- Understand the basics of convolutional neural networks, including convolutional layer mechanics, max-pooling, and learned parameters/feature maps.
- Learn how to implement a CNN architecture in PyTorch for image/object classification using best practices.
- Build intuition on the effects of modulating the design of a CNN by experimenting with your own (or "classic") architectures.
- Learn how to address the imbalanced/rare class prediction problem in multiclass classification.
- Visualize and interpret learned feature maps of a CNN.
WangWillis/PA3-CNN
This directory contains the instructions and starter code for PA3 on Convolutional Neural Networks for UCSD's CSE 190: Deep Learning.
Python