Neural Networks #4: Activations & Gradients, BatchNorm.

⏰ 13:00-15:00 Sunday, May 25
📌 F0RTHSP4CE, Ana Kalandadze, 5
👉🚪How to get to the entrance

Language: EN
Entrance: free
Host: @klntsky
Speaker: @gustawdaniel

We dive into some of the internals of MLPs with multiple layers and scrutinize the statistics of the forward pass activations, backward pass gradients, and some of the pitfalls when they are improperly scaled. We also look at the typical diagnostic tools and visualizations you'd want to use to understand the health of your deep network.

Bring your laptops with Jupyter.

This is advanced course, we assume that you have basic python, algebra and calculus knowledge.

👉 Register here (optional): https://www.meetup.com/lets-learn-together/events/306937535