Yannic Kilcher Courses

Axial-DeepLab - Stand-Alone Axial-Attention for Panoptic Segmentation

Explore a novel approach to image processing using axial-attention, combining positional embeddings and factorized self-attention to achieve state-of-the-art results in image segmentation tasks.

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

Radioactive Data - Tracing Through Training

Explore a novel technique for detecting dataset usage in model training through imperceptible "radioactive" data markers, offering robust identification even with minimal data exposure.

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

Fast Reinforcement Learning With Generalized Policy Updates - Paper Explained

Explanation of a novel reinforcement learning framework that enables agents to transfer knowledge between tasks, potentially solving new problems with zero-shot learning through generalized policy updates.

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

REALM- Retrieval-Augmented Language Model Pre-Training

Explore REALM, a novel approach to language model pre-training that integrates a latent knowledge retriever, enhancing open-domain question answering and offering interpretability and modularity benefits.

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

Meta-Learning Through Hebbian Plasticity in Random Networks - Paper Explained

Explores biologically-inspired Hebbian learning for adaptive AI agents. Demonstrates how random neural networks can self-organize during runtime to solve RL tasks and adapt to new situations without fixed policies.

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

Hopfield Networks Is All You Need - Paper Explained

Explores the connection between Hopfield networks and transformer attention, analyzing BERT through this lens and applying Hopfield attention to immune repertoire classification.

• YouTube
• 1 hour 5 minutes
• On-Demand
• Free Video

Big Bird- Transformers for Longer Sequences

Explanation of BigBird's sparse attention mechanism for transformers, enabling longer sequence processing. Covers theoretical foundations, architecture details, and experimental results in NLP and genomics applications.

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

ImageNet Classification with Deep Convolutional Neural Networks - Paper Explained

Detailed explanation of AlexNet, the groundbreaking deep convolutional neural network that revolutionized computer vision and kickstarted the deep learning era in image classification.

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

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