中文长文本分类、短句子分类、多标签分类、两句子相似度（Chinese Text Classification of Keras NLP, multi-label classify, or sentence classify, long or short），字词句向量嵌入层（embeddings）和网络层（graph）构建基类，FastText，TextCNN，CharCNN，TextRNN, RCNN, DCNN, DPCNN, VDCNN, CRNN, Bert, Xlnet, Albert, Attention, DeepMoji, HAN, 胶囊网络-CapsuleNet, Transformer-encode, Seq2seq, SWEM, LEAM, TextGCN

NLP research：基于tensorflow的nlp深度学习项目，支持文本分类/句子匹配/序列标注/文本生成 四大任务

All kinds of neural text classifiers implemented by Keras

MXNet for CTR

Speech Emotion Recognition Using Deep Convolutional Neural Network and Discriminant Temporal Pyramid Matching

Application of Demosaicking and Super Resolution on Bayer Image with Convolutional Neural Network

Robust Single Sample Face Recognition by Sparsity-Driven Sub-Dictionary Learning Using Deep Features

Keras based implementation of "Deconvolutional Paragraph Representation Learning"

Journal Article: International Journal of Information Technology

Japanese Handwritten Character Recognition using DropBlock Regulzarization

Robust Lane Detection in hazy/foggy environment using Encoder Decoder CNN & LSTM and Dark Channel Prior to tackle with hazy environemnt

implementation of dynamic convolutional neural network for text classification

Tropical Cyclone Intensity Classification and Estimation Using Infrared Satellite Images with Deep Learning

Pytorch implementation of a sentence sentiment classification model with CNN, RNN, RNF (Recurrent Neural Filter) and BERT

Parking space detection with tflearn and python

Code repository for the manuscript "Modeling naturalistic face processing in humans with deep convolutional neural networks" (https://doi.org/10.1101/2021.11.17.469009)

I've worked on a research project implementing Double Convolution Neural Network using, lasagne, theano, Caffe, and Matlab using PYTHON.

All kinds of neural text classifiers implemented by Keras

Feature Engineering for Sleep Spindle classification

This application performs sentiment analysis using a Deep CNN model built with TensorFlow. It provides a GUI where users can enter text and see whether the sentiment is positive or negative.