Deep Learning

This repository contains my project notebooks for the Deep Learning course.

---

Notebooks

LAB1_FCNN

• Implement a Two Layers Fully Connected Neural Network in Numpy by hand writing the Feedforward and Backpropagation functions.
• Train and evaluate models on MNIST data set, Comparing the influences of:
  • Stochastic / Batch / Mini batch gradient descent
  • different hidden layer size
  • different learning rate
  • sigmoid / softmax output

LAB2_CNN

• Using Tensorboard to visualize the graph and training progress.
• Re-build the FCNN model using Tensorflow.
• Implement a LeNet-5 CNN model in Tensorflow
• Perform some optimizations to get more than 99% of accuracy on MNIST.
  • Different Optimizer :Gradient Descent vs AdamOptimizer
  • Dropout

LAB3_RNN

• Build a Vanilla-RNN and a GRU by hand writing the formulas in Tensorflow.
• Classify user comments from IMDb, Amazon, and Yelp to two classification(Negative / Positive).