Multimodal Neurons in Artificial Neural Networks (w/ OpenAI Microscope, Research Paper Explained)

Yannic Kilcher · Beginner ·📄 Research Papers Explained ·5y ago
#openai #clip #microscope OpenAI does a huge investigation into the inner workings of their recent CLIP model via faceted feature visualization and finds amazing things: Some neurons in the last layer respond to distinct concepts across multiple modalities, meaning they fire for photographs, drawings, and signs depicting the same concept, even when the images are vastly distinct. Through manual examination, they identify and investigate neurons corresponding to persons, geographical regions, religions, emotions, and much more. In this video, I go through the publication and then I present my own findings from digging around in the OpenAI Microscope. OUTLINE: 0:00 - Intro & Overview 3:35 - OpenAI Microscope 7:10 - Categories of found neurons 11:10 - Person Neurons 13:00 - Donald Trump Neuron 17:15 - Emotion Neurons 22:45 - Region Neurons 26:40 - Sparse Mixture of Emotions 28:05 - Emotion Atlas 29:45 - Adversarial Typographic Attacks 31:55 - Stroop Test 33:10 - My Findings in OpenAI Microscope 33:30 - Superman Neuron 33:50 - Resting B*tchface Neuron 34:10 - Trash Bag Neuron 35:25 - God Weightlifting Neuron 36:40 - Organ Neuron 38:35 - Film Spool Neuron 39:05 - Feather Neuron 39:20 - Spartan Neuron 40:25 - Letter E Neuron 40:35 - Cleanin Neuron 40:45 - Frown Neuron 40:55 - Lion Neuron 41:05 - Fashion Model Neuron 41:20 - Baseball Neuron 41:50 - Bride Neuron 42:00 - Navy Neuron 42:30 - Hemp Neuron 43:25 - Staircase Neuron 43:45 - Disney Neuron 44:15 - Hillary Clinton Neuron 44:50 - God Neuron 45:15 - Blurry Neuron 45:35 - Arrow Neuron 45:55 - Trophy Presentation Neuron 46:10 - Receding Hairline Neuron 46:30 - Traffic Neuron 46:40 - Raised Hand Neuron 46:50 - Google Maps Neuron 47:15 - Nervous Smile Neuron 47:30 - Elvis Neuron 47:55 - The Flash Neuron 48:05 - Beard Neuron 48:15 - Kilt Neuron 48:25 - Rainy Neuron 48:35 - Electricity Neuron 48:50 - Droplets Neuron 49:00 - Escape Neuron 49:25 - King Neuron 49:35 - Country Neuron 49:45 - Overweight Men Neuron 49:55 - Weddi
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Playlist

