One-Shot Recognition of Manufacturing Defects in Steel Surfaces

CartPole game by Reinforcement Learning, a journey from training to inference

babble-rnn is a research project in the use of machine learning to generate new speech by modelling human speech audio, without any intermediate text or word representations. The idea is to learn to speak through imitation, much like a baby might.

Realtime Facial recognition system using Siamese neural network

Recurrent Neural Network (LSTM) by using TensorFlow and Keras in Python for BitCoin price prediction

Implementation of Facial Recognition System Using Facenet based on One Shot Learning Using Siamese Networks

Official PyTorch implementation of our IGARSS'22 paper: A Transformer-Based Siamese Network for Change Detection

Usage of Siamese Recurrent Neural network architectures for semantic textual similarity

Siamese Network on MNIST Dataset

Keras4Delphi is a high-level neural networks API, written in Pascal with Python Binding

Art to Image Style Transfer using Keras and Tensorflow.

Deep learning for freehand sketch object recognition

Tensorflow Implementation of FaceNet: A Unified Embedding for Face Recognition and Clustering to find the celebrity whose face matches the closest to yours.

Semestral project for the subject Methods of computational inteligence @ fit.cvut.cz

Deep Learning Stock Volatility with Google Domestic Trends: https://arxiv.org/pdf/1512.04916.pdf

Context-Aware Visual Compatibility Prediction (https://arxiv.org/abs/1902.03646)

Implementation of One Shot Learning using Convolutional Siamese Networks on Omniglot Dataset

Using SigComp'11 dataset for signature verification

Serving a keras model (neural networks) in a website with the python Django-REST framework.

Learning to Rank from Pair-wise data