Murray Shanahan is a senior research scientist at DeepMind and Professor of Cognitive Robotics at Imperial College London. Educated at Imperial College (BSc(Eng) computer science) and Cambridge University (King’s College; PhD computer science), he became a full professor at Imperial in 2006, and joined DeepMind in 2017. His publications span artificial intelligence, robotics, machine learning, logic, dynamical systems, computational neuroscience, and philosophy of mind. He is active in public engagement, and was scientific advisor on the film Ex Machina. He has written several books, including “Embodiment and the Inner Life” (2010) and “The Technological Singularity” (2015).
In spite of its undeniable effectiveness, conventional deep learning architectures have a number of limitations, such as data inefficiency, brittleness, and lack of interpretability. One way to address these limitations is to import a central idea from symbolic AI, namely the use of compositional representations based on objects and relations. In this talk I will discuss neural network architectures that learn to acquire and exploit relational information, which are a step in this direction, and will present recent work carried out at DeepMind on learning explicitly relational representations.