EEE443_MiniProjects

This repository is for Neural Networks Mini Projects. Implementation of the projects has been done using Python. Below gives the main themes for each project. However, there are more to each project than what is given below.

Key Themes of the Projects:

Project 1:

• Building a neural network to perform a simple logic formula.
• Building a single layer perceptron to learn the representations of letters in the alphabet.
  • Report
  • Code

Project 2:

• Design and implement NN from scratch for binary classification.
• Implement a neural network that predicts the fourth word given the initial three words.
  • Report
  • Code

Project 3:

• Unsupervised feature extraction using a sparse auto-encoders. MSE loss function with the addition of Tikhonov (L2) regularization and KL-Divergence to ensure sparsity.
• Implementations of RNN, GRU and LSTM.
  • Report
  • Code