Multi-Class Text Classification for products based on their description with Machine Learning algorithms and Neural Networks (MLP, CNN, Distilbert).

deep-learning machine-learning

Streamlit web app

Sentiment analysis - Pytorch

NLP-clustering(word) -Vietnamese Sentiment Analysis using artificial neural network

Быстрая и удобная библиотека для оценки тональности текста с использованием нейросети

Developed CNN-based DDoS detection for SDN using TensorFlow/Keras, achieving >95% multi-class accuracy. Plans include real-world deployment with mitigation for SDN resilience against cyber threats.

Develop a DDoS attack detection system for SDN using machine learning and deep learning, leveraging SDN datasets for binary and multi-class classification. Implement CNN models with preprocessing, data balancing, and comprehensive evaluation for enhanced network security.

Implemented a convolutional neural network (CNN) for digit recognition using the MNIST dataset. The data, which consists of images of handwritten digits, is first preprocessed by normalizing pixel values to a [0,1] range and reshaping the images to fit the input requirements of the model.

Advanced Deep Learning for Text with Pytorch on Datacamp Platform

Tutorials on getting started with PyTorch and TorchText for sentiment analysis.

Pytorch implementation of the paper Deep learning for extreme multi-label text classification

My academic Streamlit Web Application

Used Tensorflow and Keras Framework

Tweets sentiment classification using CNN

TextClf ：基于Pytorch/Sklearn的文本分类框架，包括逻辑回归、SVM、TextCNN、TextRNN、TextRCNN、DRNN、DPCNN、Bert等多种模型，通过简单配置即可完成数据处理、模型训练、测试等过程。

Recognizing handwritten character image using CNN with the CNN model trained using image dataset

Weather-Flight-Bot, a combined model of semantics slot-filling and intent detection powered by neural network (LSTM and CNN layers).

🦖 Emergency Call Response System (Imagine Cup 2018)

Project of Paraphrase Identification Based on Weighted URAE, Unit Similarity and Context Correlation Feature