Skip to content

Latest commit

 

History

History
41 lines (40 loc) · 2.11 KB

README.md

File metadata and controls

41 lines (40 loc) · 2.11 KB

Deep-Learning-Projects

Repository for Deep Learning projects using Pytorch, Keras, Tensorflow that I worked...

Artificial Neural network (ANN):

Create ANN using algorithms like gradient descent, back-propagation to train/validate/test the model.

  • Project: To predict Student Admission based on UCLA admission data
  • Project: To predict Bike-sharing patterns on a given day
  • Project: Classifying the movie review text using Sentiment Analysis
  • Project: Multi-layer Perceptron on MNIST dataset
  • Project: ANN on Fashion MNIST dataset
  • Project: ANN on IRIS dataset

Convolutional neural networks (CNN):

Create CNN, Transfer learning from existing models, Autoencoder (for image compression and de-noising), Style transfer.

  • Project: CNN on CIFAR10 dataset
  • Project: Transfer learning using VGG16 to classify images
  • Project: Transpose Convolutional Autoencoder on MNIST
  • Project: Upsamling Convolutional Autoencoder on MNIST
  • Project: Denoising Autoencoder on MNIST
  • Project: Style transfer using VGG19
  • Project: Classify dog breeds in pictures

Recurrent neural network (RNN):

Creating RNN, LSTM(Long Short Term Memory),Word embedding's using Skip-Gram and Negative Sampling, Sentiment analysis.

  • Project: Creating simple RNN
  • Project: Character-Level LSTM
  • Project: Word embedding using Skip-gram and Negative sampling
  • Project: Sentiment Analysis with RNN
  • Project: Create/deploy Sentiment Analysis on AWS, Create web app and access model from it
  • Project: Generate new TV scripts from provided existing scripts

Generative Adversarial Networks (GAN):

Implementing GAN, Deep Convolutional GAN(DCGAN), CycleGAN, Image to Image transformations

  • Project - GAN on MNIST dataset
  • Project - DCGAN on SVHN dataset
  • Project - CycleGAN for Image to Image transformation
  • Project - Use a deep convolutional GAN to generate completely new images of human faces