Neural Breakdown with AVB Courses

Byte Latent Transformers - Understanding Meta's BLT Model for Efficient Language Processing

Dive into Meta's Byte Latent Transformers (BLT) architecture, exploring how this innovative approach uses byte-level processing and dynamic compute allocation to enhance language model efficiency and performance.

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

Evolution of Transformer Architectures - From Attention to Modern Variants

Explore the evolution of neural attention mechanisms, from basic self-attention to advanced concepts like Multi Query and Grouped Query Attention, with clear visualizations and practical insights.

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

Sesame AI and RVQs - The Network Architecture Behind Viral Speech Models

Explore the architecture of Sesame Conversational Speech Model, including Mimi Encoder tokenization with split RVQ, semantic and acoustic codes, and the Autoregressive Transformer Backbone that enables natural speech interaction.

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

10 Simple Tools for Building LLM Apps with Python Code Examples

Discover 10 essential Python tools for building industry-standard LLM applications, from structured outputs with PydanticAI to deployment strategies, with practical code examples.

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

From Attention to Generative Language Models - Building Transformers from Scratch

Master the fundamentals of Causal Generative Language Models through hands-on Pytorch implementation, covering attention mechanisms, transformers, and neural architectures with practical code examples.

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

Fine-tuning LLMs with Huggingface and PyTorch - A Step-by-Step Tutorial

Master fine-tuning techniques for LLMs using Huggingface and PyTorch, from tokenization to LORA adapters, with hands-on implementation using Meta's Llama-3.2-1B-Instruct model.

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

TextGrad Tutorial - Optimize LLM Prompts, Math and Code

Master TextGrad framework for optimizing LLM prompts through practical examples covering hallucination reduction, code optimization, math problem-solving, and prompt fine-tuning techniques.

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

Building YOLO Neural Networks for Object Detection in Python and PyTorch - Part 1

Master the implementation of YOLO neural networks in Python and PyTorch, covering architecture, data preprocessing, Feature Pyramid Networks, and object detection fundamentals.

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

DSPy Tutorial - Programming Language Models with 8 Key Examples

Master DSPy framework through 8 practical examples, from basic QA to advanced LLM programming concepts like RAG, multi-hop reasoning, and model fine-tuning with popular language models.

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

History of Computer Vision and CNN Architectures: From LeNet to Vision Transformers

Explore the evolution of Computer Vision through key architectural innovations, from early CNNs to modern Vision Transformers, with clear visualizations explaining breakthrough moments in deep learning history.

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

Text-to-Image Diffusion AI Model Implementation - A Line-by-Line Code Tutorial

Dive into the fundamentals of diffusion AI models through hands-on PyTorch implementation, covering everything from basic concepts to advanced Latent Diffusion Models for text-to-image generation.

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

Historical Perspectives on AGI: Definitions, Consciousness, and Alignment Challenges

Explore key debates around AGI through expert perspectives on consciousness, behavior, and alignment, examining scientific theories and current limitations in artificial intelligence development.

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

Multimodal AI: From First Principles to Neural Networks That See, Hear and Write

Explore the evolution and capabilities of multimodal AI systems, from fundamental principles to advanced models that combine vision, text, and audio for sophisticated machine learning tasks.

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

Vision Transformers: Understanding Self-Attention and Implementation in PyTorch

Dive into Vision Transformers through clear visualizations and hands-on PyTorch implementation, mastering self-attention mechanisms and comparing them with CNNs in computer vision tasks.

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

Retrieval Augmented Generation (RAG) - Building Powerful LLM Pipelines

Dive into the fundamentals of Retrieval Augmented Generation (RAG), exploring advanced techniques from basic pipelines to modern frameworks for building powerful LLM systems with external knowledge integration.

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