Yannic Kilcher Courses

Accelerating Deep Learning by Focusing on the Biggest Losers

Explore a technique to speed up neural network training by prioritizing high-loss examples, reducing backpropagation steps, and achieving faster convergence in deep learning models.

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

Dynamic Routing Between Capsules

Explore Capsule Networks, a novel neural network architecture using capsules and dynamic routing for improved object recognition and handling of spatial relationships.

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

Auditing Radicalization Pathways on YouTube

Critical analysis of YouTube's alleged radicalization pipeline, examining user behavior, content recommendations, and community intersections to evaluate claims of systematic progression towards extreme ideologies.

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

Gauge Equivariant Convolutional Networks and the Icosahedral CNN

Explore gauge equivariant CNNs on manifolds, focusing on icosahedral surfaces. Learn how this approach improves image segmentation and climate pattern analysis with enhanced efficiency and performance.

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

Manifold Mixup: Better Representations by Interpolating Hidden States

Explore Manifold Mixup, a regularization technique that improves neural network performance by interpolating hidden representations, leading to smoother decision boundaries and more robust predictions.

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

Conversation About Population-Based Methods

Explore population-based methods and open-ended learning in AI through an insightful interview, delving into cutting-edge research and practical applications in machine learning.

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

Adversarial Examples Are Not Bugs, They Are Features

Explore the concept of adversarial examples in machine learning, their origins, and implications for AI robustness and human-AI alignment.

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

Reinforcement Learning, Fast and Slow

Explores recent advancements in deep reinforcement learning, discussing techniques for faster learning and their potential implications for cognitive science and neuroscience.

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

Blockwise Parallel Decoding for Deep Autoregressive Models

Explores a novel blockwise parallel decoding method for deep autoregressive models, enabling faster generation in tasks like machine translation and image super-resolution without sacrificing quality.

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

Discriminating Systems - Gender, Race, and Power in AI

Explore gender, race, and power dynamics in AI, examining workforce representation and systemic biases. Critically analyzes claims of causal relationships and societal impacts.

• YouTube
• 1 hour 57 minutes
• Self-Paced
• Free Video

The Odds are Odd: A Statistical Test for Detecting Adversarial Examples

Explore statistical methods for detecting adversarial examples in machine learning models, focusing on test statistics and their effectiveness in identifying manipulated inputs.

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

Neural Ordinary Differential Equations

Explore continuous-depth neural networks using differential equations, offering advantages in memory efficiency, adaptive evaluation, and numerical precision-speed tradeoffs for various machine learning tasks.

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

GPT-2: Language Models are Unsupervised Multitask Learners

Explore OpenAI's GPT-2 model, its capabilities in natural language processing tasks, and the implications of its performance on various datasets without explicit supervision.

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

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Explore how Batch Normalization accelerates deep network training by reducing internal covariate shift, enabling higher learning rates and improved model performance.

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

BERT- Pre-training of Deep Bidirectional Transformers for Language Understanding

Explore BERT's innovative approach to language representation, its bidirectional pre-training method, and its state-of-the-art performance across various natural language processing tasks.

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