31 October 2017, 12:00 - 14:00
ARITI is delighted to present our colleague Dr David Chik’s Introduction to Deep Learning.
Dr Chik’s presentation followed by a Q&A session will take place 12:00 - 13:00. Lunch and networking will take place 13:00 - 14:00.
Deep learning has become a hot research topic pursued by academia as well as big companies. Google used it to beat the world champion in the game of Go. Facebook used it to automatically tag millions of uploaded photos with the names of people. Microsoft used it to provide speech recognition. Accenture used it for cyber security. The number of potential applications seems limitless.
In this seminar, Dr Chik will explain the basic concepts of deep learning and how it is different from traditional machine learning methodologies. Three examples will be discussed: image recognition (using convolutional network structure and piecewise-linear activation functions); speech recognition (using recurrent network structure and special identity functions); and behaviour optimization (e.g. how Google trains the computer to play Pacman, using reinforcement learning with an actor-critic loop). Finally, Dr Chik will introduce some software toolkits which will be useful for researchers to use deep learning to solve their problems.
Before coming to Anglia Ruskin, David Chik worked as a software engineer in Inferret Limited Japan, where he obtained hands-on experience of developing speech recognition systems and implementing machine learning on big data. David's research experience includes KyuTech Japan, where he developed a home safety robot; RIKEN Japan, where he developed a brain model of working memory and executive functions; Plymouth University UK, where he developed a brain model of visual attention; and the University of New South Wales in Australia, where he developed a nonlinear dynamical model of heart disease.
David has published 30 refereed research articles, and received a Spotlight Presentation Award for his poster in Neuroinformatics 2010. He served as a conference session chair in DS07, and has been an invited speaker in many universities (Sydney, 2006; Exeter, 2008; Cologne, 2009; KyuTech, 2012). He's a member of UK Mathematical Neuroscience Network and Japanese Neural Network Society. David’s research interests include deep learning, mobile health, domestic robots and computational neuroscience.