March 23, 2021

Semi-Supervised Deep Learning

Register now for our upcoming Semi-Supervised Deep Learning workshop delivered online via Zoom on Tuesday, 23 March from 10:00am – 1:00pm AEDT. We strongly recommend that you log on from 10:00am AEDT to troubleshoot any connection issues to Zoom and Slack.

Modern deep neural networks require large amounts of labelled data to train. 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, reducing the amount of labelled data required.

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. The lecture is followed by a hands-on session where attendees implement a semi-supervised learning technique to train a neural network. We observe and discuss the changing performance and behaviour of the network as varying degrees of labelled 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 available in the literature for use in your research. You will also gain hands-on experience in implementing some of these techniques in your model training process.

Prerequisites: 

  • Foundational level Python programming – you may wish to attend the Data Fluency: Introduction to Python workshop
  • Some hands-on experience with deep learning
  • Basic understanding of a broad range of common deep learning concepts and methods such as gradient descent, autoencoders, variational autoencoders, GANs, dropout, embedding vectors, etc.
What you’ll need: A computer with speakers and a microphone (note: webcams and dual monitors are recommended but not required). A Google Chrome or Firefox web browser and Zoom are the only required software.  A Zoom link and instructions will be sent to registrants 2 days prior to the workshop.

~

How to register? 

1. Monash staff and Graduate Research students register here
Note: Data Fluency workshops are now only available staff to Graduate Research students.

2. 2. Monash external affiliate partners, MASSIVE partners and users, Monash ARDC project partners and users register here.

~
Data Fluency for Research is a cross-disciplinary initiative developing researcher capability at Monash University. Keep an eye out for additional upcoming workshops across our campuses by logging in to your myDevelopment training space, and also by subscribing to the Data Fluency mailing list to receive updates on events and workshops.Need some urgent individual advice, help troubleshooting your code, or just want to meet members of our community? Join our informal Friday drop-in sessions virtually from 3pm-4pm via Zoom by clicking here.