nothatcreative5/CS231N-solutions

Solutions to CS231n: Convolutional Neural Networks for Visual Recognition (Stanford University - Spring 2022) assignments

CS231n: Convolutional Neural Networks for Visual Recognition

CS231n is a course offered by Stanford University that focuses on deep learning for computer vision. The course covers a range of topics related to convolutional neural networks (CNNs), image classification, and deep learning frameworks.

Course Topics

The course covers the following topics:

• Image classification
• Convolutional neural networks (CNNs)
• k-Nearest Neighbors (kNN)
• Support vector machines (SVM)
• Softmax
• Fully connected neural networks
• Batch normalization
• Dropout
• PyTorch and TensorFlow
• Adversarial attacks
• Generative adversarial networks (GANs)
• Self-supervised contrastive learning
• Image captioning with RNNs and Transformers

Assignments

Assignment 1: Image Classification, kNN, SVM, Softmax, Fully Connected Neural Network

Notebooks

• k-Nearest Neighbors
• Support Vector Machines
• Softmax
• Fully Connected Neural Network

Assignment 2: Fully Connected and Convolutional Nets, Batch Normalization, Dropout, Pytorch & Network Visualization

Notebooks

• Fully Connected Nets
• Batch Normalization
• Dropout
• Convolutional Networks
• PyTorch / TensorFlow on CIFAR-10
• Network Visualization: Saliency maps, Class Visualization, and Fooling Images

Assignment 3: Image Captioning with RNNs and Transformers, Generative Adversarial Networks, Self-Supervised Contrastive Learning

Notebooks

• Generative Adversarial Networks
• LSTM Image Captioning
• RNN Image Captioning
• Self Supervised Learning
• Transform Image Captioning