Aleksa Gordić - The AI Epiphany Courses

ETA Prediction with Graph Neural Networks in Google Maps - Paper Explained

1 rating

Explore Graph Neural Networks for ETA prediction in Google Maps, covering graph formation, features, GNN architecture, loss functions, baselines, inference, and experimental results.

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

MosaicML - Path to 1.300.000.000$ with Davis Blalock - Discord Server Talks

Insights from MosaicML's first employee on the company's journey, efficiency strategies, competitive edge, and challenges in AI model evaluation.

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

Will LLMs Kill Search? The Future of Information Retrieval

Explore the future of search with Nils Reimers, discussing RAG, multilingual embedding, complex data search, and Cohere-Rerank. Gain insights on LLMs' impact on search technology.

• YouTube
• 1 hour 7 minutes
• Self-Paced
• Free Video

Flash Attention 2.0 with Tri Dao - Discord Server Talks

Explore Flash Attention 2.0 with author Tri Dao, covering its motivation, improvements, and future directions. Gain insights into memory bottlenecks and IO awareness in attention mechanisms for long sequences.

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

GPT-Fast - Blazingly Fast Inference with PyTorch

Explore techniques for accelerating AI inference using PyTorch, including compile, quantization, speculative decoding, and tensor parallelism, with expert insights from Horace He.

• YouTube
• 1 hour 5 minutes
• Self-Paced
• Free Video

Answer.ai - Addressing Industry and Academia Challenges

Explore Jeremy Howard's insights on answer.ai, industry and academia challenges, and unlocking human potential in AI. Gain valuable perspectives on the future of AI development and education.

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

How Groq LPU Works - Understanding Language Processing Units

Explore Groq's LPU technology with Igor Arsovski, covering hardware, software, power control, networking, and comparisons to GPUs. Gain insights into this promising AI chip's architecture and performance advantages.

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

EleutherAI Pythia and Open-Source Language Models - Interview with Hailey Schoelkopf

Explore EleutherAI's Pythia, open-source language models, and AI research infrastructure with Hailey Schoelkopf. Gain insights into Llemma, LM-Eval-Harness, and the future of AI development.

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

LLaMA 2 and Meta AI Projects - Interview with Thomas Scialom

Insightful discussion with LLaMA 2 lead Thomas Scialom, covering his journey, Meta projects, and the future of AI. Explores key concepts like supervised fine-tuning and human preference in language models.

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

Fine-tuning LLMs 30x Faster - Unsloth AI's Approach

Discover techniques to accelerate LLM fine-tuning 30x with Daniel Han from Unsloth AI. Explore bug-hunting processes, optimization strategies, and insights into ML research reproducibility.

• YouTube
• 1 hour 5 minutes
• Self-Paced
• Free Video

Emu Video Generation - From MAE Pre-training to Multimodal Embeddings

Explore Emu Video generation with Ishan Misra from Meta, covering SSL, multimodal data, and recent advancements in video AI technology.

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

DeepMind's TacticAI - An AI Assistant for Football Tactics

Explore DeepMind's TacticAI, an innovative AI assistant for football tactics, featuring insights on its development, collaboration with Liverpool FC, and evaluation methods.

• YouTube
• 1 hour 6 minutes
• Self-Paced
• Free Video

LLaMA 3 Deep Dive - Synthetic Data, Privacy, and Model Architecture

Explore LLaMA 3's innovations with Meta's Thomas Scialom, covering synthetic data, privacy concerns, scaling techniques, and architectural choices in this in-depth discussion on advanced language models.

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

Archie - Engineering AGI for the Built World

Discover Archie, an engineering AGI system from P-1 AI designed to revolutionize how we create physical systems from airplanes to Dyson Spheres, with demonstrations of its design modification capabilities.

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

The Case for Open-Source AI - Interview with Thomas Wolf of HuggingFace

Insightful interview with Thomas Wolf exploring HuggingFace's journey, open-source philosophy, business model, and current projects in AI. Covers hiring, research initiatives, and the impact of tools like Gradio.

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