Oren Bochman’s Blog

Vibe coding GPT5 Edition
A few days back, a friend discussed on FB his attempt at a mathematical puzzle and the outcomes of using a commercial LLM and a self-hosted LLM to solve it, and he then…
Oren Bochman
Thursday, September 25, 2025
 
Tree Attention: Topology-Aware Decoding for Long-Context Attention on GPU Clusters
in (Shyam et al. 2024) the authors propose a new algorithm for parallelizing attention computation across multiple GPUs. This enables cross-device decoding to be performed…
Oren Bochman
Monday, May 19, 2025

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.
Oren Bochman
Friday, May 9, 2025

Langtalks Resources # 43
generative AI
podcasts

Exploring GenAI-powered tools

Oren Bochman
Thursday, April 3, 2025

Base line Morphology Model
code

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

Oren Bochman
Wednesday, April 2, 2025

Research Questions
research
emergent languages
planning
grounding

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

Oren Bochman
Wednesday, April 2, 2025

🏒 Hockey Helmets, Concealed Weapons, and Daylight Saving – Binary Choices with Externalities
review
model thinking

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

Oren Bochman
Tuesday, April 1, 2025

Goal Inference as Inverse Planning
review
paper
podcast
reinforcement learning

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

Oren Bochman
Monday, March 31, 2025

Simulation as an engine of physical scene understanding
review
podcast

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…

Oren Bochman
Monday, March 31, 2025

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

Learning priors for Shapes

Oren Bochman
Saturday, March 29, 2025

🤝 Costly Signaling and Cooperation
review
signaling
cooperation
economics
podcast

teaser for reading this paper

Oren Bochman
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)…
Oren Bochman
Thursday, March 20, 2025

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

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

Oren Bochman
Thursday, March 13, 2025

The roles of Partial pooling and mixed strategies in the Lewis signaling game
emergent languages
lewis signaling game
game theory
complex signaling system

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

Oren Bochman
Tuesday, March 11, 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…
Oren Bochman
Monday, March 10, 2025

LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
In (BehnamGhader et al. 2024) the authors consider using LLMs which are mostly decoder only transformers as text encoders. This allows them to use the LLMs for NLP tasks…
Oren Bochman
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…
Oren Bochman
Saturday, February 15, 2025

Emergent Languages
emergent languages
reinforcement learning
information theory
linguistics
complex signaling system

A working paper on emergent languages

Oren Bochman
Tuesday, January 14, 2025

Planning in the Complex Lewis Game
compositionality
emergent languages
reinforcement learning
transfer learning
information theory
linguistics
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…
Oren Bochman
Tuesday, January 14, 2025

The Referential Lewis Signaling Game
reinforcement learning
complex signaling system
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…
Oren Bochman
Tuesday, January 14, 2025

A garden of forking paths
I’ve been thinking how to visualize learning the complex lewis games.
Oren Bochman
Saturday, January 11, 2025

Complex Signals Questions
emergent languages

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

Oren Bochman
Monday, January 6, 2025

The Many Path To A Signaling System
signaling systems
lewis signaling game
reinforcement learning
bayesian games
information theory
game theory
bayesian reinforcement learning
emergent languages
complex signaling system
The Garden of Forking Paths — Jorge Luis Borges
Oren Bochman
Sunday, January 5, 2025

Off-Policy Learning
reinforcement learning
off-policy learning
deep learning
machine learning
artificial intelligence
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…
Oren Bochman
Saturday, January 4, 2025

On Learning To Become a Successful Loser
RL
Reinforcement Learning
I tracked this paper due to it being highlighted in (Skyrms 2010) as the source of a model that learns a signaling systems faster. I got me started with the loss domain. I…
Oren Bochman
Thursday, January 2, 2025

Rethinking Signaling systems via the lens of compositionality
reinforcement learning
emergent languages
complex signaling system
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…
Oren Bochman
Thursday, January 2, 2025

