Neural Networks #5: Backpropagation training

⏰ 13:00-15:00 Sunday, Jun 01
📌 F0RTHSP4CE, Ana Kalandadze, 5
👉🚪How to get to the entrance 

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

We take the 2-layer MLP (with BatchNorm) from the previous event and backpropagate through it manually without using PyTorch autograd's loss.backward(): through the cross entropy loss, 2nd linear layer, tanh, batchnorm, 1st linear layer, and the embedding table. Along the way, we get a strong intuitive understanding about how gradients flow backwards through the compute graph and on the level of efficient Tensors, not just individual scalars like in micrograd. This helps build competence and intuition around how neural nets are optimized and sets you up to more confidently innovate on and debug modern neural networks.

Bring your laptops with Jupyter.

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

👉 Register here (optional): https://meetu.ps/e/NYWpB/vScFh/i