This is the UNOFFICIAL implementation of the ICCV 2019 paper 'Exploiting Temporal Consistency for Real-Time Video Depth Estimation'.

Automated stock trading strategy using deep reinforcement learning and recurrent neural networks

Speech Emotion Recognition (SER) using Deep neural networks CNN and RNN

Spatiotemporal Depth Estimation using Monocular Cameras using Kitty Dataset.

This repository contains a reimplementation of the C-LSTM model and compares it with textblob and spacy.

Homeworks for Neural network methods for text processing course

CLSTM and wrapper, built for xcode (libclstm)

his is a Speech Emotion Recognition system that classifies emotions from speech samples using deep learning models. The project uses four datasets: CREMAD, RAVDESS, SAVEE, and TESS. The model achieves an accuracy of 96% by combining CNN, LSTM, and CLSTM architectures, along with data augmentation techniques and feature extraction methods.