Oren Bochman’s Blog
Home
About
Source Code
Report a Bug
Archive
Paper Reviews
Notes
Paper Reviews
Reviews
1973
🏒 Hockey Helmets, Concealed Weapons, and Daylight Saving – Binary Choices with Externalities
1989
Skeletonization: A Technique for Trimming the Fat from a Network via Relevance Assessment
1991
Simplifying Neural Networks by soft weight sharing
1998
On Learning To Become a Successful Loser
1999
2000
🤝 Costly Signaling and Cooperation
2005
🗣️ Talking to Neighbors: Evolution of Regional Meaning in Communication Games
2006
title
🧠 Technical Introduction: A primer on probabilistic inference
🧠 Theory-Based Bayesian Models of Inductive Learning and Reasoning
2007
The Evolution of Coding in signaling games
Goal Inference as Inverse Planning
2008
2009
Evolutionary dynamics of Lewis signaling games: signaling systems vs. partial pooling
2010
Signals: Signals: Evolution, Learning, and Information
2011
2012
Multi-column Deep Neural Networks for Image Classification
Improving Neural Networks by Preventing Co-Adaptation of Feature Detectors
ImageNet Classification with Deep Convolutional Neural Networks
2013
Simulation as an engine of physical scene understanding
NIN — Network in Network
Handwriting beautification using token means
2014
Dropout: A Simple Way to Prevent Neural Networks from Overfitting
Some dynamics of signaling games
VGGNet: Very Deep Convolutional Networks for Large-Scale Image Recognition
2015
Variational Inference with Normalizing Flows
sense2vec - A Fast and Accurate Method for Word Sense Disambiguation In Neural Word Embeddings
2016
Shen Parsing RL
2017
🤝 Diversity Bonuses: How Diverse Teams Achieve Superior Results
️👮 Multi-agent Reinforcement Learning in Sequential Social Dilemmas
2018
Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
Learning Shape Priors for Single-View 3D Completion and Reconstruction
2019
Linguistic generalization and compositionality in modern artificial neural networks
2020
ViT — An Image is worth 16x16 words: Transformers for Image Recognition at scale
Compositionality and Generalization in Emergent Languages
Why Overfitting Isn’t Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries
2021
Generally Capable Agents Emerge from Open-Ended Play
Emergent Communication of Generalizations
2022
2023
Temporal Abstraction in Reinforcement Learning with the Successor Representation
🦚 Honest Signalling Made Simple
2024
Tree Attention: Topology-Aware Decoding for Long-Context Attention on GPU Clusters
FontCLIP: A Semantic Typography Visual-Language Model for Multilingual Font Applications
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
MambaVision A Hybrid Mamba-Transformer Vision Backbone
Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning
2BP: 2-Stage Backpropagation
TheoremLlama An End-To-End Framework to Train a General-Purpose Large Language Model to Become a Lean4 Expert
Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling
2025
Meta
Why bother reviewing papers?
Blog
Posts
2011
Tidy Text Mining With R
Text Mining With Python
Time management Tips
Text Mining With R
2012
Wikisym 2012
2013
life hacks
2014
2014 10 06 FinTech
2015
2015 02 07 Analytics Checklist
Analytics Checklist
2015 02 07 Optimal Bidding
2015 04 20 All Things Data
HotJar Heat Map Analysis - Dr. David Darmanin
Using Competitive Analysis to Benchmark Your Marketing Efforts Ariel Rosenstein - Similar Web
Using Competitive Analysis to Benchmark Your Marketing Efforts - Ariel Rosenstein - Similar Web
2016
Travel checklist
2017
2017 07 30 Experimental Design
A/B testing cost and risks?
2018
2018 01 16 BRAT
text annotation with BRAT
2019
2019 07 31 Exploding and Vanishing Nodes
Exploding and vanishing nodes.
2019 11 24 Keys to the Kingdom Extracting Api Keys from a Json File with Jq
Docker for data science
2020
brace expansion
2020 02 20 Avoid Cross Site Scriptin Errors with a Jupyter Local Runtime
How to avoid cross site scripting (XSS) errors with the Jupyter local runtime for Colab
2020 03 04 Pandas Challanges
Pandas Productivity Challenge?
