Play allNeural networks and deep learning
200 videos • 207 hr 11 min
Part of AI and machine learning. Ordered by how many people recommended each video and for how long; 19 are classics.
1 2 The spelled-out intro to neural networks and backpropagation: building micrograd
Andrej Karpathy
Recommended by 17 •
Classic3 4 Transformers, the tech behind LLMs | Deep Learning Chapter 5
3Blue1Brown
Recommended by 14 •
Recent pick5 6 7 8 9 RL Course by David Silver - Lecture 1: Introduction to Reinforcement Learning
Google DeepMind
Recommended by 10 •
Classic10 Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning
Google TechTalks
Recommended by 9 •
11 12 13 14 15 George Hotz: Comma.ai, OpenPilot, and Autonomous Vehicles | Lex Fridman Podcast #31
Lex Fridman
Recommended by 8 •
Classic16 17 18 19 20 21 22 Robocalypse Now: Using Deep Learning to Combat Cheating in Counter-Strike: Global Offensive
GDC Festival of Gaming
Recommended by 5 •
Classic23 24 Attention in transformers, step-by-step | Deep Learning Chapter 6
3Blue1Brown
Recommended by 5 •
Recent pick25 Why Greatness Cannot Be Planned — Kenneth Stanley
Machine Learning Street Talk
Recommended by 4 •
Classic26 27 28 Gradient descent, how neural networks learn | Deep Learning Chapter 2
3Blue1Brown
Recommended by 4 •
Classic29 30 Training AI Without Writing A Reward Function, with Reward Modelling
Robert Miles AI Safety
Recommended by 3 •
Classic31 Ali Rahimi's talk at NIPS(NIPS 2017 Test-of-time award presentation)
ObservantVids
Recommended by 3 •
Classic32 The Simple Essence of Automatic Differentiation - Conal Elliott
Microsoft Research
Recommended by 3 •
Classic33 34 35 Andrej Karpathy: Tesla AI, Self-Driving, Optimus, Aliens, and AGI | Lex Fridman Podcast #333
Lex Fridman
Recommended by 3 •
36 Will AI outsmart human intelligence? - with 'Godfather of AI' Geoffrey Hinton
The Royal Institution
Recommended by 3 •
37 38 Lecture 1 | Natural Language Processing with Deep Learning
Stanford University School of Engineering
Recommended by 3 •
39 40 Do we need Attention? - Linear RNNs and State Space Models (SSMs) for NLP
Sasha Rush
Recommended by 3 •
41 42 43 44 45 46 RAAIS 2017 - Simon Knowles, Co-Founder and CTO of Graphcore
The Research and Applied AI Summit - RAAIS
Recommended by 3 •
Hidden gem47 48 49 50 Full interview: "Godfather of artificial intelligence" talks impact and potential of AI
CBS Mornings
Recommended by 3 •
51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 Jeff Hawkins: Thousand Brains Theory of Intelligence | Lex Fridman Podcast #25
Lex Fridman
Recommended by 2 •
69 70 71 Jeffrey M. Siskind – The tension between convenience and performance in automatic differentiation
MILA: Montreal Institute for Learning Algorithms
Recommended by 2 •
Hidden gem72 73 74 75 76 77 Recovering Meaningful Variable Names in Decompiled Code
Software Engineering Institute | Carnegie Mellon University
Recommended by 1 •
78 79 Google DeepMind's Deep Q-learning playing Atari Breakout!
Two Minute Papers
Recommended by 2 •
Classic80 81 82 83 Face2Face: Real-time Face Capture and Reenactment of RGB Videos (CVPR 2016 Oral)
Matthias Niessner
Recommended by 1 •
84 Gradual tensor typing for practical machine learning in Haskell with Hasktorch
Breandan Considine
Recommended by 1 •
85 [SPCL_Bcast] Cloud-Scale Inference on FPGAs at Microsoft Bing
Scalable Parallel Computing Lab, SPCL @ ETH Zurich
Recommended by 1 •
86 87 88 89 90 Lecture 1 | Introduction to Convolutional Neural Networks for Visual Recognition
Stanford University School of Engineering
Recommended by 2 •
Classic91 92 93 Andrew Ng: Artificial Intelligence is the New Electricity
Stanford Graduate School of Business
Recommended by 2 •
94 95 Geoffrey Hinton in conversation with Fei-Fei Li — Responsible AI development
Arts & Science - University of Toronto
Recommended by 2 •
96 97 98 99 Munk Debate on Artificial Intelligence | Bengio & Tegmark vs. Mitchell & LeCun
Policy-Relevant Science & Technology
Recommended by 2 •
100 John Schulman - Reinforcement Learning from Human Feedback: Progress and Challenges
UC Berkeley EECS
Recommended by 2 •
101 AI Learns Noise Filtering For Photorealistic Videos | Two Minute Papers #215
Two Minute Papers
Recommended by 2 •
102 Image Classification with Transfer Learning in ML.NET using a Tensorflow Model
Jon Wood
Recommended by 1 •
103 Powerful Machine Learning at Your Fingertips by Jonatan Klosko | ElixirConf EU 2023
Code Sync
Recommended by 1 •
104 105 [SIGGRAPH 2018] Mode-Adaptive Neural Networks for Quadruped Motion Control