Books, Courses Tools
news
An Introduction to Statistical Learning by Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani.
Oren Bochman
Wednesday, January 1, 2025

Compositionality and Generalization in Emergent Languages
review
compositionality
neural networks
signaling systems
language evolution
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…
Oren Bochman
Wednesday, January 1, 2025

Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
review
compositionality
neural networks
signaling systems
language evolution
complex signaling system

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

Oren Bochman
Wednesday, January 1, 2025

Lewis Signaling Game for PettingZoo
review
compositionality
neural networks
signaling systems
language evolution
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.
Oren Bochman
Wednesday, January 1, 2025

Linguistic generalization and compositionality in modern artificial neural networks
review, compositionality neural networks signaling systems language evolution

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

Oren Bochman
Wednesday, January 1, 2025

Villeny pure and simple
screenwriting
patterns
noir
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…
Oren Bochman
Thursday, December 12, 2024

Misbehavior of Markets and Scaling in financial prices 1-4
Scaling Laws
Fractals
Financial Markets
Time series
Reviews
Popular Science

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

Oren Bochman
Monday, December 2, 2024

Scaling in financial prices 4
Scaling Laws
Fractals
Financial Markets
Time series
Reviews
“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.”
Oren Bochman
Sunday, December 1, 2024

Scaling in financial prices 3
Scaling Laws
Fractals
Financial Markets
Time series
Reviews
In the paper “Scaling in financial prices: III. Cartoon Brownian Motions in Multifractal Time” (Mandelbrot 2001) Mandelbrot continus his exploration of fractal and…
Oren Bochman
Saturday, November 30, 2024

Scaling in financial prices 2
Scaling Laws
Fractals
Financial Markets
Time series
Reviews
Popular Science
In the paper “Scaling in financial prices: II. Multifractals and the star equation” (Mandelbrot 2001) Mandelbrot continus his exploration of financial price scaling. He…
Oren Bochman
Friday, November 29, 2024

Scaling in financial prices 1
Scaling Laws
Fractals
Financial Markets
Time series
Reviews
Popular Science
“The ideal market completely disregards those spikes—but a realistic model cannot.”
Oren Bochman
Thursday, November 28, 2024

Vitter’s Algorithm
algorithm
compositionality
signaling systems
language evolution

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

Oren Bochman
Friday, October 11, 2024

Emergent Communication of Generalizations
signaling games
stub
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…
Oren Bochman
Wednesday, October 9, 2024

Evolutionary dynamics of Lewis signaling games: signaling systems vs. partial pooling
signaling games
evolutionary dynamics
complex signaling system
stub
(Huttegger et al. 2010)
Oren Bochman
Tuesday, October 8, 2024

TL-DR rethinking 💭 topological alignment
NLP
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…
Oren Bochman
Tuesday, October 1, 2024

LLM the good the bad and the ugly
NLP
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…
Oren Bochman
Monday, September 30, 2024

LLM and the missing link
wikipedia
LLM
AI
agents
wikidata
citations
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.
Oren Bochman
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…
Oren Bochman
Friday, September 27, 2024

Deduction Evaluation
logic
reasoning
deduction
goal create a deduction data-set for evaluating reasoning capabilities of a man and machine.
Oren Bochman
Thursday, September 26, 2024

Fine-tune llm for Style and Grammar advice.
NLP

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

Oren Bochman
Wednesday, September 25, 2024

Is compositionality overrated? The view from language emergence
review
compositionality
neural networks
signaling systems
language evolution
complex signaling system

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

Oren Bochman
Sunday, September 1, 2024

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.
Oren Bochman
Monday, August 26, 2024

Stumpy
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.
Oren Bochman
Thursday, August 8, 2024

replay buffer questions
we should aim to keep full options traces in the buffer
Oren Bochman
Tuesday, July 2, 2024

two ideas on generalization
The first idea comes from looking at regression and hyperparameter optimization tasks
Oren Bochman
Monday, July 1, 2024

