Deep learning demos using MNIST data set with multiple neural network models

Simple NN for MNIST Recognition

Played with Tensorspace a library for Neural network 3D visualization, building interactive and intuitive models in browsers, supports pre-trained deep learning models from TensorFlow, Keras, TensorFlow.js

Deep Neural Networks like Single Layer Perceptron and Multi Layer Perceptron implementation using Tensorflow library on Datasets like MNIST and Naval Mine for categorical Classification. Saving and Restoring Tensorflow "Variables" weights for testing.

Short python jupyter script, for training Deep learning model for MNIST Dataset about Numbers classification from images and it's evaluation.

A Convolutional neural network heavily based upon the tensorflow advanced MNIST example but equiped with labels to visualize and allowing the user to draw an image and then have the system predict the result.

CNN model for predicting random input.

This is a DCGAN trained on MNIST model. It has all the specifications as described the original paper on Deep Convolutional General Adversarial Training

VAE Implementation with LSTM Encoder and CNN Decoder

All of the code developed as part of my learning experience in the programming language R

Digit Recognition on MNIST Data

Trained deep neural networks to predict and classify input image (MNISTDD) datasets with python.

Dockerize a Keras CNN model, which is wrapped in a Webapp using Flask Micro Framework

MNIST Digits Classification with numpy only

Study of leNet implementation in Python3.6 with Keras+Tensorflow backend.

PyTorch implementation of a feed forward neural network to classify handwritten digits from the MNIST dataset

Building a model to recognise handwritten numerical digits from images of the MNIST dataset.

Performs OCR on the MNIST dataset. From my BSc. AI & Robotics at Prifysgol Aberystwyth