lmkitlanguage models toolkits with hierarchical softmax setting
deep-improvisationEasy-to-use Deep LSTM Neural Network to generate song sounds like containing improvisation.
Machine-LearningThe projects I do in Machine Learning with PyTorch, keras, Tensorflow, scikit learn and Python.
dtsA Keras library for multi-step time-series forecasting.
MogrifierLSTMA quick walk-through of the innards of LSTMs and a naive implementation of the Mogrifier LSTM paper in PyTorch
Manhattan-LSTMKeras and PyTorch implementations of the MaLSTM model for computing Semantic Similarity.
CharLSTMBidirectional Character LSTM for Sentiment Analysis - Tensorflow Implementation
Learning-Lab-C-LibraryThis library provides a set of basic functions for different type of deep learning (and other) algorithms in C.This deep learning library will be constantly updated
Robust-Deep-Learning-PipelineDeep Convolutional Bidirectional LSTM for Complex Activity Recognition with Missing Data. Human Activity Recognition Challenge. Springer SIST (2020)
Intelligent-Bangla-typing-assistantArtificially intelligent typing assistant that suggest the next word using user typing history and full sentence using LSTM . Works with any environment (MS word, notepad, coding IDEs or anything)
object-trackingMultiple Object Tracking System in Keras + (Detection Network - YOLO)
CS231nPyTorch/Tensorflow solutions for Stanford's CS231n: "CNNs for Visual Recognition"
SpectrumSpectrum is an AI that uses machine learning to generate Rap song lyrics
Patient2VecPatient2Vec: A Personalized Interpretable Deep Representation of the Longitudinal Electronic Health Record
lstm-mathNeural network that solves math equations on the character level
ntua-slp-semeval2018Deep-learning models of NTUA-SLP team submitted in SemEval 2018 tasks 1, 2 and 3.
Speech-RecognitionEnd-to-end Automatic Speech Recognition for Madarian and English in Tensorflow
traffic-predictionPredict traffic flow with LSTM. For experimental purposes only, unsupported!
iPerceiveApplying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering | Python3 | PyTorch | CNNs | Causality | Reasoning | LSTMs | Transformers | Multi-Head Self Attention | Published in IEEE Winter Conference on Applications of Computer Vision (WACV) 2021
OCROptical character recognition Using Deep Learning
theano-recurrenceRecurrent Neural Networks (RNN, GRU, LSTM) and their Bidirectional versions (BiRNN, BiGRU, BiLSTM) for word & character level language modelling in Theano
deep-transTransliterating English to Hindi using Recurrent Neural Networks
SentimentAnalysis(BOW, TF-IDF, Word2Vec, BERT) Word Embeddings + (SVM, Naive Bayes, Decision Tree, Random Forest) Base Classifiers + Pre-trained BERT on Tensorflow Hub + 1-D CNN and Bi-Directional LSTM on IMDB Movie Reviews Dataset
sequence-rnn-pySequence analyzing using Recurrent Neural Networks (RNN) based on Keras
LearningMetersPoemsOfficial repo of the article: Yousef, W. A., Ibrahime, O. M., Madbouly, T. M., & Mahmoud, M. A. (2019), "Learning meters of arabic and english poems with recurrent neural networks: a step forward for language understanding and synthesis", arXiv preprint arXiv:1905.05700
voice zaloaidentifying gender and regional accent from speech
SpeakerDiarization RNN CNN LSTMSpeaker Diarization is the problem of separating speakers in an audio. There could be any number of speakers and final result should state when speaker starts and ends. In this project, we analyze given audio file with 2 channels and 2 speakers (on separate channels).
deep-char-cnn-lstmDeep Character CNN LSTM Encoder with Classification and Similarity Models
extkerasPlayground for implementing custom layers and other components compatible with keras, with the purpose to learn the framework better and perhaps in future offer some utils for others.
novel writerTrain LSTM to writer novel (HongLouMeng here) in Pytorch.