Mesa & RL
Ifs we can store state, action, reward trajectories (to a file) this would facilitate
Oren Bochman
Tuesday, June 25, 2024

zero inflated data
Zero inflated data is a type of data that has a large number of zero values.
Oren Bochman
Sunday, June 23, 2024

readings in rl
rl
reinforcement learning
papers
notes
reading
rl-papers
rl-algorithms
rl-resources
A list of RL-papers and resources that I have read or plan to read.
Oren Bochman
Tuesday, June 18, 2024

Hyperparameter Optimization
one the idea is for a set of Hyperparameters to find the best one.
Oren Bochman
Thursday, June 13, 2024

More Sugar please
sugarscape
multi-agent simulation
agent-based modeling
agent-based social simulation
multi-agent reinforcement learning
sequential social dilemmas
cooperation
Markov games
non-cooperative games
complex signaling system

Exploring new ideas for enhancing the Sugarscape environment

Oren Bochman
Tuesday, June 11, 2024

Risk-constrained Markov decision processes
paper review
risk-constrained MDPs
stochastic optimization
CVaR
decision-making under uncertainty
by Vivek Borkar and Rahul Jain
Oren Bochman
Tuesday, June 11, 2024
 
Why Overfitting Isn’t Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries
This paper, “Why Overfitting Isn’t Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries,” challenges the traditional view that overfitting is inherently…
Oren Bochman
Tuesday, June 11, 2024
 
Generally Capable Agents Emerge from Open-Ended Play
paper review
multi-agent reinforcement learning
sequential social dilemmas
sequential social dilemmas
cooperation
Markov games
agent-based social simulation
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…
Oren Bochman
Monday, June 10, 2024

The Evolution of Coding in signaling games
review
reinforcement learning
signaling games
complex signaling system
This paper considers a setting for the evolution of a complex signaling systems
Oren Bochman
Monday, June 10, 2024
 
️👮 Multi-agent Reinforcement Learning in Sequential Social Dilemmas
paper review
multi-agent reinforcement learning
sequential social dilemmas
sequential social dilemmas
cooperation
Markov games
agent-based social simulation
non-cooperative games
Matrix games like Prisoner’s Dilemma have guided research on social dilemmas for decades. However, they necessarily treat the choice to cooperate or defect as an atomic…
Oren Bochman
Monday, June 10, 2024

Evolutionary Games and Population Dynamics Summary
mathematics
evolutionary games
population dynamics
Lotka-Volterra
dynamical systems
logistic growth
predator-prey model
I’ve recently come across a book called “Evolutionary Games and Population Dynamics” by Josef Hofbauer and Karl Sigmund.
Oren Bochman
Sunday, May 12, 2024

Roth Erev learning in Lewis signaling games
signaling games
reinforcement learning
Lewis signaling games
language evolution
signaling systems
neural networks
emergent languages
deep learning
complex signaling system
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…
Oren Bochman
Thursday, May 9, 2024

Signals Experiment
some refactoring ideas:
Oren Bochman
Tuesday, May 7, 2024

ad hoc complex signaling systems
signaling games
emergent languages
complex signaling system

A deep dive into the complex signaling systems

Oren Bochman
Sunday, May 5, 2024

Shannon Game
signaling games
compositionality
communication protocols
emergent languages
complex signaling system
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…
Oren Bochman
Thursday, May 2, 2024

Urn models using Numpy
probability
urn models
emergent languages
“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…
Oren Bochman
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
Oren Bochman
Wednesday, May 1, 2024

Signals: Signals: Evolution, Learning, and Information
game theory
Lewis signaling games
reinforcement learning
emergent languages
complex signaling system
book review
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…
Oren Bochman
Wednesday, May 1, 2024

Mesa Lessons
reinforcement learning
mesa
agent-based modeling
sugarscape
Implementing Sugarscape has some interesting lessons.
Oren Bochman
Sunday, March 31, 2024

Sugar Scapes
Agent movement rule M:
Oren Bochman
Sunday, March 31, 2024

OCR building blocks
code
buggy code
TODO
OCR
split into:
Oren Bochman
Thursday, March 28, 2024

