pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.

Text classification using deep learning models in Pytorch

A simple state update rule to enhance length generalization for CUT3R

Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation implemented by Pytorch

RNNSharp is a toolkit of deep recurrent neural network which is widely used for many different kinds of tasks, such as sequence labeling, sequence-to-sequence and so on. It's written by C# language and based on .NET framework 4.6 or above versions. RNNSharp supports many different types of networks, such as forward and bi-directional network, sequence-to-sequence network, and different types of layers, such as LSTM, Softmax, sampled Softmax and others.

A R/Shiny app for interactive RNN tensorflow models

I used in this project a reccurent neural network to generate c code based on a dataset of c files from the linux repository.

A food ordering android application with feedback analyzer to improve food suggestions to customer.

generate captions for images using a CNN-RNN model that is trained on the Microsoft Common Objects in COntext (MS COCO) dataset

Recurrent Neural Network (LSTM) by using TensorFlow and Keras in Python for BitCoin price prediction

Price Prediction Case Study predicting the Bitcoin price and the Google stock price using Deep Learning, RNN with LSTM layers with TensorFlow and Keras in Python. (Includes: Data, Case Study Paper, Code)

Cyber Security: Development of Network Intrusion Detection System (NIDS), with Machine Learning and Deep Learning (RNN) models, MERN web I/O System.

Deep Learning notes and practical implementation with Tensorflow and keras. Text Analytics and practical application implementation with NLTK, Spacy and Gensim.

Sinhalese Language based Hate Speech Detection

Event-based neural networks

No description provided.

Time series forecasting using RNN, Twitter Sentiment Analysis and Turtle Trading Strategy applied on Cryptocurrency

Cyber Security: Development of Network Intrusion Detection System (NIDS), with Machine Learning and Deep Learning (RNN) models, MERN web I/O System. The deployed project link is as follows.

Cyber Security: Development of Network Intrusion Detection System (NIDS), with Machine Learning and Deep Learning, Recurrent Neural Network models, MERN web I/O System.

A comprehensive collection of 25+ recurrent neural network layers for Lux.jl

A QA System based by BiLSTM. 一个基于双向LSTM的智能问答系统，有交互界面、详细注释、多版本、能运行、文件齐全。

Annabelle the noob. An experimental, incomplete(at present) chatbot.

An AI chatbot built using SEQ2SEQ Model

基于tensorflow搭建的神经网络recursive autuencode，用于实现句子聚类

Depression detection from social media

Built RNNs that can generate sequences based on input data - with a focus on two applications: used real market data in order to predict future Apple stock prices using an RNN model. The second one will be trained on Sir Arthur Conan Doyle's classic novel Sherlock Holmes and generates wacky sentences based on it that may - or may not - become the next great Sherlock Holmes novel.

Piano music generation with RNN with Tensorflow

A repository for my pytorch models

Deep Learning, Attention, Transformers, BERT, GPT-2, GTP-3

make stock prediction model using Tensorflow, Python and web crawling