Uploads from Yannic Kilcher · Yannic Kilcher · 0 of 60

← Previous Next →
1 Imagination-Augmented Agents for Deep Reinforcement Learning
Imagination-Augmented Agents for Deep Reinforcement Learning
Yannic Kilcher
 2 Learning model-based planning from scratch
Learning model-based planning from scratch
Yannic Kilcher
 3 Reinforcement Learning with Unsupervised Auxiliary Tasks
Reinforcement Learning with Unsupervised Auxiliary Tasks
Yannic Kilcher
 4 Attention Is All You Need
Attention Is All You Need
Yannic Kilcher
 5 git for research basics: fundamentals, commits, branches, merging
git for research basics: fundamentals, commits, branches, merging
Yannic Kilcher
 6 Curiosity-driven Exploration by Self-supervised Prediction
Curiosity-driven Exploration by Self-supervised Prediction
Yannic Kilcher
 7 World Models
World Models
Yannic Kilcher
 8 Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
Yannic Kilcher
 9 Stochastic RNNs without Teacher-Forcing
Stochastic RNNs without Teacher-Forcing
Yannic Kilcher
 10 What’s in a name? The need to nip NIPS
What’s in a name? The need to nip NIPS
Yannic Kilcher
 11 BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Yannic Kilcher
 12 Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Yannic Kilcher
 13 GPT-2: Language Models are Unsupervised Multitask Learners
GPT-2: Language Models are Unsupervised Multitask Learners
Yannic Kilcher
 14 Neural Ordinary Differential Equations
Neural Ordinary Differential Equations
Yannic Kilcher
 15 The Odds are Odd: A Statistical Test for Detecting Adversarial Examples
The Odds are Odd: A Statistical Test for Detecting Adversarial Examples
Yannic Kilcher
 16 Discriminating Systems - Gender, Race, and Power in AI
Discriminating Systems - Gender, Race, and Power in AI
Yannic Kilcher
 17 Blockwise Parallel Decoding for Deep Autoregressive Models
Blockwise Parallel Decoding for Deep Autoregressive Models
Yannic Kilcher
 18 S.H.E. - Search. Human. Equalizer.
S.H.E. - Search. Human. Equalizer.
Yannic Kilcher
 19 Reinforcement Learning, Fast and Slow
Reinforcement Learning, Fast and Slow
Yannic Kilcher
 20 Adversarial Examples Are Not Bugs, They Are Features
Adversarial Examples Are Not Bugs, They Are Features
Yannic Kilcher
 21 I'm at ICML19 :)
I'm at ICML19 :)
Yannic Kilcher
 22 Population-Based Search and Open-Ended Algorithms
Population-Based Search and Open-Ended Algorithms
Yannic Kilcher
 23 XLNet: Generalized Autoregressive Pretraining for Language Understanding
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Yannic Kilcher
 24 Conversation about Population-Based Methods (Re-upload)
Conversation about Population-Based Methods (Re-upload)
Yannic Kilcher
 25 Reconciling modern machine learning and the bias-variance trade-off
Reconciling modern machine learning and the bias-variance trade-off
Yannic Kilcher
 26 Learning World Graphs to Accelerate Hierarchical Reinforcement Learning
Learning World Graphs to Accelerate Hierarchical Reinforcement Learning
Yannic Kilcher
 27 Manifold Mixup: Better Representations by Interpolating Hidden States
Manifold Mixup: Better Representations by Interpolating Hidden States
Yannic Kilcher
 28 Processing Megapixel Images with Deep Attention-Sampling Models
Processing Megapixel Images with Deep Attention-Sampling Models
Yannic Kilcher
 29 Gauge Equivariant Convolutional Networks and the Icosahedral CNN
Gauge Equivariant Convolutional Networks and the Icosahedral CNN
Yannic Kilcher
 30 Auditing Radicalization Pathways on YouTube
Auditing Radicalization Pathways on YouTube
Yannic Kilcher
 31 RoBERTa: A Robustly Optimized BERT Pretraining Approach
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Yannic Kilcher
 32 Dynamic Routing Between Capsules
Dynamic Routing Between Capsules
Yannic Kilcher
 33 DEEP LEARNING MEME REVIEW - Episode 1
DEEP LEARNING MEME REVIEW - Episode 1
Yannic Kilcher
 34 Accelerating Deep Learning by Focusing on the Biggest Losers
Accelerating Deep Learning by Focusing on the Biggest Losers
Yannic Kilcher
 35 [News] The Siraj Raval Controversy
[News] The Siraj Raval Controversy
Yannic Kilcher
 36 LeDeepChef 👨‍🍳 Deep Reinforcement Learning Agent for Families of Text-Based Games
LeDeepChef 👨‍🍳 Deep Reinforcement Learning Agent for Families of Text-Based Games
Yannic Kilcher
 37 The Visual Task Adaptation Benchmark
The Visual Task Adaptation Benchmark
Yannic Kilcher
 38 IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Yannic Kilcher
 39 AlphaStar: Grandmaster level in StarCraft II using multi-agent reinforcement learning
AlphaStar: Grandmaster level in StarCraft II using multi-agent reinforcement learning
Yannic Kilcher
 40 SinGAN: Learning a Generative Model from a Single Natural Image
SinGAN: Learning a Generative Model from a Single Natural Image
Yannic Kilcher
 41 A neurally plausible model learns successor representations in partially observable environments
A neurally plausible model learns successor representations in partially observable environments
Yannic Kilcher
 42 MuZero: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
MuZero: Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Yannic Kilcher
 43 Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions
Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions
Yannic Kilcher
 44 NeurIPS 19 Poster Session
NeurIPS 19 Poster Session
Yannic Kilcher
 45 Go-Explore: a New Approach for Hard-Exploration Problems
Go-Explore: a New Approach for Hard-Exploration Problems
Yannic Kilcher
 46 Reformer: The Efficient Transformer
Reformer: The Efficient Transformer
Yannic Kilcher
 47 [Interview] Mark Ledwich - Algorithmic Extremism: Examining YouTube's Rabbit Hole of Radicalization
[Interview] Mark Ledwich - Algorithmic Extremism: Examining YouTube's Rabbit Hole of Radicalization
Yannic Kilcher
 48 Turing-NLG, DeepSpeed and the ZeRO optimizer
Turing-NLG, DeepSpeed and the ZeRO optimizer
Yannic Kilcher
 49 Growing Neural Cellular Automata
Growing Neural Cellular Automata
Yannic Kilcher
 50 NeurIPS 2020 Changes to Paper Submission Process
NeurIPS 2020 Changes to Paper Submission Process
Yannic Kilcher
 51 Deep Learning for Symbolic Mathematics
Deep Learning for Symbolic Mathematics
Yannic Kilcher
 52 Online Education - How I Make My Videos
Online Education - How I Make My Videos
Yannic Kilcher
 53 [Rant] coronavirus
[Rant] coronavirus
Yannic Kilcher
 54 Axial Attention & MetNet: A Neural Weather Model for Precipitation Forecasting
Axial Attention & MetNet: A Neural Weather Model for Precipitation Forecasting
Yannic Kilcher
 55 Agent57: Outperforming the Atari Human Benchmark
Agent57: Outperforming the Atari Human Benchmark
Yannic Kilcher
 56 State-of-Art-Reviewing: A Radical Proposal to Improve Scientific Publication
State-of-Art-Reviewing: A Radical Proposal to Improve Scientific Publication
Yannic Kilcher
 57 Dream to Control: Learning Behaviors by Latent Imagination
Dream to Control: Learning Behaviors by Latent Imagination
Yannic Kilcher
 58 POET: Endlessly Generating Increasingly Complex and Diverse Learning Environments and Solutions
POET: Endlessly Generating Increasingly Complex and Diverse Learning Environments and Solutions
Yannic Kilcher
 59 Evaluating NLP Models via Contrast Sets
Evaluating NLP Models via Contrast Sets
Yannic Kilcher
 60 [Drama] Who invented Contrast Sets?
[Drama] Who invented Contrast Sets?
Yannic Kilcher

