Through the ARDC Environments to Accelerate Machine Learning-Based Discovery project, QCIF is pleased to offer our members places on a range of Machine Learning and Visualisation workshops delivered by specialists from Monash University.
Modern deep neural networks require large amounts of labelled data to train, but obtaining the required labelled data is often an expensive and time consuming process. Semi-supervised deep learning involves the use of various creative techniques to train deep neural networks on partially labelled data. If successful, it allows better training of a model despite the limited amount of labelled data available.
This workshop covers various semi-supervised learning techniques available in the literature. The workshop consists of a lecture introducing at a high level a selection of techniques that are suitable for semi-supervised deep learning. We discuss how these techniques can be implemented and the underlying assumptions they require. This is followed by a hands-on session where you will implement a semi-supervised learning technique to train a neural network. We will observe and discuss the changing performance and behaviour of the network as varying degrees of labelled and unlabelled data is provided to the network during training.
On conclusion of this workshop, you should have a good theoretical understanding of a wide range of semi-supervised deep learning techniques for use in your research. You will also gain hands-on experience in implementing some of these techniques in your model training process.
Pre-requisites: Proficiency in Python programming with some hands-on experience in training deep neural networks is required for this workshop
A basic understanding of common deep learning concepts and methods, such as gradient descent, autoencoders, GANs, dropout, and embedding vectors, will be helpful in better understanding the various techniques discussed in this workshop. This experience can be gained from the Introduction to Deep Learning and Tensorflow workshop
Places for this workshop are very limited and only available to researchers from QCIF member institutions;
please use this form to apply. Please note, we expect demand to be high and may not be able to offer places to all applicants. REGISTRATION NOW CLOSED