K

keras

TensorFlow examples for Artificial Neural Networks course including: MLP with softmax output layer; MLP and CNN for MNIST dataset; CNN for CIFAR-10 dataset with data augmentation; LSTM with CNN layer for IMDB sentiment classification task.

REST API written in FastAPI used to recognize images taken with mobile application.

Machine Learning Project with the Movie Lens dataset, containing the implementation of a Neural Network through Keras.

The original dataset and all the files to clean and prepare it to develop a keras model to predict houses prices.

sentiment analysis using keras and tensorflow

This project uses transfer learning to predict the cases of Pneumonia. Transfer learning is a machine learning method where model trained for a task is used as a starting point for a similar task.

A central repository where past submissions to a variety of data science competitions step from. The goal is to share a common framework (for reporting, organization, debugging etc).

Model prediction for Driven Data Prediction

Overview Help NOAA better forecast changes in Earth’s magnetic field!

The efficient transfer of energy from solar wind into the Earth’s magnetic field causes geomagnetic storms. The resulting variations i

DI assignment on encoding and classifying 28x28 images from the MNIST database. Includes a script for optimising the variables of the autoencoder using a natural evolution strategy algorithm.

Also known as "The Tradegy of Darth Python the Scripter"

comp7015-ai

Annonymizing facial footprints - anonyME allows users to inoculate their personal images against unauthorized machine learning models, with minimal distortion of the input image, and no need for prior machine learning knowledge.

An AI for the popular mobile game 2048.

A kivy-based Pong Game, and a neural network learning to play it

Playground to get started with training NN on azure cloud

A simple calculator, but with no buttons. It takes its inputs with a raspicamera and analyse it using machine learning. This project is made possible by M. Kromer.

Project containing multiple designs of neural networks with the purpose of categorising accelerometer data into driving behaviours. There are 2 densely connected ANNs for categorial classification and binary classification. Also an RNN with LSTM node

transfer learning for recommendation of woman dresses using Keras

A golang microservice for predicting next frame using tensorflow serving