Sebastian Starke
Recommended by 1 •
106 107 108 109 110 Compose :: Melbourne 2017 - Huw Campbell - Grenade - Dependently Typed Neural Networks in Haskell
Compose Conference
Recommended by 1 •
111 112 Lecture 2 | The Universal Approximation Theorem
Carnegie Mellon University Deep Learning
Recommended by 1 •
113 114 115 116 117 118 119 120 Elixir YOLO v0.2.0 🤖: YOLOX Support, Custom Models and Performance Boost 🚀
poeticoding
Recommended by 1 •
121 122 clojureD 2019: "Tricking Sand into Thinking: Deep Learning in Clojure" by Dave Liepmann
:clojureD
Recommended by 1 •
123 124 125 Princeton Robotics - Russ Tedrake - Dexterous Manipulation with Diffusion Policies
Intelligent Robot Motion Lab
Recommended by 1 •
126 127 128 129 130 131 132 133 134 JuliaCon 2020 | ChainRules.jl | Frames Catherine White
The Julia Programming Language
Recommended by 1 •
135 "Program Synthesis as High-Level Machine Learning" Swarat Chaudhuri | FLOC 2018
Conference on Computer-Aided Verification
Recommended by 1 •
136 137 138 139 140 141 142 143 But how do AI images and videos actually work? | Guest video by Welch Labs
3Blue1Brown
Recommended by 1 •
Recent pick144 Yann Lecun: Meta AI, Open Source, Limits of LLMs, AGI & the Future of AI | Lex Fridman Podcast #416
Lex Fridman
Recommended by 1 •
145 146 147 148 149 Human AI is Decades Away, But We Need to Start the Debate Now | Demis Hassabis | Google Zeitgeist
Google Zeitgeist
Recommended by 1 •
150 151 No Priors Ep. 80 | With Andrej Karpathy from OpenAI and Tesla
No Priors: AI, Machine Learning, Tech, & Startups
Recommended by 1 •
152 Neural Network Learns The Physics of Fluids and Smoke | Two Minute Papers #118
Two Minute Papers
Recommended by 1 •
153 154 Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI | Lex Fridman Podcast #75
Lex Fridman
Recommended by 1 •
155 Andrej Karpathy (Tesla): CVPR 2021 (see description for better quality version)
YarrowFlower
Recommended by 1 •
156 157 158 159 Swift for TensorFlow: The Next-Generation Machine Learning Framework (TF Dev Summit '19)
TensorFlow
Recommended by 1 •
160 161 162 163 164 165 166 Stanford CS336 Language Modeling from Scratch | Spring 2025 | Lecture 1: Overview and Tokenization
Stanford Online
Top upload •
167 168 169 1: Introduction to Neural Networks and Deep Learning; Training Deep NNs
MIT OpenCourseWare
Top upload •
170 171 172 173 174 175 176 Stanford XCS224U: NLU I Intro & Evolution of Natural Language Understanding, Pt. 1 I Spring 2023
Stanford Online
Top upload •
177 178 179 Stanford CS25: V3 I Beyond LLMs: Agents, Emergent Abilities, Intermediate-Guided Reasoning, BabyLM
Stanford Online
Top upload •
180 181 Stanford CS25: V5 I Transformers in Diffusion Models for Image Generation and Beyond
Stanford Online
Top upload •
182 Stanford CS153 Frontier Systems | Anjney Midha from AMP PBC on Frontier Systems
Stanford Online
Top upload •
183 Stanford CS25: V3 I How I Learned to Stop Worrying and Love the Transformer
Stanford Online
Top upload •
184 185 What Really Separates Autoregression and Diffusion? A Synthesis and Path Beyond
Simons Institute for the Theory of Computing
Top upload •
186 187 Re-thinking Transformers: Searching for Efficient Linear Layers over a Continuous Space of...
Simons Institute for the Theory of Computing
Top upload •
188 Diffusion in RL and robotics: how expressive policies changed how we use continuous actions
Simons Institute for the Theory of Computing
Top upload •
189 190 How to Build a Modern Diffusion Language Model
Simons Institute for the Theory of Computing
Top upload •
191 192 Grounding Diffusion Models: The Path to Reliable Synthesis Without Hallucination
Simons Institute for the Theory of Computing
Top upload •
193 Nicolas Kuhaupt - Probabilistic Forecasting with DeepAR and AWS SageMaker
EuroPython Conference
Top upload •
194 Hacking LLMs: An Introduction to Mechanistic Interpretability — Jenny Vega
EuroPython Conference
Top upload •
195 Compositional Reasoning with Diffusion Models
Simons Institute for the Theory of Computing
Top upload •
196 The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence, Task Complexity, and...
Simons Institute for the Theory of Computing
Top upload •
197 Advancing Diffusion Models for Text Generation
Simons Institute for the Theory of Computing
Top upload •
198 When Can We Trust What a Model Has Learned? Identifiability, Causality, and Reliable AI
Simons Institute for the Theory of Computing
Top upload •
199 200 Let’s run a tiny chess neural network by hand! - Amédée d’Aboville at !!Con 2024
Confreaks
Top upload •
