October
Papers
- Intelligence at the Edge of Chaos
- Bulk tissue cell type deconvolution with multi-subject single-cell expression reference
- Less is More: Parameter-Free Text Classification with Gzip
Links
- https://transformer-circuits.pub/2024/september-update/index.html Circuits Updates - September 2024
- https://justine.lol/mutex/ The Fastest Mutexes
- https://www.nature.com/immersive/d42859-024-00053-4/index.html The FlyWire connectome: neuronal wiring diagram of a complete fly brain
- https://www.nature.com/articles/s41586-024-07558-y Neuronal wiring diagram of an adult brain
- https://www.cell.com/trends/neurosciences/abstract/S0166-2236(22)00213-2 The tricky business of defining brain functions
- 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://www.biorxiv.org/content/10.1101/2024.10.05.616803v1 Neural dynamics for working memory and evidence integration during olfactory navigation in Drosophila
- https://rxivist.org/ Where did Rxivist go?
- https://www.kaggle.com/datasets/selfishgene/single-neurons-as-deep-nets-nmda-train-data Single Neurons as Deep Nets - NMDA train data
- https://www.kaggle.com/datasets/grantwiersum/biorxiv-abstracts BioRxiv Abstracts
- https://www.da.vidbuchanan.co.uk/blog/dram-emfi.html Can You Get Root With Only a Cigarette Lighter?
- https://jmlr.org/papers/v21/20-345.html Topology of Deep Neural Networks
- https://arxiv.org/abs/2201.02177 Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
- https://cses.fi/problemset/ CSES Problem Set
- https://www.overcomingbias.com/ Overcoming Bias
- https://www.overcomingbias.com/p/do-the-easy-neglected-task Do The Easy Neglected Task
- https://en.m.wikipedia.org/wiki/The_Emperor's_New_Clothes The Emperor's New Clothes
- https://www.alignmentforum.org/posts/Es2qzCxhJ8QYsckaA/eis-xiv-is-mechanistic-interpretability-about-to-be EIS XIV: Is mechanistic interpretability about to be practically useful?
- https://www.snailab.ca/home The Systems Neuroscience and AI Lab
- https://deepgenerativemodels.github.io/notes/flow/ Normalizing flow models
- https://terrytao.wordpress.com/career-advice/dont-be-afraid-to-learn-things-outside-your-field/ Don’t be afraid to learn things outside your field
- https://www.nature.com/articles/s41467-024-52541-w Maintenance and transformation of representational formats during working memory prioritization
- https://x.com/kenbwork/status/1845300893396369841 Technical people should learn biology
- https://arxiv.org/abs/2012.02550 Effect of the initial configuration of weights on the training and function of artificial neural networks
- https://arxiv.org/abs/2410.07174 Neural Circuit Architectural Priors for Quadruped Locomotion
- https://www.nature.com/articles/s41597-021-00981-0 Data sharing practices and data availability upon request differ across scientific disciplines
- https://www.lesswrong.com/posts/FF8i6SLfKb4g7C4EL/inside-the-mind-of-a-superhuman-go-model-how-does-leela-zero-2 Inside the mind of a superhuman Go model: How does Leela Zero read ladders?
- https://lczero.org/dev/wiki/technical-explanation-of-leela-chess-zero/ Technical Explanation of Leela Chess Zero
- https://github.com/rasbt/LLMs-from-scratch/blob/main/ch05/07_gpt_to_llama/converting-llama2-to-llama3.ipynb Converting Llama 2 to Llama 3.2 From Scratch
- http://www.scholarpedia.org/article/Encyclopedia:Computational_neuroscience Encyclopedia:Computational neuroscience
- http://www.hutter1.net/ai/uaibook.htm#oneline Universal Artificial Intelligence
- https://arxiv.org/pdf/cs/0701125 UNIVERSAL ALGORITHMIC INTELLIGENCE: A mathematical top down approach
- https://en.wikipedia.org/wiki/Lyapunov_exponent Lyapunov exponent
- https://blog.gopenai.com/how-to-speed-up-llms-and-use-100k-context-window-all-tricks-in-one-place-ffd40577b4c The Secret Sauce behind 100K context window in LLMs: all tricks in one place
- https://shreyansh26.github.io/post/2023-03-26_flash-attention/ Paper Summary #8 - FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
- https://research.google/blog/constructing-transformers-for-longer-sequences-with-sparse-attention-methods/ Constructing Transformers For Longer Sequences with Sparse Attention Methods
- https://scottaaronson.blog/ Shtetl-Optimized - The Blog of Scott Aaronson
- https://paulgraham.com/disagree.html How to Disagree
- https://pmc.ncbi.nlm.nih.gov/articles/PMC7579744/ The Bayesian brain: What is it and do humans have it?
- https://en.wikipedia.org/wiki/Predictive_coding Predictive coding
- https://en.wikipedia.org/wiki/Free_energy_principle Free energy principle
- https://people.hws.edu/graham/GrahamField_sparse.pdf Sparse Coding in the Neocortex
- https://arxiv.org/abs/1503.02406 Deep Learning and the Information Bottleneck Principle
- https://arxiv.org/abs/physics/0004057 The information bottleneck method
- https://www.quantamagazine.org/even-a-single-bacterial-cell-can-sense-the-seasons-changing-20241011/ Even a Single Bacterial Cell Can Sense the Seasons Changing
- https://arena3-chapter1-transformer-interp.streamlit.app/[1.3.2]_Interpretability_with_SAEs Interpretability with SAEs
- https://transformer-circuits.pub/2022/toy_model/index.html Toy Models of Superposition
- https://darioamodei.com/machines-of-loving-grace Machines of Loving Grace - How AI Could Transform the World for the Better
- https://bellard.org/nncp/ NNCP: Lossless Data Compression with Neural Networks
- https://llvm.org/docs/tutorial/ LLVM Tutorials
- https://arxiv.org/abs/2402.01502 Why do Random Forests Work? Understanding Tree Ensembles as Self-Regularizing Adaptive Smoothers
- https://ai.meta.com/blog/meta-llama-quantized-lightweight-models/ Introducing quantized Llama models with increased speed and a reduced memory footprint