PodcastIntel
Sign in Get Started Free
Andrej Karpathy
Andrej Karpathy

Building makemore Part 3: Activations & Gradients, BatchNorm

Oct 4, 2022
Listen to Episode
✨ AI Summary
  • Analyze MLP activation and gradient statistics for network health.
  • Learn diagnostic tools and visualizations for deep networks.
  • Introduce Batch Normalization to stabilize deep network training.

More from Andrej Karpathy

Andrej Karpathy
How I use LLMs
Feb 27, 2025
Andrej Karpathy
Deep Dive into LLMs like ChatGPT
Feb 5, 2025
Andrej Karpathy
Let's reproduce GPT-2 (124M)
Jun 9, 2024
Andrej Karpathy
Let's build the GPT Tokenizer
Feb 20, 2024
View all episodes →

Get AI Summaries for Every New Episode

Subscribe to Andrej Karpathy and get AI summaries, guest tracking, and email digests delivered automatically.

Sign Up Free →