring the Jupyter notebook server to allow…

Thursday, February 20, 2020

Sunday, November 24, 2019

Docker for data science

Post description

Exploding and vanishing nodes.

One paradgm is that the network could be dynamic. For such a model we want to be able to add and remove nodes. This could be an issue for networks that are engineered to…

brain farts

Wednesday, July 31, 2019

Mitigating Overfitting via Topological Signal Partitioning

Lobeformation: A New Architecture for Deep Learning

deep learning

research note

Inspired by Mixture of Experts (MoE), Lobeformation proposes boosting the Signal-to-Noise Ratio (SNR) by partitioning models into specialized sub-topologies (‘lobes’) that…

Friday, July 19, 2019

text annotation with BRAT

BRAT is a rapid annotation tool. Its old no long maintained - the original developers seem to have moved on. Requests for RTL support have been largely ignored. Some…

Tuesday, January 16, 2018

A/B testing cost and risks?

cro

experimental design

a/b testing

A/B testing cost and risks and some recommendation.

Sunday, July 30, 2017

Sunday, July 30, 2017

Travel checklist

life hacks for travel

Wednesday, December 14, 2016

travel

checklist

This might be useful:

NLP IL F2F Meetup at Intuit

An Overview of Modern Speech Recognition

meetup

Tuesday, November 1, 2016

A recap of the talk on modern speech recognition, which covered the key principles of automatic speech recognition, the impact of self-supervised learning on the field, and…

Wednesday, April 20, 2016

HotJar Heat Map Analysis - Dr. David Darmanin

NLP IL F2F Meetup at Intuit

Efficient Long-Text Understanding with Short-Text Models

meetup

A recap of the talk on efficient long-text understanding with short-text models, which covered the challenges of processing long sequences with transformer-based language…

Sunday, November 1, 2015

Mr Jerbi’s Background:       Come to web analytics from academia Industry and Management - Scheduling and QA.       Recalls that before it was bought by Google Urchin cost…

Using Competitive Analysis to Benchmark Your Marketing Efforts Ariel Rosenstein - Similar Web

organizational behaviour

Monday, April 20, 2015

Ari is the Sr. Marketing Director at Similarweb

Using Competitive Analysis to Benchmark Your Marketing Efforts - Ariel Rosenstein - Similar Web

Monday, April 20, 2015

Analytics Checklist

Saturday, February 7, 2015

analytics

checklists

NLP IL F2F Meetup at Intuit

SCROLLS - Standardized CompaRison Over Long Language Sequences

meetup

Saturday, November 1, 2014

A recap of the talk on SCROLLS, which covered the challenges of evaluating long-range reasoning in language models, the introduction of the SCROLLS benchmark for…

A recap of the NLP IL meetup at Intuit, featuring talks on long-range reasoning in language models, efficient long-text understanding, and modern speech recognition.

NLP IL F2F Meetup at Intuit

The introduction talk of the NLP IL meetup at Intuit, which provided an overview of the meetup’s goals, the speakers, and the topics that would be covered in the subsequent…

Friday, November 1, 2013

life hacks

Health and supplements:

Friday, June 7, 2013

A recap of the NLP IL meetup at Intuit, featuring talks on long-range reasoning in language models, efficient long-text understanding, and modern speech recognition.

NLP IL F2F Meetup at Intuit

A detailed recap of the NLP IL meetup at Intuit, which included talks on long-range reasoning in language models, efficient long-text understanding with short-text models…

Thursday, November 1, 2012

a number of NLP tasks in Python

Text Mining With Python

processing unknown tokens

Tuesday, November 29, 2011

a number of NLP tasks in R

Text Mining With R

Computational Linguistics tasks:

Tuesday, November 29, 2011

Computational Linguistics tasks:

Tidy Text Mining With R

an update on NLP with R

Tuesday, November 29, 2011

We could all use a productivity boost

Time management Tips

Thursday, August 11, 2011

time management

productivity

Effective time management is crucial for success in both personal and professional life. With the right approach, you can achieve more in less time while maintaining a…

Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning

The announcement of the GPT-5 strawberry model has sparked a lot of interest in this paper which seems to be the theory behind Open.ai’s new model.

llms

deliberative planning

heuristic search

Friday, May 9, 2025

Binary Choices with Externalities

🏒 Hockey Helmets, Concealed Weapons, and Daylight Saving

model thinking

Thomas Schelling’s 1973 article
explores binary choices where one person’s decision
affects others, called by economists as externalities

Tuesday, April 1, 2025

Goal Inference as Inverse Planning

How do could RL agents infer the goals of other agents?