🦚 Honest Signalling Made Simple
review
podcast
game theory
signaling systems

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…

Oren Bochman
Thursday, March 14, 2024

A definition by Patrick Henry Winston
kb-ai
speaking
rhetoric
awsome-learning
ai
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…

Oren Bochman
Sunday, March 3, 2024

OCR - Brain Dump
linkage
brain dump
OCR
Working of OCR articles by Susmith Reddy
Oren Bochman
Sunday, February 25, 2024

Rhetoric NLP Tasks
rhetoric
nlp
ideas
I recently have been annotating speeches following up on the edx a course on Rhetoric.
Oren Bochman
Saturday, February 17, 2024

Lewis Game from a Bayesian Perspective
signaling games
Lewis signaling games
emergent languages
complex signaling system

Some thoughts on the Lewis signaling game

Oren Bochman
Monday, February 12, 2024

😁 Quarto 💖 Mermaid🧜 Mindmaps 🧠

Quarto at last supports Mindmap charts using Mermaid charts.

Oren Bochman
Monday, February 12, 2024

Temporal Abstraction in Reinforcement Learning with the Successor Representation
review
Reinforcement learning
podcast
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…
Oren Bochman
Saturday, February 10, 2024

man standing beside pipes by Kaique Rocha

The Great Migration
quarto
blogging
code

some migration notes from Blooger to Jekyl to Quarto blog.

Oren Bochman
Tuesday, January 30, 2024

Post With Code
news
code
analysis
This is an obligatory post with executable code.
Oren Bochman
Sunday, January 28, 2024

Engineering Reinforcement Learning Algorithms
emergent languages
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…
Oren Bochman
Wednesday, January 10, 2024

SuperLearner
demos
code
r

SuperLearner is an ensambeleing library.

Oren Bochman
Wednesday, January 10, 2024

Understanding Emergent Languages
NLP
language evolution
emergent languages
complex signaling system
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.
Oren Bochman
Thursday, January 4, 2024

D3.js in in Quarto Observable
code
d3.js
observable.js
So I’ve migrated my sample to Quarto – which supports d3.js via Observable and without the need for whack hacks
Oren Bochman
Tuesday, January 2, 2024

AutoGluon Cheetsheets
cheatsheets
code
data science
auto-ml

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

Oren Bochman
Wednesday, December 20, 2023

🤝 Diversity Bonuses: How Diverse Teams Achieve Superior Results
review
podcast
model-thinking

teaser for reading this paper

Oren Bochman
Sunday, October 1, 2023

Spark Tips
BigData
Spark
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…
Oren Bochman
Thursday, June 1, 2023

Summary: Synthesis and Stabilization of Complex Behaviors through Online Trajectory Optimization
Reinforcement Learning
Model Based RL
Model Predictive Control
MPC
LQR
MuJoCo
iLQG
Cost Functions
Iterative LQG Method
Numerical Methods
Optimal Control
Trajectory Optimization
Complex Behaviors
Humanoid Robots
Physics Simulator
Real-Time Control
Robustness
Planning
Robtics
Coursera

This paper was referenced by Drew Bagnell in the Coursera RL specilization for using simple quadratic approximation to learn a model in a continous control setting. The…

Oren Bochman
Thursday, June 1, 2023

MCMC algorithms
Bayesian statistics
MCMC

Pseudocode for common MCMC algorithms

Oren Bochman
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…
Oren Bochman
Tuesday, April 11, 2023

Text2topic Leverage reviews data for multi-label topics classification in Booking.com
Having millions of customer reviews, we would like to better understand them and leverage this data for different use cases. For example, finding popular activities per…
Oren Bochman
Tuesday, February 28, 2023

Validating NLP data and models
NLP data, and unstructured data in general, is very hard to validate. Validating NLP data is a real challenge, as actions such as statistical analysis and segmentation…
Oren Bochman
Tuesday, February 28, 2023

