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 …
Watch on YouTube ↗ (saves to browser)

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

Playlist

Uploads from Yannic Kilcher · Yannic Kilcher · 0 of 60

← Previous Next →
1 Yannic Kilcher Live Stream
Yannic Kilcher Live Stream
Yannic Kilcher
 2 Imagination-Augmented Agents for Deep Reinforcement Learning
Imagination-Augmented Agents for Deep Reinforcement Learning
Yannic Kilcher
 3 Learning model-based planning from scratch
Learning model-based planning from scratch
Yannic Kilcher
 4 Reinforcement Learning with Unsupervised Auxiliary Tasks
Reinforcement Learning with Unsupervised Auxiliary Tasks
Yannic Kilcher
 5 Attention Is All You Need
Attention Is All You Need
Yannic Kilcher
 6 git for research basics: fundamentals, commits, branches, merging
git for research basics: fundamentals, commits, branches, merging
Yannic Kilcher
 7 Curiosity-driven Exploration by Self-supervised Prediction
Curiosity-driven Exploration by Self-supervised Prediction
Yannic Kilcher
 8 World Models
World Models
Yannic Kilcher
 9 Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
Yannic Kilcher
 10 Stochastic RNNs without Teacher-Forcing
Stochastic RNNs without Teacher-Forcing
Yannic Kilcher
 11 What’s in a name? The need to nip NIPS
What’s in a name? The need to nip NIPS
Yannic Kilcher
 12 BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Yannic Kilcher
 13 Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Yannic Kilcher
 14 GPT-2: Language Models are Unsupervised Multitask Learners
GPT-2: Language Models are Unsupervised Multitask Learners
Yannic Kilcher
 15 Neural Ordinary Differential Equations
Neural Ordinary Differential Equations
Yannic Kilcher
 16 The Odds are Odd: A Statistical Test for Detecting Adversarial Examples
The Odds are Odd: A Statistical Test for Detecting Adversarial Examples
Yannic Kilcher
 17 Discriminating Systems - Gender, Race, and Power in AI
Discriminating Systems - Gender, Race, and Power in AI
Yannic Kilcher
 18 Blockwise Parallel Decoding for Deep Autoregressive Models
Blockwise Parallel Decoding for Deep Autoregressive Models
Yannic Kilcher
 19 S.H.E. - Search. Human. Equalizer.
S.H.E. - Search. Human. Equalizer.
Yannic Kilcher
 20 Reinforcement Learning, Fast and Slow
Reinforcement Learning, Fast and Slow
Yannic Kilcher
 21 Adversarial Examples Are Not Bugs, They Are Features
Adversarial Examples Are Not Bugs, They Are Features
Yannic Kilcher
 22 I'm at ICML19 :)
I'm at ICML19 :)
Yannic Kilcher
 23 Population-Based Search and Open-Ended Algorithms
Population-Based Search and Open-Ended Algorithms
Yannic Kilcher
 24 Talking to companies at ICML19
Talking to companies at ICML19
Yannic Kilcher
 25 XLNet: Generalized Autoregressive Pretraining for Language Understanding
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Yannic Kilcher
 26 Conversation about Population-Based Methods (Re-upload)
Conversation about Population-Based Methods (Re-upload)
Yannic Kilcher
 27 Reconciling modern machine learning and the bias-variance trade-off
Reconciling modern machine learning and the bias-variance trade-off
Yannic Kilcher
 28 Learning World Graphs to Accelerate Hierarchical Reinforcement Learning
Learning World Graphs to Accelerate Hierarchical Reinforcement Learning
Yannic Kilcher
 29 Manifold Mixup: Better Representations by Interpolating Hidden States
Manifold Mixup: Better Representations by Interpolating Hidden States
Yannic Kilcher
 30 Processing Megapixel Images with Deep Attention-Sampling Models
