pytorch and neural nets review session
play

PyTorch and Neural Nets Review Session CS285 Instructor: Vitchyr - PowerPoint PPT Presentation

PyTorch and Neural Nets Review Session CS285 Instructor: Vitchyr Pong Goal of this course Train an agent to perform useful tasks common training paradigm this lecture train model agent data collect data How do we train a model? How do


  1. PyTorch and Neural Nets Review Session CS285 Instructor: Vitchyr Pong

  2. Goal of this course Train an agent to perform useful tasks

  3. common training paradigm this lecture train model agent data collect data

  4. How do we train a model?

  5. How do we train a model? neural network

  6. How do we train a model? gradient descent neural network

  7. How do we train a model? gradient descent neural network

  8. What is PyTorch? Python library for… ● Defining neural networks ● Automatically computing gradients gradient descent neural network

  9. What is PyTorch? Python library for… ● Defining neural networks ● Automatically computing gradients ● And more (GPU, optimizers, etc.) gradient descent neural network

  10. PyTorch Alternatives TensorFlow, JAX, Chainer, … Basically all do the same

  11. How does Pytorch work?

  12. PyTorch: forward pass [picture from Stanford’s CS231n]

  13. PyTorch: backward pass You define PT computes [picture from Stanford’s CS231n]

  14. PyTorch Tutorial (Colab) https://colab.research.google.com/drive/1r_-Ow0QYPN58cfuNjZDUy4O6HUvPDxyN?usp=sharing

Recommend


More recommend