Transformations in Linguistic Representation
nlp
linguistics
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…
Oren Bochman
Wednesday, February 22, 2023

event generator
news
code
analysis
prompt engineering

fake data

Oren Bochman
Thursday, February 16, 2023

OLS regression From Scratch
data science
ml
algorithms
OLS regression is a method for estimating the parameters of a linear regression model. The goal is to find the line that best fits a set of data points. The line is…
Oren Bochman
Wednesday, February 1, 2023

entropy for uncertainty quantification

using entropy to quantify uncertainty in probabilistic models

Oren Bochman
Thursday, September 22, 2022

Loss engineering and uncertainty for multi-task learning
data science

Understanding the challenges and strategies in multi-task learning

Oren Bochman
Monday, September 12, 2022

Robust Regression
Data science
Robust regression

Robust Regression Techniques

Oren Bochman
Monday, September 12, 2022

Some dynamics of signaling games
draft
review

teaser for reading this paper

Oren Bochman
Wednesday, August 10, 2022

wikisym 2012 logo

Wikisym 2012
report
wikisym
conference
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.
Oren Bochman
Tuesday, July 26, 2022

figure 1

Variational Inference with Normalizing Flows
variational inference
normalizing flows
probabilistic modeling
stub
The choice of approximate posterior distribution is one of the core problems in variational inference. Most applications of variational inference employ simple families of…
Oren Bochman
Sunday, June 26, 2022
 
sense2vec - A Fast and Accurate Method for Word Sense Disambiguation In Neural Word Embeddings
Sense2Vec (Trask, Michalak, and Liu 2015) is an interesting deep learning model based on word2vec that can learn more interesting and detailed word vectors from large…
Oren Bochman
Sunday, June 26, 2022
 
Simplifying Neural Networks by soft weight sharing
neural networks
regularization
stub
This paper was mentioned in Geoffrey Hinton’s Coursera course as a way to simplify neural networks.
Oren Bochman
Wednesday, June 22, 2022

Skeletonization: A Technique for Trimming the Fat from a Network via Relevance Assessment
neural networks
pruning
This Nips 1988 paper is about simplifying neural networks by removing redundant units. The authors’ approach is systematically identifying and removing redundant or…
Oren Bochman
Wednesday, June 22, 2022

Set Up M1 MacBooks for DS & ML
mac

Set Up M1 MacBooks for DS & ML

Oren Bochman
Thursday, May 5, 2022

command line
productivity
mac

command line cheat sheet macos + zsh + git

Oren Bochman
Thursday, May 5, 2022

🧠 Theory-Based Bayesian Models of Inductive Learning and Reasoning
review
induction

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

Oren Bochman
Thursday, March 10, 2022

FontCLIP: A Semantic Typography Visual-Language Model for Multilingual Font Applications
paper-review
typography
vision-language-model
CLIP
multilingual
cross-lingual
semantic attributes
Acquiring the desired font for various design tasks can be challenging and requires professional typographic knowledge. While previous font retrieval or generation works…
Oren Bochman
Tuesday, February 15, 2022

Meme bank
meme
TRIZ
tetrad
brainstorm
algorithm

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.

Oren Bochman
Thursday, December 30, 2021

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…
Oren Bochman
Friday, October 22, 2021

Getting more from your agency ?
marketing
digital marketing
agency

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

Oren Bochman
Monday, September 27, 2021

Attention for sensor fusion
attention
data science
marketing
sensor fusion
statistics
autoecoder

Attention for sensor fusion

Oren Bochman
Friday, September 24, 2021

Excel 2019 for Marketing Statistics in pandas
data science
statistics
marketing

Excel 2019 for Marketing Statistics in pandas

Oren Bochman
Friday, September 24, 2021

Language models and explainability
data science
statistics
marketing
NLP

Language models and explainability

Oren Bochman
Friday, September 24, 2021

Advertising Models
PPC
data science
digital marketing
quantitative marketing
intelligence