Processing Megapixel Images with Deep Attention-Sampling Models
Yannic Kilcher
 31 Gauge Equivariant Convolutional Networks and the Icosahedral CNN
Gauge Equivariant Convolutional Networks and the Icosahedral CNN
Yannic Kilcher
 32 Auditing Radicalization Pathways on YouTube
Auditing Radicalization Pathways on YouTube
Yannic Kilcher
 33 RoBERTa: A Robustly Optimized BERT Pretraining Approach
RoBERTa: A Robustly Optimized BERT Pretraining Approach
Yannic Kilcher
 34 Dynamic Routing Between Capsules
Dynamic Routing Between Capsules
Yannic Kilcher
 35 DEEP LEARNING MEME REVIEW - Episode 1
DEEP LEARNING MEME REVIEW - Episode 1
Yannic Kilcher
 36 Accelerating Deep Learning by Focusing on the Biggest Losers
Accelerating Deep Learning by Focusing on the Biggest Losers
Yannic Kilcher
 37 [News] The Siraj Raval Controversy
[News] The Siraj Raval Controversy
Yannic Kilcher
 38 LeDeepChef 👨‍🍳 Deep Reinforcement Learning Agent for Families of Text-Based Games
LeDeepChef 👨‍🍳 Deep Reinforcement Learning Agent for Families of Text-Based Games
Yannic Kilcher
 39 The Visual Task Adaptation Benchmark
The Visual Task Adaptation Benchmark
Yannic Kilcher
 40 IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Yannic Kilcher
 41 AlphaStar: Grandmaster level in StarCraft II using multi-agent reinforcement learning
AlphaStar: Grandmaster level in StarCraft II using multi-agent reinforcement learning
Yannic Kilcher
 42 SinGAN: Learning a Generative Model from a Single Natural Image
SinGAN: Learning a Generative Model from a Single Natural Image
Yannic Kilcher
 43 A neurally plausible model learns successor representations in partially observable environments
A neurally plausible model learns successor representations in partially observable environments
Yannic Kilcher
 44 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
 45 NeurIPS 2019
NeurIPS 2019
Yannic Kilcher
 46 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
 47 NeurIPS 19 Poster Session
NeurIPS 19 Poster Session
Yannic Kilcher
 48 Go-Explore: a New Approach for Hard-Exploration Problems
Go-Explore: a New Approach for Hard-Exploration Problems
Yannic Kilcher
 49 Reformer: The Efficient Transformer
Reformer: The Efficient Transformer
Yannic Kilcher
 50 [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
 51 Turing-NLG, DeepSpeed and the ZeRO optimizer
Turing-NLG, DeepSpeed and the ZeRO optimizer
Yannic Kilcher
 52 Growing Neural Cellular Automata
Growing Neural Cellular Automata
Yannic Kilcher
 53 NeurIPS 2020 Changes to Paper Submission Process
NeurIPS 2020 Changes to Paper Submission Process
Yannic Kilcher
 54 Deep Learning for Symbolic Mathematics
Deep Learning for Symbolic Mathematics
Yannic Kilcher
 55 Online Education - How I Make My Videos
Online Education - How I Make My Videos
Yannic Kilcher
 56 [Rant] coronavirus
[Rant] coronavirus
Yannic Kilcher
 57 Axial Attention & MetNet: A Neural Weather Model for Precipitation Forecasting
Axial Attention & MetNet: A Neural Weather Model for Precipitation Forecasting
Yannic Kilcher
 58 Agent57: Outperforming the Atari Human Benchmark
Agent57: Outperforming the Atari Human Benchmark
Yannic Kilcher
 59 State-of-Art-Reviewing: A Radical Proposal to Improve Scientific Publication
State-of-Art-Reviewing: A Radical Proposal to Improve Scientific Publication
Yannic Kilcher
 60 Can we Contain Covid-19 without Locking-down the Economy?
Can we Contain Covid-19 without Locking-down the Economy?
Yannic Kilcher
The Most Clever Trick To Speedup LLMs
Next Up
The Most Clever Trick To Speedup LLMs
bycloud