Computation in Nature and Lifelong Learning Machines
Colloquium | April 24 | 4-5 p.m. | 606 Soda Hall
Hava Siegelmann, DARPA
Lifelong Learning encompasses computational methods that allow systems to learn in runtime and incorporate learning for application in new, unanticipated situations. As this sort of computation is found almost exclusively in nature, Lifelong Learning looks to nature for its underlying principles and mechanisms.
An alternative model of computation for lifelong learning machines is needed, and we will discuss different computational concepts found in nature - including Super Turing computation, stochastic and asynchronous communication, continual adaptivity, and interactive computation. While seemingly different, these varied computational attributes are, in fact, computationally equivalent, implying and underlying basis for computational lifelong learning.
As part of the search for practical lifelong learning machines, we are looking to biology, where this learning paradigm is the rule. My lab has been studying neuroscience features and their translations to technology, including memory reconsolidation, oscillatory rhythms, and cognitively transparent interfaces. We will discuss out recent finding: a property of the human connectome that leads to the capability of abstraction. The analytic results identified a previously unrecognized brain connectome hierarchy, shedding light on the role of brain structure and processing pathways in creating varying levels of cognition and leading ultimately to abstract thought.
Dr. Siegelmann is a program manager at the MTO of DARPA, developing programs to advance the fields of Neural Networks and Machine Learning. She is on leave from the University of Massachusetts where she serves as the director of the Biologically Inspired Neural and Dynamical Systems (BINDS) Laboratory, a Professor of Computer Science and a Core Member of the Neuroscience and Behavior Program. She conducts interdisciplinary and edge cutting research in neural networks, machine learning, computational studies of the brain, intelligence and cognition, big data and industrial/biomedical applications.
Her research into neural processes has led to theoretical modeling and original algorithms capable of superior computation, and to more realistic, human-like intelligent systems. Siegelmann was named the 2016 Donald O. Hebb Award winner from the International Neural Network Society.
Siegelmann's Super-Turing theory introduced a major variation in computational method. It became a sub-field of computation and the foundation of lifelong machine learning, Super Turing also opens up a new way to interpret cognitive processes, as well as disease processes and their reversal. Her modeling of geometric neural clusters resulted in the highly utile and widely used Support Vector Clustering algorithm with Vladimir Vapnik and colleagues, specializing in the analysis of high-dimensional, big, complex data. Her neuroinformatics methods are used to identify overarching concepts of brain organization and function. A unifying theme underlying her research is the study of time and space dependent dynamical and complex systems. Her work is often interdisciplinary, combining complexity science, computational simulations, biological sciences and healthcare focusing on better and more completely modeling human intelligence, and spanning medical, military and energy applications. Recent contributions include advanced human-machine interfaces that empower human beyond regular capabilities, dynamical studies of the biological rhythm, and the study of brain structure that leads to abstract thoughts. Her work on energy constrained brain activation paradigm with relation to performance and diet was awarded 2015 BRAIN initiative.
Dr. Siegelmann remains very active in supporting young researchers and encouraging minorities and women to enter and advance in STEM. She has designed and taught a variety of interdisciplinary classes. She has years of experience consulting with industry, creating educational and international programs, fund raising, organization and management