Marketing Research Models

Oren Bochman
Tuesday, September 14, 2021

Customer Lifetime Value - Pareto/NBD (BTYD) Model
PPC
data science
digital marketing
quantitative marketing
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.…

Oren Bochman
Tuesday, September 14, 2021

Storytelling and other essentials
data science
statistics
marketing
war story

Storytelling and other essentials,

Oren Bochman
Thursday, September 2, 2021

Python Graphs
PPC
code
data science
digital marketing
quantitative marketing
intelligence

Python Graph Cookbook

Oren Bochman
Sunday, August 29, 2021

Stochastic Gradient Descent - The good parts

Stochastic Gradient Descent - The good parts

Oren Bochman
Sunday, August 29, 2021

WaveNet
deep learning
data science
NLP

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

Oren Bochman
Sunday, August 29, 2021

What is in a citation?

Creating Citation Web Components

Oren Bochman
Sunday, August 29, 2021

Hackathon session link dumps & notes
modelling
chat bot
wikipedia
support

Wikipedia Hackathon notes

Oren Bochman
Friday, August 13, 2021

Inlining Citations for Wikipedia articles
modelling
chat bot
wikipedia
support

An algorithm for Inlining Citations for Wikipedia articles.

Oren Bochman
Friday, August 13, 2021

Transfer learning in NLP
modelling
chat bot
wikipedia
support

Transfer learning in NLP

Oren Bochman
Friday, August 13, 2021

A type of Witness and an evolving Idiom

writing better code = writing more readable code.

Oren Bochman
Wednesday, July 14, 2021

json-ld
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…

Oren Bochman
Thursday, July 1, 2021

TensorFlow probability
ML
AI
NLP
Bijectors
Auto Regressive Flows
In a recent google ai blog post an transformer based autoencoder is shown that can be used to learn and generate document layouts.
Oren Bochman
Tuesday, June 1, 2021

Ebook Hacks
hacks
ebooks
resolution
A number of djvu docs collected over a long time need to be convert them into pdf.
Oren Bochman
Saturday, May 29, 2021

Multilevel Models
NLP
notes
summarization task
lecture notes
bibliography
literature review

Different Multilevel Models Types

Oren Bochman
Sunday, May 16, 2021

Q&A and the Winograd schemas
idea
NLP
intelligence
resolution
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…
Oren Bochman
Tuesday, April 27, 2021

Automatic Summarization Task
NLP
notes
summarization task
lecture notes
bibliography
literature review
video
automatic extracting
automatic abstracting
sentence selection
document screening
sentence significance
relevance
content words
key words
pragmatic words
cue words
title words
sentence location
research methodology
parameterization
comparative evaluation

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

Oren Bochman
Saturday, April 24, 2021

Bayesian agents
idea
game theory
bayesian games
sub-perfect bayesian equilibrium
Let’s try to define a KR framework for a Bayesian agent.
Oren Bochman
Wednesday, April 14, 2021

Modeling Events
modelling
data science

Modeling Events.

Oren Bochman
Friday, April 9, 2021

10 Tips To Improve Your Workflow

How to blog like a life-hacker.

Oren Bochman
Wednesday, April 7, 2021

Language Models Are Open Knowledge Graphs
paper
language models
deep learning
data mining
NLP

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

Oren Bochman
Wednesday, April 7, 2021

Effective Approaches to Attention-based NMT
nlp
coursera
notes
paper
attention
deep learning
literature review

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

Oren Bochman
Sunday, March 21, 2021

numpy melt down
python
macos
bugs

numpy melt down.

