SLIDE 1
Goal of this course
Train an agent to perform useful tasks
PyTorch and Neural Nets Review Session CS285 Instructor: Vitchyr - - PowerPoint PPT Presentation
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
SLIDE 2
SLIDE 3
common training paradigm
data agent train model collect data this lecture
SLIDE 4
How do we train a model?
SLIDE 5
How do we train a model?
neural network
SLIDE 6
How do we train a model?
gradient descent neural network
SLIDE 7
How do we train a model?
gradient descent neural network
SLIDE 8
What is PyTorch?
Python library for…
- Defining neural networks
- Automatically computing gradients
gradient descent neural network
SLIDE 9
What is PyTorch?
Python library for…
- Defining neural networks
- Automatically computing gradients
- And more (GPU, optimizers, etc.)
gradient descent neural network
SLIDE 10
PyTorch Alternatives
TensorFlow, JAX, Chainer, … Basically all do the same
SLIDE 11
How does Pytorch work?
SLIDE 12
PyTorch: forward pass
[picture from Stanford’s CS231n]
SLIDE 13
PT computes You define
PyTorch: backward pass
[picture from Stanford’s CS231n]
SLIDE 14
PyTorch Tutorial (Colab)
https://colab.research.google.com/drive/1r_-Ow0QYPN58cfuNjZDUy4O6HUvPDxyN?usp=sharing