Aleksa Gordić - The AI Epiphany Courses

Convergence of Vision and Language in AI - Recent Developments and Projects

Explore the convergence of vision and language in AI with Lucas Beyer from Google DeepMind, covering topics like ViT, PaLI, and the future of multimodal AI architectures.

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

State Space Models: Advancements and Applications in AI - Featuring Albert Gu and Karan Goel

Explore state space models with experts Albert Gu and Karan Goel, discussing their groundbreaking research, real-time demos, and how SSMs compare to transformers in AI applications.

• YouTube
• 1 hour 4 minutes
• Self-Paced
• Free Video

Building LLM Apps in Production - Challenges and Best Practices

Explore LLM app development in production with insights on common challenges, data handling, testing, and industry trends. Gain valuable perspectives from an experienced consultant in the field.

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

Building the Best RLHF Library - TRLX Development with Louis Castricato

Explore the journey of building CarperAI and the TRLX library for RLHF, featuring insights on open-source development and the growth of AI projects.

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

Imbue - Training a 70B Model from Scratch - Infrastructure and Challenges

Explore Imbue's journey in building infrastructure for a 70B model, covering technical challenges, cluster setup, and insights into large-scale AI training with Bowei, head of infrastructure.

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

Building AI Agents with Integrail - From Email Drafting to ArXiv Scraping

Master practical AI agent development with Integrail through hands-on demonstrations, including email drafting, job post parsing, and arxiv paper summarization, with expert guidance and platform insights.

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

Qwen 2 LLM - Overview and Development with Junyang Lin

Explore Qwen2 LLM with author Junyang Lin, covering tokenization, training, architecture, context length, and future developments in AI language models.

• YouTube
• 1 hour 4 minutes
• Self-Paced
• Free Video

Neural Style Transfer

Dive into neural style transfer from basic theory to advanced implementations, covering optimization and feed-forward methods with hands-on PyTorch coding examples.

• YouTube
• 1 hour 33 minutes
• Self-Paced
• Free Video

Building Web Apps Using Streamlit - Streamlit Crash Course - MLOps Series

Learn to build web apps with Streamlit and HuggingFace API. Covers environment setup, Streamlit basics, API integration, Git versioning, and cloud deployment for a comprehensive MLOps introduction.

• YouTube
• 1 hour 6 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