2020 04 10 Pdf Extraction
2020 10 25 Deep Learning Relu Intutions
Deep Learning Intuitions
2020 11 29 Numpy Meltdown
numpy melt down
2020 12 30 Meme Bank
Meme bank
2021
Transfer learning in NLP
Excel 2019 for Marketing Statistics in pandas
Inlining Citations for Wikipedia articles
WaveNet
Storytelling and other essentials
Getting more from your agency ?
What is in a citation?
Stochastic Gradient Descent - The good parts
2021 03 21 Review of Effective Approaches to Attention Based Neural Machine Translation
Effective Approaches to Attention-based NMT
2021 03 21 Review of Language Models Are Open Knowledge Graphs
Language Models Are Open Knowledge Graphs
2021 04 03 Ruby Installation Snafus
Jekyll take 3
2021 04 06 Jekyll Mathjax 3.0 Fix
MathJax 3 fix for Jekyll hosted on Github pages
2021 04 07 Linkage
Linkage 2021-04-07
2021 04 07 Ten Tips to Improve Your Workflow
10 Tips To Improve Your Workflow
2021 04 08 Other People Problems
2021 04 09 Modeling Events
Modeling Events
2021 04 11 Lexical and Semantic Features
2021 04 24 Summerization
Automatic Summarization Task
2021 04 25 Bayesian Agent
Bayesian agents
2021 04 27 Wingrad Schema
Q&A and the Winograd schemas
2021 05 16 Mulitlevel Models
Multilevel Models
2021 05 18 Bayesian Betting
2021 05 29 Djvu to Pdf
Ebook Hacks
2021 06 10 Layout Models
TensorFlow probability
2021 07 01 Json Ld
json-ld
2021 07 14 Type Witness Evolving Idiom
A type of Witness and an evolving Idiom
2021 08 13 Hackathon Notes
Hackathon session link dumps & notes
2021 09 16 Python Graphs
Python Graphs
2021 11 08 Advanced ML Workflows
2021 11 12 Language Models and Explainability
Language models and explainability
2021 12 07 Attention for Sensor Fusion
Attention for sensor fusion
2022
2022 03 05 M1
Set Up M1 MacBooks for DS & ML
2022 04 01 Bandits
2022 05 05 Command Line
command line
2022 09 12 Robust Regression
2022 09 16 Adaptive Learning Rate
2022 09 16 Loss Engineering
2022 09 22 Entropy for Uncertainty Quantification
entropy for uncertainty quantification
2023
AutoGluon Cheetsheets
The Great Migration
2023-01-11-NLP-IL-Intuit Meetup
2023 02 01 Ds from Scratch
OLS regression From Scratch
2023 02 20 Ts Nonlinear
2023 02 28 NLP.IL Booking.com
Text2topic Leverage reviews data for multi-label topics classification in Booking.com
Validating NLP data and models
2023 03 01 Braindump
2023 03 01 Spark Emr
2023 03 08 Responsible AI
2023 04 11 Quarto Loves Psdocode
Quarto loves pseudocode
2023 04 22 Mcmc Algs
MCMC algorithms
2023 06 01 Spark
Spark Tips
2023 06 01 Synthesis and Stabilization
Summary: Synthesis and Stabilization of Complex Behaviors through Online Trajectory Optimization
S3 Series
2024
readings in rl
LLM and the missing link
ad hoc complex signaling systems
Shannon Game
OCR - Brain Dump
TL-DR rethinking 💭 topological alignment
two ideas on generalization
Deduction Evaluation
SuperLearner
Evolutionary Games and Population Dynamics Summary
D3.js in in Quarto Observable
A definition by Patrick Henry Winston
Is compositionality overrated? The view from language emergence
Vitter’s Algorithm
Lewis Signaling Game for PettingZoo
NLP with RL
Signals Experiment
Lewis Game from a Bayesian Perspective
Stumpy
Understanding Emergent Languages
More Sugar please
event generator
replay buffer questions
RAD REPL
Villeny pure and simple
OCR building blocks
Post With Code
LLM the good the bad and the ugly
Mesa Lessons
Transformations in Linguistic Representation
😁 Quarto 💖 Mermaid🧜 Mindmaps 🧠
Six quick tips to improve modeling
Fine-tune llm for Style and Grammar advice.
