Structured Prediction with Deep Learning

Back to search results

Structured prediction is concerned with predicting multiple interdependent variables. This project will develop the fundamental science for the next generation of structured-prediction algorithms, which will have a significant impact on a large variety of applications, such as social graphs, natural language processing, action recognition and computational biology. We develop techniques for deep learning of features in structured prediction, along with Bayesian approaches for the characterisation and quantification of uncertainty. The immediate impact of these will be reflected in better accuracy of the resulting algorithms and in a significant reduction in the amount of annotated data they require for learning.

Apply Now
Supervisory team
Edwin
Bonilla

Engineering
Computer Science and Engineering
Robert
Kohn

Business School
Economics
Aleksandar
Ignjatovic

Engineering
Computer Science and Engineering
e.bonilla@unsw.edu.au

Apply Now

Please start your application by taking the self assessment. Download the editable MS Word version or download the non-editable PDF version (best for Mac or mobile devices). Once the self assessment form is completed, save as a PDF and upload along with your application.

One file only.
50 MB limit.
Allowed types: gif jpg png bmp eps tif pict psd txt rtf html odf pdf doc docx ppt pptx xls xlsx xml avi mov mp3 ogg wav bz2 dmg gz jar rar sit svg tar zip.
If you have not done so, please complete the self assessment PDF as noted above.