Monday, March 31, 2025

Simulation as an engine of physical scene understanding

Model for a cognitive mechanism similar to computer engines that simulate rich physics in video games and graphics, but that uses approximate, probabilistic simulations to…

Monday, March 31, 2025

Learning Shape Priors for Single-View 3D Completion and Reconstruction

Learning priors for Shapes

Saturday, March 29, 2025

🤝 Costly Signaling and Cooperation

teaser for reading this paper

Monday, March 24, 2025

Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling

in (Bansal et al. 2024) the authors consider the trade-offs between generating synthetic data using a stronger but more expensive (SE) model versus a weaker but cheaper (WC)…

Thursday, March 20, 2025

🗣️ Talking to Neighbors: Evolution of Regional Meaning in Communication Games

Zollman’s paper on how adding spatial structure affects the evolutionary outcomes of games with emergent communication and social cooperation

Thursday, March 13, 2025

TheoremLlama An End-To-End Framework to Train a General-Purpose Large Language Model to Become a Lean4 Expert

Proving mathematical theorems using computer-verifiable formal languages like Lean significantly impacts mathematical reasoning. One approach to formal theorem proving…

Monday, March 10, 2025

AI - narration of this paper.

LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

Saturday, February 15, 2025

MambaVision A Hybrid Mamba-Transformer Vision Backbone

In (Hatamizadeh and Kautz 2024), the authors apply the State Space Model (SSM) inherent in recently introduced Mamba architecture, (Gu and Dao 2023), for vision tasks. They…

Saturday, February 15, 2025

On Learning To Become a Successful Loser

Thursday, January 2, 2025

9 min

psychology

A review and study guide of the paper ‘On Learning To Become a Successful Loser: A Comparison of Alternative Abstractions of Learning Processes in the Loss Domain’ by…

Very exciting - this is a paper with a lot of interesting ideas. It comes with a a lot of code in the form of a library called EGG as well as many JuPyteR notebooks. There…

Compositionality and Generalization in Emergent Languages

Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input

Review of ‘Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input’ by Angeliki Lazaridou et al.

Linguistic generalization and compositionality in modern artificial neural networks

A review of the paper ‘Linguistic generalization and compositionality in modern artificial neural networks’ by Marco Baroni.

I think this is an amazing paper. I read it critically and made copious notes to see what I could learn from it. The paper point out some limitations of Lewis referential…

Emergent Communication of Generalizations

Wednesday, October 9, 2024

Evolutionary dynamics of Lewis signaling games: signaling systems vs. partial pooling

evolutionary dynamics

stub

(Huttegger et al. 2010)

Tuesday, October 8, 2024

Why Overfitting Isn’t Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries

summary

This paper, “Why Overfitting Isn’t Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries,” challenges the traditional view that overfitting is inherently…

Tuesday, June 11, 2024

sequential social dilemmas

Generally Capable Agents Emerge from Open-Ended Play

cooperation

markov games

agent based modeling

non-cooperative games

The paper does not present a breakthrough like alpha go zero etc. But it shows very high level of creativity and innovation. I am still a new comer to RL and this paper has…

Monday, June 10, 2024

The Evolution of Coding in signaling games

13 min

This paper considers a setting for the evolution of a complex signaling systems

Monday, June 10, 2024

sequential social dilemmas

️👮 Multi-agent Reinforcement Learning in Sequential Social Dilemmas

cooperation

markov games

agent based modeling

non-cooperative games

In this post, I review the paper ‘Multi-agent Reinforcement Learning in Sequential Social Dilemmas’ by Leibo et al. (2017), which introduces a new class of social dilemmas…

Monday, June 10, 2024

Signals: Signals: Evolution, Learning, and Information

learning language games

65 min

game theory

lewis signaling games

In (Skyrms 2010) philosopher and mathematician Brian Skyrms discusses how one can extend the concept of a signaling games into a full-fledged signaling systems and to some…

book review

Wednesday, May 1, 2024

🦚 Honest Signalling Made Simple

How can we ensure signals are honest in a world where deception is rewarded? This paper delves into the theory of honest signalling in animal behavior, specifically…

Thursday, March 14, 2024

Temporal Abstraction in Reinforcement Learning with the Successor Representation

23 min

This paper review is an extended introduction to temporal abstraction using options. It covers lots of advanced concepts in reinforcement learning that were introduced in…

podcast

Saturday, February 10, 2024

🤝 Diversity Bonuses: How Diverse Teams Achieve Superior Results

teaser for reading this paper

Sunday, October 1, 2023

Variational Inference with Normalizing Flows

The choice of approximate posterior distribution is one of the core problems in variational inference. Most applications of variational inference employ simple families of…

variational inference

normalizing flows

probabilistic modeling

stub

Sunday, June 26, 2022

sense2vec - A Fast and Accurate Method for Word Sense Disambiguation In Neural Word Embeddings

