RISHIKESH JHA

Implements a basic Seq2Seq model with LSTM encoder-decoder architecture for English to French translation. Incorporates word embeddings, teacher forcing, and batch processing.

A PyTorch-based LSTM model that predicts the next word in a text sequence. Explores challenges in data preprocessing and model stability, with experiments using LSTM, BiLSTM, and BiGRU architectures.

Classifies emotions and severity levels from audiovisual data using a dual-branch model architecture with fine-tuned 3D ResNet and VGG16 for video and audio processing.

A simple implementation of a Convolutional Neural Network built from the ground up using Python and NumPy, demonstrating core CNN concepts.

This project implements the classic LeNet-5 architecture using PyTorch for handwritten digit classification on the MNIST dataset. The model achieves an impressive 98.85% test accuracy, showcasing its effectiveness in image classification tasks.

A binary image classification model using CNN to distinguish between dogs and cats, built with PyTorch and deployed on Streamlit.

An IoT-enabled Smart Poultry Farm project designed to automate and optimize farming operations using ESP32 and Firebase.

We have developed 3 simulations using Unity and Arduino for Google Cardboard VR as a prototype, for training with virtual reality. They are controlled using a modified gun which is made as the controller. If further development is done, it can give more realistic experience.