Skip to content

Latest commit

 

History

History
40 lines (30 loc) · 1.33 KB

README.md

File metadata and controls

40 lines (30 loc) · 1.33 KB
Raw

Programming Assignment 1

Implementation of deep neural networks from scratch for multiclass classification with mean squared error and cross entropy loss, tanh, relu and sigmoid activations, gradient descent, momentum, nag and adam optimizers with l2 regularization.

Prerequisites

  1. Numpy
  2. Pickle
  3. Sklearn

Usage

Download the directory and use bash run.sh in terminal. Change placeholders in run.sh for train, validation and test data. Weights will be stored in save_dir and logs will be stored in expt_dir along with predictions.

Programming Assignment 2

Implementation of CNN for multiclass classification in Tiny Imagenet dataset. Also includes code for fooling network, guided backpropogation and plotting weight of layer 1 filter.

Prerequisites

  1. Numpy
  2. Pickle
  3. Sklearn
  4. Tensorflow
  5. scipy
  6. Matplotlib
  7. Pandas

Usage

Download the directory and use bash run.sh in terminal. Change placeholders in run.sh for train, validation and test data.

Programming Assignment 3

Implementation of RNN for transliteration from english to Hindi. Also includes code for bidirectional lstm and attention.

Prerequisites

  1. Numpy
  2. Pickle
  3. Tensorflow
  4. Matplotlib
  5. Scipy

Usage

Download the directory and use bash run.sh in terminal. Change placeholders in run.sh for train, validation and test data.