Lifelong learning in human activity recognition with evolvable NLP techniques

This project visions to turn sensor-based human activity recognition as a NLP (natural language processing) problem; where we learn an activity pattern as a sentence that is constructed by a sequence of sensor events. With this, we can predict the next sensor event based on observed events and also more importantly we can perform lifelong […]

Continue reading

Learning to learn and extend with meta-learning

Traditionally, machine learning algorithms are designed to receive a fixed dataset as an input and after training the model will stay the same. However, in real world applications, the machine learning models often need to evolve with a constantly changing dataset that increases with new training examples. The main challenge is to tackle catastrophic forgetting; […]

Continue reading

Visualisation toolkit to bridge data and deep learning

This project aims to design and develop a web application to visualise sensor data, which will be processed and analysed by deep learning techniques, including convolutional neural networks and RNNs. The feedback from the deep learning techniques, such as the prediction accuracy, will help human to evaluate the quality of data and effectiveness of the […]

Continue reading

A.I. and Deep Learning for Guiding SAT Solvers

Deep Learning is a currently popular technique for learning patterns in many types of data, including text, images and video. Deep Learning has also been used, with success, to provide learn many types of games, most famously Go.   However, deep learning has many weaknesses, it particular it is currently unable to solve even quite […]

Continue reading