Yannic Kilcher Courses

Generative Adversarial Networks - Paper Explained

Explore the groundbreaking Generative Adversarial Networks paper, covering its innovative approach, theoretical foundations, and practical implications for AI-driven image generation and deep learning advancements.

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

Word2Vec- Distributed Representations of Words and Phrases and Their Compositionality

Explore Word2Vec, a groundbreaking technique for creating word vectors. Learn about distributed representations, skip-gram model, negative sampling, and subsampling methods to improve vector quality and training efficiency.

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

Deep Residual Learning for Image Recognition - Paper Explained

Explore deep residual learning for image recognition, covering the problem of depth, residual connections, and their impact on neural network performance in computer vision tasks.

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

Deep Ensembles: A Loss Landscape Perspective

Explore deep ensembles' effectiveness in neural networks, their superiority over Bayesian models, and how they capture non-convex loss landscapes to improve generalization and robustness in AI.

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

NVAE- A Deep Hierarchical Variational Autoencoder

Detailed explanation of NVAE, a deep hierarchical variational autoencoder for high-resolution image generation, covering architecture, training techniques, and state-of-the-art results.

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

Supermasks in Superposition - Paper Explained

Explore supermasks in neural networks for lifelong learning, tackling catastrophic forgetting and automatic task identification. Learn about mask superpositions, entropy minimization, and innovative extensions.

• YouTube
• 1 hour
• On-Demand
• Free Video

SpineNet - Learning Scale-Permuted Backbone for Recognition and Localization

Explores SpineNet, a novel CNN architecture using scale-permuted features and cross-scale connections, outperforming traditional models in object detection and classification tasks.

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

Transformers Are RNNs- Fast Autoregressive Transformers With Linear Attention

Explore a novel approach to transformers using linear attention, reducing computational complexity and revealing connections to RNNs. Gain insights into faster, more efficient deep learning models for long sequences.

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

BERTology Meets Biology - Interpreting Attention in Protein Language Models

Explores how BERT models trained on protein sequences learn biological properties, revealing insights into protein structure, binding sites, and biophysical characteristics through attention mechanism analysis.

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

GShard- Scaling Giant Models with Conditional Computation and Automatic Sharding

Detailed explanation of Google's 600 billion parameter transformer for multilingual translation, focusing on scaling techniques, mixture-of-experts, and automatic sharding implementation on TPUs.

• YouTube
• 1 hour 13 minutes
• On-Demand
• Free Video

Object-Centric Learning with Slot Attention

Explanation of a novel deep learning module for object-centric visual scene understanding. Covers architecture, algorithm, experiments, and implications of Slot Attention for improved object recognition and reasoning.

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

Set Distribution Networks - A Generative Model for Sets of Images

Explores a novel framework for generating and encoding sets of images, introducing Set Distribution Networks that can create new object/identity sets while preserving key attributes.

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

Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures

Explores Direct Feedback Alignment as a biologically plausible alternative to backpropagation, demonstrating its effectiveness in training modern deep learning architectures for various challenging tasks.

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

Discovering Symbolic Models from Deep Learning with Inductive Biases

Exploring how Graph Neural Networks and symbolic regression can derive accurate symbolic equations from observational data, combining deep learning with physics-inspired inductive biases.

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

How I Read a Paper- Facebook's DETR

Explore the process of understanding Facebook AI's DETR paper through a step-by-step analysis, from title to conclusions, with insights on interpreting research effectively.

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