Yannic Kilcher Courses

Deep Networks Are Kernel Machines

Explores the theory that deep neural networks function as kernel machines, challenging the view that they discover new data representations. Discusses implications for interpretability and algorithm development.

• YouTube
• 43 minutes
• Self-Paced
• Free Video

Extracting Training Data from Large Language Models - Paper Explained

Explores a method to extract training data from large language models, discussing security implications, risks, and mitigation strategies for models like GPT-3. Covers technical aspects and ethical considerations.

• YouTube
• 1 hour 3 minutes
• Self-Paced
• Free Video

Daniel Negreanu's No-Limit Hold'em Challenge - Poker Hand Analysis

Analysis of poker situations from Daniel Negreanu's Twitter challenge, exploring AI bot strategies and Nash equilibria in No-Limit Hold'em. Insights into advanced poker decision-making and game theory.

• YouTube
• 28 minutes
• Self-Paced
• Free Video

DeepMind's AlphaFold 2 Explained - AI Breakthrough in Protein Folding - What We Know and What We Don't

Comprehensive exploration of DeepMind's AlphaFold 2, a groundbreaking AI system that solved the protein folding problem. Covers the science, previous approaches, and potential implications for biology and medicine.

• YouTube
• 55 minutes
• Self-Paced
• Free Video

What Matters in On-Policy Reinforcement Learning? A Large-Scale Empirical Study

Comprehensive study on on-policy reinforcement learning, examining 50+ design choices across 5 environments. Provides insights and recommendations for practitioners to optimize agent performance in continuous control tasks.

• YouTube
• 38 minutes
• Self-Paced
• Free Video

PCGRL - Procedural Content Generation via Reinforcement Learning - Paper Explained

Explore how reinforcement learning can be applied to game level design, framing it as a sequential decision-making process for fast and diverse level generation.

• YouTube
• 25 minutes
• Self-Paced
• Free Video

Self-Training With Noisy Student Improves ImageNet Classification - Paper Explained

Explore a novel semi-supervised learning approach for image classification using unlabeled data, improving model performance and robustness through iterative self-training and noise injection techniques.

• YouTube
• 41 minutes
• Self-Paced
• Free Video

Playing Atari with Deep Reinforcement Learning - Paper Explained

Explore deep reinforcement learning's breakthrough in Atari game mastery using convolutional neural networks, revolutionizing AI with pixel-based control policies and outperforming human experts.

• YouTube
• 39 minutes
• Self-Paced
• Free Video

Neural Architecture Search Without Training - Paper Explained

Explores a novel approach to Neural Architecture Search using statistics of the Jacobian around data points, enabling rapid architecture evaluation without training and significantly accelerating the search process.

• YouTube
• 35 minutes
• Self-Paced
• Free Video

Gradient Origin Networks - Paper Explained with Live Coding

Explore Gradient Origin Networks: a novel implicit generative model for efficient latent representation learning, with live coding demonstration and in-depth explanation of the paper's key concepts.

• YouTube
• 42 minutes
• Self-Paced
• Free Video

Addendum for Supermasks in Superposition - A Closer Look

In-depth analysis of "Supermasks in Superposition" paper, exploring G objective, superposition concept, and broader impact. Includes live coding demonstration and theoretical discussions.

• YouTube
• 49 minutes
• Self-Paced
• Free Video

Live Machine Learning Research - Plain Self-Ensembles - Part 1

Live implementation of a novel ensemble model using label-free self-distillation, demonstrating improved accuracy with more students and challenging assumptions about ensemble learning in machine learning research.

• YouTube
• 1 hour 19 minutes
• Self-Paced
• Free Video

On the Measure of Intelligence by François Chollet - The ARC Challenge - Paper Explained

Explores the ARC challenge for testing machine intelligence, focusing on rapid generalization tasks based on human core knowledge priors like object-ness and symmetry. Discusses goals, examples, and potential solutions.

• YouTube
• 34 minutes
• Self-Paced
• Free Video

Context R-CNN- Long Term Temporal Context for Per-Camera Object Detection

Explores Context R-CNN, an object detection model leveraging long-term temporal context from static cameras. Improves performance in wildlife and traffic monitoring by incorporating data from multiple frames.

• YouTube
• 34 minutes
• Self-Paced
• Free Video

On the Measure of Intelligence by François Chollet - The Math Explained

Explore the formal definition of intelligence measurement, focusing on generalization difficulty, priors, and experience in terms of algorithmic complexity, as proposed by François Chollet.

• YouTube
• 43 minutes
• Self-Paced
• Free Video