Aleksa Gordić - The AI Epiphany Courses

Graph SAGE - Inductive Representation Learning on Large Graphs - GNN Paper Explained

Deep dive into Graph SAGE, exploring its innovative approach to large-scale graph learning. Covers key concepts, training methods, aggregator functions, and comparisons with other graph neural networks.

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

Graph Convolutional Networks - GNN Paper Explained

Comprehensive exploration of Graph Convolutional Networks, covering theory, implementation, and applications. Delves into spectral methods, Weisfeiler-Lehman perspective, and GNN depth, offering insights for both beginners and experts.

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

Graph Attention Networks - GNN Paper Explained

Explore Graph Attention Networks (GAT) in-depth, covering graph theory basics, GAT methodology, multi-head versions, visualizations, and applications in transductive/inductive learning scenarios.

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

Attention Is All You Need - Transformer Paper Explained

Detailed walkthrough of the original transformer architecture, covering tokenization, embeddings, attention mechanisms, and decoding, with a focus on machine translation applications.

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

Developing a Deep Learning Project - Case Study on Transformer

Explore the development process of a transformer model, from project planning to implementation challenges, with insights on time management, data handling, and optimization techniques.

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

What Is MLOps and How to Get Started - MLOps Series

Comprehensive introduction to MLOps, covering key concepts and resources for building automated ML-powered applications. Includes walkthroughs of popular courses and practical insights for aspiring ML engineers.

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

How to Build a Deep Learning Machine - Everything You Need to Know

Comprehensive guide on building a deep learning machine, covering component selection, cost comparisons, and practical tips for assembling a high-performance workstation tailored to AI tasks.

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

High Fidelity Neural Audio Compression - Paper & Code Explained

Explore neural audio compression techniques achieving 10x compression rates, with in-depth analysis of paper and code implementation, including VQ-VAE, VQ-GAN, and AudioGen applications.

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

AudioGen- Textually Guided Audio Generation - Paper Explained

Explore text-guided audio synthesis with AudioGen, delving into its architecture, audio representation, language modeling, and innovative approaches for generating diverse sounds from textual descriptions.

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

OpenAI Whisper - Robust Speech Recognition via Large-Scale Weak Supervision

Explore OpenAI's Whisper: a robust speech recognition system using large-scale weak supervision. Dive into the paper, code, and architecture, covering dataset collection, evaluation metrics, and practical implementation.

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

BigScience BLOOM - 3D Parallelism Explained - Large Language Models - ML Coding Series

Explore 3D parallelism in large language models: pipeline, model, and data parallelism. Dive into BLOOM's codebase to understand scaling techniques behind recent ML breakthroughs.

• YouTube
• 1 hour 12 minutes
• Self-Paced
• Free Video

Open Pretrained Transformer - ML Coding Series

Deep dive into OPT-175B codebase, covering setup, training script, model construction, CUDA kernels, and mixed precision training concepts for large language models.

• YouTube
• 1 hour 15 minutes
• Self-Paced
• Free Video

Training Large Language Models - GPT-NeoX-20B, BigScience BLOOM, OPT-175B Explained

Explore three groundbreaking large language models: BLOOM, OPT, and GPT-NeoX-20B. Gain insights into their development, challenges faced during training, and unique features of each project.

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

Get Started With Stable Diffusion - Code, HF Spaces, Diffusers Notebooks

Learn three methods to use Stable Diffusion: HuggingFace Spaces, Colab notebooks, and local setup. Gain practical skills in image generation, metadata reproduction, and interpolation techniques.

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

Ultimate Guide to Scaling ML Models - Megatron-LM - ZeRO - DeepSpeed - Mixed Precision

Comprehensive guide to scaling machine learning models, covering parallelism techniques, mixed precision training, and memory optimization strategies for training large-scale AI models efficiently.

• YouTube
• 1 hour 23 minutes
• Self-Paced
• Free Video