Oren Bochman
Sunday, November 29, 2020

Deep Learning Intuitions
intuition
data analysis
python
deep learning
Stacking n-layers RELUS in a feed forward neural network is functionally equivalent to a set of nested inequalities.
Oren Bochman
Sunday, October 25, 2020

brace expansion
bash
command line
linux
  • the bash shell supports brace expansion.
  • the idea is that the string before and after are concatenated with element in the braces
echo "you won "{two,three,four}"…
Oren Bochman
Friday, June 12, 2020

Pandas Productivity Challenge?
data-science
python
data-wrangling

Just a little rant on Pandas various contexts

Oren Bochman
Wednesday, March 4, 2020

How to avoid cross site scripting (XSS) errors with the Jupyter local runtime for Colab
data-science
ds-tips
Google-colab
colab
jupyter
python
R
tool-tip
data analysis
XSS
So the trick is
Oren Bochman
Thursday, February 20, 2020

Docker for data science
docker
conternerization
data analysis

Post description

Oren Bochman
Sunday, November 24, 2019

Exploding and vanishing nodes.
brain farts
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…

Oren Bochman
Wednesday, July 31, 2019

NIN — Network in Network
In (Lin, Chen, and Yan 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…
Oren Bochman
Monday, December 31, 2018

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…
Oren Bochman
Tuesday, January 16, 2018

A/B testing cost and risks?
PPC,
data science,
digital marketing,
quantitative marketing,
CRO,
experimental design,
A/B testing

A/B testing cost and risks and some recommendation.

Oren Bochman
Sunday, July 30, 2017

Travel checklist
travel
checklist
This might be useful:
Oren Bochman
Wednesday, December 14, 2016

Dropout in a nutshell

Dropout: A Simple Way to Prevent Neural Networks from Overfitting
paper review

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

Oren Bochman
Wednesday, June 15, 2016

Multi-column Deep Neural Networks for Image Classification
In (Cireşan, Meier, and Schmidhuber 2012) titled “Multi-column Deep Neural Networks for Image Classification”, the authors, Dan Cireşan, Ueli Meier, Juergen Schmidhuber…
Oren Bochman
Sunday, June 12, 2016

HotJar Heat Map Analysis - Dr. David Darmanin
Conference
Analytics
Heat Maps
What are Heatmaps
Oren Bochman
Wednesday, April 20, 2016

architecture

VGGNet: Very Deep Convolutional Networks for Large-Scale Image Recognition
Deep Learning
Computer Vision
Reviews

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…

Oren Bochman
Thursday, December 10, 2015
 
ImageNet Classification with Deep Convolutional Neural Networks
(Krizhevsky, Sutskever, and Hinton 2012) is a seminal paper in the field of deep learning. It introduced the AlexNet architecture, which won the ImageNet Large Scale Visual…
Oren Bochman
Thursday, December 3, 2015

Using Competitive Analysis to Benchmark Your Marketing Efforts Ariel Rosenstein - Similar Web
all things data
conference
analytics
orgenizational behviour
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…
Oren Bochman
Monday, April 20, 2015

Using Competitive Analysis to Benchmark Your Marketing Efforts - Ariel Rosenstein - Similar Web
Marketing
Analytics
Competitive Analysis
Ari is the Sr. Marketing Director at Similarweb
Oren Bochman
Monday, April 20, 2015

🧠 Technical Introduction: A primer on probabilistic inference
draft
review
induction

How to model human cognition using probabilistic inference

Oren Bochman
Friday, March 20, 2015

Analytics Checklist
Oren Bochman
Saturday, February 7, 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…
Oren Bochman
Friday, December 20, 2013

life hacks
life
hacks
health
productivity
Health and supplements:
Oren Bochman
Friday, June 7, 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…
Oren Bochman
Thursday, March 7, 2013

Text Mining With Python
python
NLP
text mining
code
processing unknown tokens
Oren Bochman
Tuesday, November 29, 2011

Text Mining With R
R
NLP
text Mining
code
Computational Linguistics tasks:
Oren Bochman
Tuesday, November 29, 2011

Tidy Text Mining With R
R
NLP
Text Mining
tidyverse
code
Computational Linguistics tasks:
Oren Bochman
Tuesday, November 29, 2011

Photo by Pixabay

Time management Tips
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…

Oren Bochman
Thursday, August 11, 2011
No matching items