Recurrent Neural Networks (RNNs) are a class of artificial neural networks designed to recognize patterns in sequences of data, such as time series, speech, or text.

This project uses an ensemble of CNN, RNN, and VGG16 models to enhance CIFAR-10 image classification accuracy and robustness. By combining multiple architectures, we significantly outperform single-model approaches, achieving superior classification performance.

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

applying different RNN architecture to build character prediction model and a word based prediction model these model are trained on data of specific topics from wikipedia

Event-based neural networks

Learned knowledge and techniques in Deep Learning and also related tools: Python, Pytorch, Jupyter Notebook, RNN, CNN, Reinforcement Learning, LSTM, BERT, Language Modeling

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.

This is my Repository for Deep Learning Project and Works

The built model(LSTM) is able to Categorize emails into Primary, Spam, Promotions and Social. Because of dataset taken from individual, it's not uploaded for privacy concern.

Image Captioning using Recurrent Neural Networks

This project uses LSTM neural networks to forecast Google Stock prices. Data is fetched from Tiingo using pandas datareader, preprocessed, and used to train the model. It's designed to run on Google Colab with GPU acceleration for faster training.

Predicting future stock values is achieved through the utilization of the Recurrent Neural Network (RNN) model, which analyzes the historical data of globally recognized companies' stocks.

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

PBL7_Support_Tourism is a web application built to help users have enjoyable trips in Vietnam. The application is developed using NodeJS (Express) and Angular with MongoDB as the database. Additionally, the application utilizes an RNN machine learning model to recognize user reviews.

Neural Networks for Neuroscience Tasks

This repository consists of RNN-model, CNN-model and use of DeepNET architectute.

Gesture control for Smart Television

Neural Network based on the Seq2Seq from Code5T to analyze code and give you a summary in plain English(natural language). This is a POC for codesapiens.ai

Here, I have developed POS-Tagging for Sanskrit Language. The dataset for the development of the model is pre-processed by me which was originally(raw-data) taken from JNU site.