Sense2Vec (Trask et al. 2015) is an interesting deep learning model based on word2vec that can learn more interesting and detailed word vectors from large corpora. Sense2Vec…

Sunday, June 26, 2022

Simplifying Neural Networks by Soft Weight Sharing

A review and study guide of the paper ‘Simplifying Neural Networks by Soft Weight Sharing’ by Nowlan and Hinton, which introduces a method for reducing the complexity of…

Wednesday, June 22, 2022

This Nips 1988 paper is about simplifying neural networks by removing redundant units. The authors’ approach is systematically identifying and removing redundant or…

Skeletonization: A Technique for Trimming the Fat from a Network via Relevance Assessment

Wednesday, June 22, 2022

🧠 Theory-Based Bayesian Models of Inductive Learning and Reasoning

How do humans make powerful generalizations from sparse data when learning about word meanings, unobserved properties, causal relationships, and many other aspects of the…

Thursday, March 10, 2022

ViT — An Image is worth 16x16 words: Transformers for Image Recognition at scale

While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision…

Friday, October 22, 2021

Stochastic Gradient Descent - The good parts

14 min

Stochastic Gradient Descent - The good parts

Language Models Are Open Knowledge Graphs

A review of the arXiv:2010.11967 paper by Chenguang Wang, Xiao Liu, Dawn Song

Wednesday, April 7, 2021

Paper review for the deeplearning.ai NLP specialization

Effective Approaches to Attention-based NMT

Review of the paper on dot product attention for the deeplearning.ai NLP specialization.

Sunday, March 21, 2021

Wednesday, April 7, 2021

NIN — Network in Network

In (Lin et al. 2014) the authors, Lin, Min, Qiang Chen, and Shuicheng Yan, of this paper titled “Network in Network” paper came up with a way of connencting somee ideas on…

Monday, December 31, 2018

Dropout: A Simple Way to Prevent Neural Networks from Overfitting

This paper introduces a simple yet effective regularization technique called dropout, which helps prevent overfitting in deep neural networks by randomly dropping units…

Wednesday, June 15, 2016

Multi-column Deep Neural Networks for Image Classification

In (Cireşan et al. 2012) titled “Multi-column Deep Neural Networks for Image Classification”, the authors, Dan Cireşan, Ueli Meier, Juergen Schmidhuber introduce a…

Sunday, June 12, 2016

Thursday, December 10, 2015

VGGNet: Very Deep Convolutional Networks for Large-Scale Image Recognition

In this paper the authors, investigated the effect of increasing the convolutional network depth on the accuracy in the large-scale image recognition setting. The authors…

ImageNet Classification with Deep Convolutional Neural Networks

(Krizhevsky et al. 2012) is a seminal paper in the field of deep learning. It introduced the AlexNet architecture, which won the ImageNet Large Scale Visual Recognition…

Thursday, December 3, 2015

🧠 Technical Introduction: A primer on probabilistic inference

How to model human cognition using probabilistic inference

Friday, March 20, 2015

Handwriting beautification using token means

In (Zitnick 2013) the author shows how we can use a model for beautifying handwriting. The problem raised is that there is lots of variation in handwriting for a single…

Friday, December 20, 2013

Improving Neural Networks by Preventing Co-Adaptation of Feature Detectors

In (Hinton et al. 2012) titled “Improving Neural Networks by Preventing Co-Adaptation of Feature Detectors”, the authors, Hinton, Geoffrey E., Nitish Srivastava, Alex…

Thursday, March 7, 2013

Algebraic Models for Social Networks

Review and Study Guide

structural equivalence

A comprehensive review, study guide, and deep-dive into the SNA classic ‘Algebraic Models for Social Networks’ by Philippa Pattison, covering key concepts such as algebraic…

Monday, January 4, 1993

CMU - 36-705 - Intermediate Statistics - Lesson 01

Larry Wasserman’s course

Material from Larry Wasserman’s course on Intermediate Statistics at CMU. This course covers a wide range of topics in statistical inference, including estimation…

Tuesday, June 10, 2025

CMU - 36-705 - Intermediate Statistics - Lesson 01

Larry Wasserman’s course

Material from Larry Wasserman’s course on Intermediate Statistics at CMU. This course covers a wide range of topics in statistical inference, including estimation…

Tuesday, June 10, 2025

Statistical Methods for Machine Learning

Larry Wasserman’s course

A review of Larry Wasserman’s course on Statistical Methods for Machine Learning, covering key concepts and lectures on various topics in machine learning and statistics.

Tuesday, June 10, 2025

All of nonparametric statistics

book review

46 min

A brief review of nonparametric statistical methods.

Saturday, June 10, 2006