Farida Yusuf

Profile

Project title:

Information-theoretic neural networks for online perception of auditory objects    

Abstract:

The power of deep neural networks is well evidenced in producing effective embeddings of complex data. However, the theory of deep learning is not well understood and shows a severe reliance on training data, casting a shadow over the robustness and generalisation of deep networks. A way forward is to merge neural networks with information-theoretic learning processes: if applied to sensor data (e.g. image, video, audio), this can furthermore yield organised methods of self-supervised learning that mimic cognitive learning in humans. This is particularly relevant to audio models and representations.

C4DM theme affiliation:

Machine Listening, Music Cognition

Research

Research Interests:

Auditory perception, auditory scene analysis, self-supervised learning, real-time computing