Neural Networks

concepts · 36 notes linked

Related: Deep Learning · Machine Learning · Gradient Descent · Backpropagation · Mit · Michael Nielsen · Large Language Models · Reinforcement Learning

Notes

• 35 Best Resources To Learn Machine Learning — Curated list of free interactive ML and deep learning visualization tools
• A Simple Neural Network - With Numpy in Python — Implementing neural network forward pass and backpropagation from scratch with NumPy
• A Step-by-Step Guide to the Microsoft News Recommendation Competition | Towards Data Science — Walkthrough of NRMS algorithm and MIND competition submission process
• An Applied Mathematician Strengthens AI With Pure Math | Quanta Magazine — Applying topology and algebraic geometry to explain and improve neural networks
• Attention in Neural Networks | Towards Data Science — Survey of attention mechanism variants beyond basic encoder-decoder attention
• CSC321 Neural Networks and Machine Learning (UTM) — University of Toronto UTM introductory neural networks and ML course
• Calculus on Computational Graphs: Backpropagation — Backpropagation as reverse-mode differentiation on computational graphs
• Cheatsheet — Comprehensive reference index of Torch7 packages, tutorials, and GPU setup
• Cheatsheet — Torch7 Lua deep learning framework comprehensive reference guide
• ConvNetJS — JavaScript library for training neural networks in the browser
• Deep Learning — Goodfellow, Bengio, Courville canonical deep learning textbook freely online
• Getting an all-optical AI to handle non-linear math — Photonic chip runs neural network at 410 picosecond latency
• GitHub - catalyst-team/dl-course: Deep Learning with Catalyst — Open-source deep learning course using PyTorch and Catalyst framework
• GitHub - erdc/ampl: Automated Machine-learning PipeLine — ERDC automated ML pipeline for novice and expert users
• GitHub - pkmital/tensorflow_tutorials: From the basics to slightly more interesting applications of Tensorflow — TensorFlow tutorial series from basics through autoencoders and residual networks
• Godfather of Artificial Intelligence" Geoffrey Hinton on the promise, risks of advanced AI — Geoffrey Hinton 60 Minutes interview warning of AI existential and societal risks
• How Computationally Complex Is a Single Neuron? | Quanta Magazine — Single biological neuron equivalent to 5–8 layer deep neural network
• Is This Analog AI's Best Hope? — Capacitor-based analog AI chip overcomes noise limitations of current-based designs
• Machine Learning & Neural Research - Chapelle — Overview of ML research topics including spectral CNNs and formal verification
• Machine Learning Course Series — Three-course ML curriculum from Python basics to LLMs
• Machine Learning Course Series — Three-course ML curriculum from Python basics to LLMs
• Machine Learning Video Library — Caltech indexed video segments covering core ML topics
• Machine Learning, Kolmogorov Complexity, and Squishy Bunnies — Using neural networks to approximate physics simulation via Kolmogorov complexity intuition and PCA
• Marvin Minsky's Vision of the Future — 1981 New Yorker profile of Marvin Minsky and origins of AI
• Marvin Minsky's Vision of the Future — 1981 New Yorker profile of Marvin Minsky and origins of AI research at MIT
• Neural Networks and Deep Learning — Chapter 2 derivation of the four backpropagation equations
• Neural Networks and Deep Learning — Introductory neural network tutorial using MNIST handwritten digit recognition
• Neural Networks and Deep Learning — Chapter 4 — Visual proof that neural networks with hidden layers can approximate any continuous function
• PyTorch Explained: From Automatic Differentiation to Training Custom Neural Networks | Towards Data Science — PyTorch core abstractions from tensors and autograd to transformer encoder
• Quoc Le's Lectures on Deep Learning — Gaurav Trivedi — Content guide for Quoc Le's 3-lecture deep learning series at MLSS 2014
• Researchers Discover a More Flexible Approach to Machine Learning | Quanta Magazine — MIT liquid neural networks inspired by C. elegans offer adaptive continuous-time inference
• Symbolic Mathematics Finally Yields to Neural Networks — Facebook AI neural network solves symbolic integrals and ODEs via sequence translation
• This AI Uses Light Instead of Electricity and It's Mind-Blowingly Fast — Photonic neural network accelerator processes distributed acoustic sensing in real-time
• What is nn.Embedding really? — PyTorch embedding layer as efficient lookup-based linear layer equivalent
• Why does Deep Learning work? — Deep learning energy landscape as spin funnel not spin glass
• neural-networks-and-deep-learning/src/network.py at master · mnielsen/neural-networks-and-deep-learning — Michael Nielsen's minimal readable feedforward neural network with SGD and backpropagation in Python