CS231nMy solutions for Assignments of CS231n: Convolutional Neural Networks for Visual Recognition
Dense BiLSTMTensorflow Implementation of Densely Connected Bidirectional LSTM with Applications to Sentence Classification
PFL-Non-IIDThe origin of the Non-IID phenomenon is the personalization of users, who generate the Non-IID data. With Non-IID (Not Independent and Identically Distributed) issues existing in the federated learning setting, a myriad of approaches has been proposed to crack this hard nut. In contrast, the personalized federated learning may take the advantage…
rnn2dCPU and GPU implementations of some 2D RNN layers
deep-improvisationEasy-to-use Deep LSTM Neural Network to generate song sounds like containing improvisation.
ScrambleTestsRunning compostionality tests on InferSent embedding on SNLI
GAN-RNN Timeseries-imputationRecurrent GAN for imputation of time series data. Implemented in TensorFlow 2 on Wikipedia Web Traffic Forecast dataset from Kaggle.
CDRP TFCNN Event Detection & RNN Phase Picking (in Tensorflow)
GestureAIRNN(Recurrent Nerural network) model which recognize hand-gestures drawing 5 figures.
char-VAEInspired by the neural style algorithm in the computer vision field, we propose a high-level language model with the aim of adapting the linguistic style.
Speech-RecognitionEnd-to-end Automatic Speech Recognition for Madarian and English in Tensorflow
mangoQuestion-Answering NLP model with character-level RNN (TensorFlow).
yunyi2018“云移杯- 景区口碑评价分值预测
theano-recurrenceRecurrent Neural Networks (RNN, GRU, LSTM) and their Bidirectional versions (BiRNN, BiGRU, BiLSTM) for word & character level language modelling in Theano
ECGClassifierCNN, RNN, and Bayesian NN classification for ECG time-series (using TensorFlow in Swift and Python)
sequence-rnn-pySequence analyzing using Recurrent Neural Networks (RNN) based on Keras
DeepLearning-LabCode lab for deep learning. Including rnn,seq2seq,word2vec,cross entropy,bidirectional rnn,convolution operation,pooling operation,InceptionV3,transfer learning.
Deep-Learning-CourseraProjects from the Deep Learning Specialization from deeplearning.ai provided by Coursera
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).
modulesThe official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We develop a method for analyzing emerging functional modularity in neural networks based on differentiable weight masks and use it to point out important issues in current-day neural networks.
novel writerTrain LSTM to writer novel (HongLouMeng here) in Pytorch.
Customer-Feedback-AnalysisMulti Class Text (Feedback) Classification using CNN, GRU Network and pre trained Word2Vec embedding, word embeddings on TensorFlow.
sp2cpImageboard bot with recurrent neural network (RNN, GRU)
VariationalNeuralAnnealingA variational implementation of classical and quantum annealing using recurrent neural networks for the purpose of solving optimization problems.
cnn-rnn-classifierA practical example on how to combine both a CNN and a RNN to classify images.
Solar-Rad-ForecastingIn these notebooks the entire research and implementation process carried out for the construction of various machine learning models based on neural networks that are capable of predicting levels of solar radiation is captured given a set of historical data taken by meteorological stations.
cnn-rnn-bitcoinReusable CNN and RNN model doing time series binary classification
ArrayLSTMGPU/CPU (CUDA) Implementation of "Recurrent Memory Array Structures", Simple RNN, LSTM, Array LSTM..
stylegan-pokemonGenerating Pokemon cards using a mixture of StyleGAN and RNN to create beautiful & vibrant cards ready for battle!
EBIM-NLIEnhanced BiLSTM Inference Model for Natural Language Inference
IndRNN pytorchIndependently Recurrent Neural Networks (IndRNN) implemented in pytorch.
DrowsyDriverDetectionThis is a project implementing Computer Vision and Deep Learning concepts to detect drowsiness of a driver and sound an alarm if drowsy.
Rep-CounterAI Exercise Rep Counter based on Google's Human Pose Estimation Library (Posenet)