This repo contains implementation of some basic ML algorithms from scratch on PyTorch with GPU support.

This repository contains a recurrent neural network (rnn) that was trained on Chopin's nocturnes. It also contains a program that parses midi files into strings of characters that are more easily understood by the rnn.

Vanilla RNN example on the MNIST dataset using a 1-1 RNN model with one timestep.

Wine Quality Classification Using Deep Learning

A type of potential-based recurrent neural networks implemented with PyTorch

Bachelor Project: Training a hierarchical RNN Network to infer navigation in a dynamic scenario

Song lyrics generation using Recurrent Neural Networks (RNNs)

Predict whether the number of confirmed people will increase or not with the use of RNN.

turbESN is an echo state network implementation, used in my PhD research as part of the DeepTurb project of the Carl-Zeiss Stiftung. See https://pypi.org/project/turbESN/

Tear open RNNs and LSTMs, wire them back together with BPTT and from-scratch optimizers and activations

Rede Neural Artificial para análise de sentimentos em sentenças em língua inglesa. A Rede Neural Artificial Recursiva Long Short-Term Memory foi implementada para o treinamento do modelo de análise. Com a aplicação da RNA desenvolvida sobre uma base de dados pública com 50.000 registros de filmes usando GPU foi possível reduzir o tempo de treina…

Classifies emails into ham or spam based on the mail contents. Implemented with TensorFlow.

Bengali sentiment analysis by using Recurrent Neural Network (RNN). Python project.

text classification using RCNN, cutting-edge technology,

Recurrent autoencoder with sequence-aware encoding - recurrent autoencoder, which trains faster.

This is a Recurrent Neural Network based project to generate Novel readable tweets from a short list of given tweets.

RNNs with layer normalization; Prep package for tensorflow/addons, see v0.8.2, and commit https://github.com/tensorflow/addons/commit/cdb43ffd7e4b89d6ce8cdadcd62fec46c7f0f7fa

Web app where users can analyze the sentiment of recent tweets using an RNN to determine how society feels about certain issues

Code for "Sufficient conditions for offline reactivation in recurrent neural networks" (ICLR 2024)

Deep-learned metallicity estimation of RR Lyrae-type pulsating stars from their G and Ks light curves