/COMP4901J-Deep-Learning-in-Computer-Vision

Deep learning course (similar to Stanford's cs231n) taken at HKUST during Fall 2017-18.

Primary LanguagePython

HKUST-COMP4901J-Deep-Learning-in-Computer-Vision: Assignment Solutions

These are my solutions for COMP4901J taken during Fall 17-18 semester in HKUST. The first three assignments are identical to Stanford CS231n (Spring 2017).

Assignment list:

  • Assignment 1
    • Q1: k-Nearest Neighbor classifier
    • Q2: Training a Support Vector Machine
    • Q3: Implement a Softmax classifier
    • Q4: Two-Layer Neural Network
    • Q5: Higher Level Representations: Image Features
  • Assignment 2
    • Q1: Fully-connected Neural Network
    • Q2: Batch Normalization
    • Q3: Dropout
    • Q4: Convolutional Networks
    • Q5: PyTorch / TensorFlow on CIFAR-10
  • Assignment 3
    • Q1: Image Captioning with Vanilla RNNs
    • Q2: Image Captioning with LSTMs
    • Q3: Network Visualization: Saliency maps, Class Visualization, and Fooling Images
    • Q4: Style Transfer
    • Q5: Generative Adversarial Networks
  • Assignment 4
    • Q1: Basic Q-learning algorithms
    • Q2: World navigation with DQN
    • Q3: CartPole with Policy Gradient
    • Q4: Model-based Reinforcement Learning