Yannic Kilcher Courses

Deconstructing Lottery Tickets - Zeros, Signs, and the Supermask

Explores the Lottery Ticket Hypothesis, analyzing key components of sparse networks and uncovering insights on weight initialization, sign importance, and the concept of Supermasks in neural network training.

• YouTube
• 36 minutes
• On-Demand
• Free Video

Do ImageNet Classifiers Generalize to ImageNet? - Paper Explained

Exploring ImageNet classifiers' generalization capabilities through new test datasets, revealing surprising accuracy drops and insights into model performance on slightly "harder" images.

• YouTube
• 26 minutes
• On-Demand
• Free Video

Supervised Contrastive Learning

Explore a novel supervised learning approach that outperforms cross-entropy loss, improving image classification models' performance and robustness across various architectures and data augmentations.

• YouTube
• 30 minutes
• On-Demand
• Free Video

Thinking While Moving - Deep Reinforcement Learning with Concurrent Control

Explore concurrent control in reinforcement learning, where agents make decisions while executing actions, revolutionizing robotic movement and decision-making processes.

• YouTube
• 30 minutes
• On-Demand
• Free Video

Gradient Surgery for Multi-Task Learning

Explore PCGrad, a technique addressing gradient conflicts in multi-task learning, enhancing efficiency and performance in supervised and reinforcement learning scenarios.

• YouTube
• 32 minutes
• On-Demand
• Free Video

Longformer - The Long-Document Transformer

Explore Longformer's innovative attention mechanism for processing lengthy documents, combining local windowed and global attention to overcome Transformer limitations in handling long sequences.

• YouTube
• 27 minutes
• On-Demand
• Free Video

Backpropagation and the Brain

Explore a biologically plausible variant of backpropagation and its potential role in brain learning, discussing feedback connections and error signal approximation in cortical networks.

• YouTube
• 32 minutes
• On-Demand
• Free Video

Shortcut Learning in Deep Neural Networks

Explore deep neural networks' shortcut learning, its impact on AI generalization, and strategies to improve model robustness and real-world applicability.

• YouTube
• 49 minutes
• On-Demand
• Free Video

Feature Visualization and the OpenAI Microscope

Explore neural network visualizations using OpenAI Microscope, understanding feature extraction in ImageNet classifiers and techniques for visualizing internal model workings.

• YouTube
• 21 minutes
• On-Demand
• Free Video

FixMatch - Simplifying Semi-Supervised Learning with Consistency and Confidence

Explore FixMatch, a powerful semi-supervised learning approach combining consistency regularization and pseudo-labeling for improved model performance with limited labeled data.

• YouTube
• 20 minutes
• On-Demand
• Free Video

Dynamical Distance Learning for Semi-Supervised and Unsupervised Skill Discovery

Explore dynamical distance learning for reinforcement agents, enhancing policy learning through state distance estimation. Discover applications in semi-supervised and unsupervised skill acquisition.

• YouTube
• 23 minutes
• On-Demand
• Free Video

CURL - Contrastive Unsupervised Representations for Reinforcement Learning

Explore how contrastive learning enhances reinforcement learning, improving performance in complex tasks using high-level features extracted from raw pixels.

• YouTube
• 29 minutes
• On-Demand
• Free Video

Evolving Normalization-Activation Layers

Explore evolutionary search for optimal normalization-activation layers in neural networks, uncovering novel designs that outperform traditional methods across various image-related tasks.

• YouTube
• 31 minutes
• On-Demand
• Free Video

POET - Endlessly Generating Increasingly Complex and Diverse Learning Environments and Solutions

Explore POET, an innovative algorithm that generates and solves increasingly complex challenges, fostering open-ended learning and diverse problem-solving capabilities through evolutionary methods and transfer learning.

• YouTube
• 34 minutes
• On-Demand
• Free Video

Dream to Control - Learning Behaviors by Latent Imagination

Explore DeepMind's Dreamer, an innovative RL agent that learns complex behaviors through latent imagination, surpassing existing approaches in visual control tasks.

• YouTube
• 23 minutes
• On-Demand
• Free Video