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

Understanding autoencoders through playing with the pictures of Japanese multiplication.

Space signals comes with huge noise in it. For analyzing the signals we have to make sure there is as less noise as possible. Detecting the noise and denoising the signals is quite hard to do. As a Data Science Analytics one should have the capability to handling any kind of dataset.

My personal attempt to write well designed autoencoders-NNets.

Experiments with Variational Autoencoders in pytorch

In this project, I explore different methods for detecting credit card fraud transactions; including using the Catboost algorithm with undersampling & oversampling methods, and using an almost new approach, by using deep learning and autoencoder.

friendly examples of using autoencoders with different applications

Base space-time model with on top a classic autoencoder to perform video anomaly detection

Performance analysis of different Artificial Neural Networks

Design and Development of a convolutional artificial neural network to paint dogs images

Novel Pooling for anti-aliasing convolutional neural networks

Complexity Assessment of LC methods on CPU and GPU

A Recommender System that predicts ratings from 1 to 5 on MovieLens 1M Dataset

An implementation of the parser described in "Non-Projective Dependency Parsing via Latent Heads Representation (LHR) - Matteo Grella and Simone Cangialosi (2018)" [DEPRECATED]

My Deep Learning (mdl) is a repository to keep records of the most interesting learnt examples.

PyTorch implementation of different types of autoencoders

Comparison between a linear and convolutional autoencoder.

Thesis work on Video Anomaly Detection