Towards Building an Intelligent Anti-Malware System: A Deep Learning Approach using Support Vector Machine for Malware Classification

THEANO-KALDI-RNNs is a project implementing various Recurrent Neural Networks (RNNs) for RNN-HMM speech recognition. The Theano Code is coupled with the Kaldi decoder.

Implementing different RNN models (LSTM,GRU) & Convolution models (Conv1D, Conv2D) on a subset of Amazon Reviews data with TensorFlow on Python 3. A sentiment analysis project.

Bachelor's thesis carried at Universitat Politecnica de Catalunya in partial fullfilment of the requirements for the degree in Telecommunications Technologies and Services Engineering

Stock Price prediction for Yahoo Inc. using GRU (Gated Recurrant Units) in Keras. Predicting closing price for Yahoo stocks

Image classification using CNN

Take an Emotion Walk: Perceiving Emotions from Gaits Using Hierarchical Attention Pooling and Affective Mapping

Curated implementation notebooks and scripts of deep learning based natural language processing tasks and challenges in TensorFlow.

Chatbot using Seq2Seq model and Attention

Construct a speech dataset and implement an algorithm for trigger word detection (sometimes also called keyword detection, or wakeword detection).

With an ever-increasing amount of astronomical data being collected, manual classification has become obsolete; and machine learning is the only way forward. Keeping this in mind, the LSST Team hosted the PLAsTiCC in 2018. This repository details our approach to this problem.

👨🏻‍💻 My own repository to explore LearnQuran tech product in particular -obviously- AI stuffs

Gated Recurrent Unit implementation from scratch

It analyses the movie review entered by a user for any specific movie and analyses what is the sentiment of the review. It helps the companies rate the movie and understand crowd sentiment regarding it. Sentiment analysis is a natural language processing problem where text is understood and the underlying intent is predicted.

A RNN based voice application which can do tasks when it recognizes the user speaking the Trigger word. Here the trigger word is "activate".

Recurrent Neural Network for generative MIDI music

Predictes the posible full word based on given partial text.

This repository contains Jupyter Notebook Files of some state of the art projects that I completed during my internship program in deeplearning.ai. The project files are divided into 5 main categories or respective courses that the deeplearning.ai provides.

A simple figure of speech classifier made in a jupyter notebok using keras. Gated Recurrent Units are used inplace of LSTM's becuase of little data.

Comparing Long Term Short Memory (LSTM) & Gated Re-current Unit (GRU) during forecasting of oil price .Exploring multivariate relationships between West Texas Intermediate and S&P 500, Dow Jones Utility Avg, US Dollar Index Futures , US 10 Yr Treasury Bonds , Gold Futures.

Implementation of Dynamic Memory Networks for QA System using Tensorflow

Coherent text generation with limited training data

Implementation of the paper "Show and Tell: A Neural Image Caption Generator" by Vinyals et al. (CVPR 2015)

Some Python scripts about image processing and signal analysis (Course: Intelligent Systems for Pattern Recognition)

A deep learning based application which is entitled to help the visually impaired people. The application automatically generates the textual description of what's happening in front of the camera and conveys it to person through audio. It is capable of recognising faces and tell user whether a known person is present in front of him or not.

RNN is one of the very powerful deep-learning algorithm which works amazingly well on Sequential Data. As historical or past data plays major role in the prediction of sequential data, RNN takes these inputs of not only recent output but also past output. Here I have used GRU for the prediction of eminem's Rap.

This repository contains all the work done by me for Coursera's Deep Learning Specialization.

3rd project of Deep Learning Nanodegree

Rnn (vanial, GRU and LSTM) from scratch