Sugar Scapes
2024 02 01 Quarto Bootstrap
2024 02 19 Rhetoric
Rhetoric NLP Tasks
2024 05 02 Signaling Games Tikz
2024 05 03 Urn Models
Urn models using Numpy
2024 05 04 Signals Bib
2024 05 09 Roth Erev RL
Roth Erev learning in Lewis signaling games
2024 06 01 Bayesian Agents
2024 06 11 Risk Constrained MDP
Risk-constrained Markov decision processes
2024 06 12 Logic Puzzles
2024 06 13 Hyper
Hyperparameter Optimization
2024 06 23 Zero Inflated Data
zero inflated data
2024 06 25 Mesa Rl
Mesa & RL
Misbehavior of Markets and Scaling in financial prices 1-4
Scaling in financial prices 3
Scaling in financial prices 2
Scaling in financial prices 4
Scaling in financial prices 1
2025
The roles of Partial pooling and mixed strategies in the Lewis signaling game
Rethinking Signaling systems via the lens of compositionality
The Referential Lewis Signaling Game
Books, Courses Tools
Engineering Reinforcement Learning Algorithms
Compositionality in Lewis signaling games and MARL transfer learning.
Emergent Languages
Complex Signals Questions
Planning in the Complex Lewis Game
Off-Policy Learning
A garden of forking paths
The Many Path To A Signaling System
Podcast
All Reviews
Order By
Default
Date - Oldest
Date - Newest
Title
title
teaser for reading this paper
Oren Bochman
🧠 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…
Oren Bochman
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
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
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
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
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
Dropout: A Simple Way to Prevent Neural Networks from Overfitting
In
(Srivastava et al. 2014)
the authors, present a novel regularization technique for deep neural networks called “dropout.” The key idea behind dropout is to randomly drop…
Oren Bochman
Some dynamics of signaling games
teaser for reading this paper
Oren Bochman
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
Temporal Abstraction in Reinforcement Learning with the Successor Representation
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
FontCLIP: A Semantic Typography Visual-Language Model for Multilingual Font Applications
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
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
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
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
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
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
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
2BP: 2-Stage Backpropagation
in
(Shyam et al. 2024)
the authors …
Oren Bochman
Why bother reviewing papers?
Why bother reviewing papers?
Oren Bochman
🏒 Hockey Helmets, Concealed Weapons, and Daylight Saving – Binary Choices with Externalities
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
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
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
Learning priors for Shapes
Oren Bochman
Saturday, March 29, 2025
🤝 Costly Signaling and Cooperation
teaser for reading this paper
Oren Bochman
Monday, March 24, 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
Oren Bochman
Thursday, March 13, 2025
On Learning To Become a Successful Loser
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
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.
Oren Bochman
Wednesday, January 1, 2025
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.
Oren Bochman
Wednesday, January 1, 2025
Compositionality and Generalization in Emergent Languages
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
Emergent Communication of Generalizations
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
(Huttegger et al. 2010)
Oren Bochman
Tuesday, October 8, 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
The Evolution of Coding in signaling games
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
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
Generally Capable Agents Emerge from Open-Ended Play
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
Signals: Signals: Evolution, Learning, and Information
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
🦚 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…
Oren Bochman
Thursday, March 14, 2024
🤝 Diversity Bonuses: How Diverse Teams Achieve Superior Results
teaser for reading this paper
Oren Bochman
Sunday, October 1, 2023
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
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…
Oren Bochman
Sunday, June 26, 2022
Skeletonization: A Technique for Trimming the Fat from a Network via Relevance Assessment
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
Simplifying Neural Networks by soft weight sharing
This paper was mentioned in Geoffrey Hinton’s Coursera course as a way to simplify neural networks.
Oren Bochman
Wednesday, June 22, 2022
VGGNet: Very Deep Convolutional Networks for Large-Scale Image Recognition
In this paper
(Simonyan and Zisserman 2015)
the authors, Karen Simonyan and Andrew Zisserman from the Visual Geometry Group at Oxford, investigated the effect of increasing…
Oren Bochman
Thursday, December 10, 2015
🧠 Technical Introduction: A primer on probabilistic inference
How to model human cognition using probabilistic inference
Oren Bochman
Friday, March 20, 2015
No matching items
title
