November

Papers

• The Bayesian brain: What is it and do humans have it?
• Deep Differentiable Logic Gate Networks
• A critique of pure learning and what artificial neural networks can learn from animal brains
• Evidence of Learned Look-Ahead in a Chess-Playing Neural Network
• Ten simple rules for structuring papers
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Links

• https://ora.ox.ac.uk/objects/uuid:a6880196-34c7-47a0-80f1-74d32ab98788/files/s5m60qt58t Whole Brain Emulation: A Roadmap
• https://plato.stanford.edu/entries/identity-personal/ Personal Identity - Stanford Encyclopedia of Philosophy
• https://www.pnas.org/doi/10.1073/pnas.2409160121 Encoding innate ability through a genomic bottleneck
• https://www.nature.com/articles/s41598-021-91786-z Event-based backpropagation can compute exact gradients for spiking neural networks
• https://www.jneurosci.org/content/18/10/3870 The Variable Discharge of Cortical Neurons: Implications for Connectivity, Computation, and Information Coding
• https://nickbostrom.com/ethics/ai Ethical Issues in Advanced Artificial Intelligence
• https://www.mackenziemathislab.org/deeplabcut DeepCutLab: A software package for animal pose estimation
• https://link.springer.com/article/10.1007/BF02478259 A logical calculus of the ideas immanent in nervous activity
• https://www.thetransmitter.org/how-to-teach-this-paper/how-to-teach-this-paper-coordination-of-entorhinal-hippocampal-ensemble-activity-during-associative-learning-by-igarashi-et-al-2014/ How to teach this paper: ‘Coordination of entorhinal-hippocampal ensemble activity during associative learning,’
• https://ceur-ws.org/Vol-1419/paper0045.pdf Compressionism: A Theory of Mind Based on Data Compression
• https://en.wikipedia.org/wiki/Approximate_Bayesian_computation Approximate Bayesian computation
• https://www.fil.ion.ucl.ac.uk/bayesian-brain/ The Bayesian Brain
• https://en.wikipedia.org/wiki/Dutch_book_theorems Dutch book theorems
• https://www.lesswrong.com/posts/xJyY5QkQvNJpZLJRo/radical-probabilism-1 Radical Probabilism
• https://en.wikipedia.org/wiki/Von_Neumann%E2%80%93Morgenstern_utility_theorem Von Neumann–Morgenstern utility theorem
• https://en.wikipedia.org/wiki/Bayesian_inference Bayesian inference
• https://www.lesswrong.com/tag/sequences LessWrong Sequences
• https://www.lesswrong.com/posts/2TPph4EGZ6trEbtku/explainers-shoot-high-aim-low Explainers Shoot High. Aim Low!
• https://plato.stanford.edu/entries/logic-higher-order/ Second-order and Higher-order Logic: Stanford Encyclopedia of Philosophy
• https://www.sas.upenn.edu/~cavitch/pdf-library/Nagel_Bat.pdf What Is It Like to Be a Bat?
• https://plato.stanford.edu/entries/zombies/ Zombies: Stanford Encyclopedia of Philosophy
• https://en.wikipedia.org/wiki/Salience_(neuroscience) Salience (neuroscience)
• https://www.lesswrong.com/tag/availability-heuristic Availability Heuristic
• https://en.wikipedia.org/wiki/Motivational_salience Motivational salience
• https://mtlynch.io/editor/ How I Hired a Freelance Editor for My Blog
• https://interstitiality.net/BD/brainEngDiagram.html An Engineering Diagram of the Brain
• https://www.lesswrong.com/posts/9Yc7Pp7szcjPgPsjf/the-brain-as-a-universal-learning-machine The Brain as a Universal Learning Machine
• https://onlinelibrary.wiley.com/doi/full/10.1155/2013/149329 Strategic Cognitive Sequencing: A Computational Cognitive Neuroscience Approach
• https://www.sciencedirect.com/science/article/abs/pii/S0166432808005421 Neurocomputational models of basal ganglia function in learning, memory and choice
• https://direct.mit.edu/neco/article-abstract/18/2/283/7028/Making-Working-Memory-Work-A-Computational-Model Making Working Memory Work: A Computational Model of Learning in the Prefrontal Cortex and Basal Ganglia
• https://en.wikipedia.org/wiki/Action_selection Action selection
• https://sweet-hall-e72.notion.site/Why-are-Modern-Neural-Nets-the-way-they-are-And-Hidden-Hypernetworks-6c7195709e7b4abbada921875a951c54 Why are Modern Neural Nets the way they are? And Hidden Hypernetworks.
• https://spectrum.ieee.org/ai-designers-find-inspiration-in-rat-brains AI Designers Find Inspiration in Rat Brains
• https://stars.library.ucf.edu/cgi/viewcontent.cgi?article=3177&context=facultybib2000 A Hyper A Hypercube-Based Encoding for E cube-Based Encoding for Evolving Lar olving Large-Scale Neur ge-Scale Neural Networks
• https://leela-interp.github.io/ Evidence of Learned Look-Ahead in a Chess-Playing Neural Network
• https://arxiv.org/abs/2403.15498 Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models
• https://www.edwardtufte.com/books/ Data Visualization Books by Edward Tufte
• https://medium.com/luminasticity/a-theory-as-to-why-art-is-created-b0a2538416e3 A Theory as to Why Art is Created
• https://github.com/rasbt/LLMs-from-scratch LLMs from scratch
