R

RNN

Real-time Gender and Age Recognition from Audio

Evaluation of various deep learning models for sentiment analysis You are given the reviews dataset. These are 194439 amazon reviews for cell phones and accessories taken from https://jmcauley.ucsd.edu/data/amazon/ Use the “reviewText” and “overall” fields from this file. The goal is to predict the rating given the review by modeling it as a multi-class classification problem. • Take the first 70% dataset for train, next 10% for validation/development, and remaining 20% for test. • Recurrent neural networks • RNNs: Train a single directional RNN with L layers. Vary the number of layers (as 1,2,3,4) and also size of layers (20, 50, 100, 200). Report accuracy on test set. • LSTMs: Train a single directional LSTM with L layers. Vary the number of layers (as 1,2,3,4) and also size of layers (20, 50, 100, 200). Report accuracy on test set. • BiLSTM: Train a single directional RNN with L layers. Vary the number of layers (as 1,2,3,4) and also size of layers (20, 50, 100, 200). Report accuracy on test set.

Bistable Recurrent Cell (BRC) and neuromodulated BRC (nBRC) implementation in PyTorch

Text generation model based on characters from friends. Originally forked from https://github.com/pender/chatbot-rnn

Build a Bitcoin predictive model. (Inputs : Klines, Google Trend data. Future inputs implementation : Liquidations data)

A sequence to sequence implementation (Encoder-Decoder network) in Keras for sorting a list of integers

Executing infamous Deep learning algorithms + Neural Networks.

A new semi supervised algorithm for classifying cross lingual texts