Related AI Lessons

⚡
The ABCs of reading medical research and review papers these days
Learn to critically evaluate medical research papers by accepting nothing at face value, believing no one blindly, and checking everything
Medium · LLM
 ⚡
#1 DevLog Meta-research: I Got Tired of Tab Chaos While Reading Research Papers.
Learn to manage research paper tabs efficiently and apply meta-research techniques to improve productivity
Dev.to AI
 ⚡
How to Set Up a Karpathy-Style Wiki for Your Research Field
Learn to set up a Karpathy-style wiki for your research field to organize and share knowledge effectively
Medium · AI
 ⚡
The Non-Optimality of Scientific Knowledge: Path Dependence, Lock-In, and The Local Minimum Trap
Scientific knowledge may be stuck in a local minimum, hindering optimal progress, and understanding this concept is crucial for advancing research
ArXiv cs.AI

Chapters (53)

Intro & Overview
3:35 OpenAI Microscope
7:10 Categories of found neurons
11:10 Person Neurons
13:00 Donald Trump Neuron
17:15 Emotion Neurons
22:45 Region Neurons
26:40 Sparse Mixture of Emotions
28:05 Emotion Atlas
29:45 Adversarial Typographic Attacks
31:55 Stroop Test
33:10 My Findings in OpenAI Microscope
33:30 Superman Neuron
33:50 Resting B*tchface Neuron
34:10 Trash Bag Neuron
35:25 God Weightlifting Neuron
36:40 Organ Neuron
38:35 Film Spool Neuron
39:05 Feather Neuron
39:20 Spartan Neuron
40:25 Letter E Neuron
40:35 Cleanin Neuron
40:45 Frown Neuron
40:55 Lion Neuron
41:05 Fashion Model Neuron
41:20 Baseball Neuron
41:50 Bride Neuron
42:00 Navy Neuron
42:30 Hemp Neuron
43:25 Staircase Neuron
43:45 Disney Neuron
44:15 Hillary Clinton Neuron
44:50 God Neuron
45:15 Blurry Neuron
45:35 Arrow Neuron
45:55 Trophy Presentation Neuron
46:10 Receding Hairline Neuron
46:30 Traffic Neuron
46:40 Raised Hand Neuron
46:50 Google Maps Neuron
47:15 Nervous Smile Neuron
47:30 Elvis Neuron
47:55 The Flash Neuron
48:05 Beard Neuron
48:15 Kilt Neuron
48:25 Rainy Neuron
48:35 Electricity Neuron
48:50 Droplets Neuron
49:00 Escape Neuron
49:25 King Neuron
49:35 Country Neuron
49:45 Overweight Men Neuron
49:55 Weddi
Up next
Generating novel scientific hypotheses with Co-Scientist
Google DeepMind
Watch →