Analysing Iterative Machine Learning Algorithms with Information Geometric Methods. Online machine learning problems arise from situations where data is provided a point at a time. There are many classical algorithms for solving such problems based on the principle of stochastic gradient descent. Recent research by the CIs and others have thrown up interesting but diverse geometric connections that offer new insights. The proposed research aims to integrate the understanding of these algori ....Analysing Iterative Machine Learning Algorithms with Information Geometric Methods. Online machine learning problems arise from situations where data is provided a point at a time. There are many classical algorithms for solving such problems based on the principle of stochastic gradient descent. Recent research by the CIs and others have thrown up interesting but diverse geometric connections that offer new insights. The proposed research aims to integrate the understanding of these algorithms with the aim of designing algorithms better able to exploit prior knowledge, and to extend existing algorithms to new problem domains thus offering well principled and well understood algorithms for solving a variety of novel online problems.Read moreRead less
Electronic Auditory Pathway. We will develop electronic building blocks to investigate biological signal processing. In particular, we will investigate the auditory pathway and develop the most accurate electronic model of the biological cochlea and auditory nerve. These will be followed by electronic circuits that model the processing of sensory signals in the brain. Processing signals with neural spikes offers distinct advantages over current analogue and digital signal processing techniques i ....Electronic Auditory Pathway. We will develop electronic building blocks to investigate biological signal processing. In particular, we will investigate the auditory pathway and develop the most accurate electronic model of the biological cochlea and auditory nerve. These will be followed by electronic circuits that model the processing of sensory signals in the brain. Processing signals with neural spikes offers distinct advantages over current analogue and digital signal processing techniques in terms of noise, energy consumption and extraction of temporal information. We will implement the first spike-based models of pitch and timbre perception, and a neural model of speech recognition in noisy environments.Read moreRead less
Online Structural Health Monitoring (SHM) System Using Active Diagnostic Sensor Network. It is imperative to remain technological leading for Australian research community. But current lack of reliable technique in structural health monitoring in Australia is considerably impeding her competition with other developed countries in areas of forefront technology. Outcomes of the project will lead to an online structural health monitoring system incorporated with active diagnostic sensor network, re ....Online Structural Health Monitoring (SHM) System Using Active Diagnostic Sensor Network. It is imperative to remain technological leading for Australian research community. But current lack of reliable technique in structural health monitoring in Australia is considerably impeding her competition with other developed countries in areas of forefront technology. Outcomes of the project will lead to an online structural health monitoring system incorporated with active diagnostic sensor network, related software and hardware, novel signal processing technique, and artificial intelligence algorithm-based damage identification scheme. Its successful applications in various industries, e.g. aerospace, maritime and civil, are expected to bring significant improvement in operation safety and great benefit in reducing maintenance cost.Read moreRead less