• https://pacificklaus.com/the-silurian-hypothesis-it-was-the-cephalopods/ The Silurian Hypothesis: It was the Cephalopods
• https://en.m.wikipedia.org/wiki/Process_isolation Process isolation
• https://physicalintelligence.company/blog/pi0 π0: Our First Generalist Policy
• https://nature.com/articles/s41586-024-08145-x A cellular basis for mapping behavioural structure
• https://jackcook.com/2024/11/09/bigger-fish.html When Machine Learning Tells the Wrong Story
• https://vitalik.eth.limo/general/2024/11/09/infofinance.html From prediction markets to info finance
• https://ben-mini.github.io/2024/img-0416 IMG_0416
• https://github.com/francisrstokes/githublog/blob/main/2024%2F11%2F1%2Fsending-an-ethernet-packet.md I sent an ethernet packet
• https://press.asimov.com/articles/grow-mars Why Nothing Can Grow on Mars*
• https://thetransmitter.org/neuroai/neuroai-a-field-born-from-the-symbiosis-between-neuroscience-ai/ NeuroAI: A field born from the symbiosis between neuroscience, AI
• https://thetransmitter.org/neuroai/what-the-brain-can-teach-artificial-neural-networks/ What the brain can teach artificial neural networks
• https://arcprize.org ARC Prize
• https://arxiv.org/abs/2411.04732 Convolutional Differentiable Logic Gate Networks
• https://arxiv.org/abs/2410.02543 Diffusion Models are Evolutionary Algorithms
• https://security.humanativaspa.it/fault-injection-down-the-rabbit-hole/ Fault Injection – Down the Rabbit Hole
• https://spinningup.openai.com/en/latest/spinningup/keypapers.html Key Papers in Deep RL
• https://neuwritewest.org NeuWrite West Blog
• https://sciencedirect.com/science/article/abs/pii/S0893608020300563 Supervised learning in spiking neural networks: A review of algorithms and evaluations
• https://sciencedirect.com/science/article/abs/pii/S0893608019303181 A review of learning in biologically plausible spiking neural networks
• https://en.m.wikipedia.org/wiki/Spiking_neural_network Spiking neural network
• https://web.mit.edu/6.001/6.037/sicp.pdf Structure and Interpretation of Computer Programs
• https://rishimehta.xyz/2024/11/17/alphaproofs-greatest-hits.html AlphaProof's Greatest Hits
• https://github.com/vishalbakshi/webgpupuzzles/blob/main/Official%20Solutions.md Web GPU Puzzles
• https://www.nature.com/articles/d41586-024-03716-4 How human brains got so big: our cells learned to handle the stress that comes with size
• https://cell.com/trends/cognitive-sciences/fulltext/S1364-6613%2824%2900189-X The Dimensions of dimensionality
• https://chessprogramming.org/Stockfish_NNUE Stockfish NNUE
• https://kaggle.com/competitions/fide-google-efficiency-chess-ai-challenge/overview FIDE & Google Efficient Chess AI Challenge
• https://emschwartz.me/understanding-the-bm25-full-text-search-algorithm/ Understanding the BM25 full text search algorithm
• https://cns.nyu.edu/malab/bayesianbook.html Bayesian models of perception and action
• https://transformer-circuits.pub/2022/mech-interp-essay Mechanistic Interpretability, Variables, and the Importance of Interpretable Bases
• https://arxiv.org/abs/2410.16144 1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs
• https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf Reciprocal Rank Fusion outperforms Condorcet and individual Rank Learning Methods
• https://tobiasvanderwerff.github.io/2024/05/15/cnn-vs-vit.html CNN vs. Vision Transformer: A Practitioner's Guide to Selecting the Right Model
• http://karpathy.github.io/2014/09/02/what-i-learned-from-competing-against-a-convnet-on-imagenet/ What I learned from competing against a ConvNet on ImageNet
• https://karpathy.ai/books.html Karpathy Books List
• https://biorxiv.org/content/10.1101/2024.11.19.624167v1 Boltz-1 Democratizing Biomolecular Interaction Modeling
• https://zed.dev/blog/zed-decoded-rope-optimizations-part-1 Rope Optimizations, Part 1
• https://blog.frost.kiwi/analytical-anti-aliasing/ AAA - Analytical Anti-Aliasing
• https://graphics.stanford.edu/~seander/bithacks.html Bit Twiddling Hacks
• https://en.m.wikipedia.org/wiki/XOR_swap_algorithm XOR swap algorithm
• https://github.com/PaulPauls/llama3_interpretability_sae Llama 3 Interpretability with Sparse Autoencoders
• https://arxiv.org/abs/1802.03426 UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• https://web.archive.org/web/20241123230238/https://www.cs.toronto.edu/~duvenaud/distill_bayes_net/public/ Bayesian Neural Networks
• https://dynomight.net/more-chess/ OK, I can partly explain the LLM chess weirdness now
• https://matt-rickard.com/accidentally-turing-complete Accidentally Turing Complete
• https://construction-physics.com/p/the-influence-of-bell-labs The Influence of Bell Labs
• https://modular.com/blog/understanding-simd-infinite-complexity-of-trivial-problems Understanding SIMD: Infinite Complexity of Trivial Problems
• https://anthropic.com/news/model-context-protocol Introducing the Model Context Protocol