Machine learning: how does technology see us?

This talk will describe computational methods to analyse brain Magnetic Resonance Images. MRI is a popular medical imaging modality for scanning soft tissues like the brain. I will introduce different machine learning models for recognition of patterns in brain MRI for better characterising disease like brain tumours or looking at functional differences between patients with neurological disorders and controls.

This talk will present some of the challenges faced when trying to build artistic machines. Through his work on creating adaptive musical scores for video games at Melodrive, Andrew will highlight the different musical components of the vast topic of automatic musical composition. Given his background in computational music perception and generation, he will emphasise the importance of building machine-learning models that can perform particular musical tasks, thus creating artificially intelligent composers. Andrew also once conducted a robot orchestra performing the Dr Who theme tune.

Recent years have seen significant advancements in Computer Vision algorithms, where computers can look at image and video data to understand a given scene. Be it face recognition or smart cars in real-world scenarios, computers are beginning to excel and, in some cases, surpass their human counterparts. This talk introduces the audience to the concept of machine learning, which enables computers to learn from known examples of a given task and apply their learned knowledge to a new, but similar, scenario.

What do you reveal about yourself when you use social media?  Who wants to know what your are going online?  David will take you on a typical journey through social media to identify the ways in which your personal data is exposed.  He will also suggest ways in which you can reduce these risks.  His talk is based on his research into privacy on social networks.
(Image: (c) Dave Pearson, 2007)

Computer security audit is a decision-making process about a system’s security level. This, in part, involves penetration testing: a set of targeted system compromises are launched in order to reveal potential vulnerabilities. Computer systems are always different and penetration testers ("ethical computer hackers") have to develop the attack strategy from scratch every time. One of the biggest challenges in computer security is the automation of the audit process in order to exclude human error. This talk introduces the methods of automation of penetration testing using machine learning