This talk is co-hosted by the Center for Brains, Minds, and Machines (CBMM) and MIT Quest for Intelligence.

Abstract: Demis Hassabis will discuss the capabilities and power of self-learning systems. He will illustrate this with reference to some of DeepMind's recent breakthroughs, and talk about the implications of cutting-edge AI research for scientific and philosophical discovery.

Speaker Biography: Demis is a former child chess prodigy, who finished his A-levels two years early before coding the multi-million selling simulation game Theme Park aged 17. Following graduation from Cambridge University with a Double First in Computer Science he founded the pioneering videogames company Elixir Studios producing award winning games for global publishers such as Vivendi Universal. After a decade of experience leading successful technology startups, Demis returned to academia to complete a PhD in cognitive neuroscience at UCL, followed by postdocs at MIT and Harvard, before founding DeepMind. His research into the neural mechanisms underlying imagination and planning was listed in the top ten scientific breakthroughs of 2007 by the journal Science. Demis is a 5-times World Games Champion, a Fellow of the Royal Society of Arts, and the recipient of the Royal Society’s Mullard Award and the Royal Academy of Engineering's Silver Medal.

Abstract: The brain’s memory systems are like time machines for thought: they transport sensory experiences from the past to the present, to guide our current decisions and actions. Memories have been classified into long-term, stored for time intervals of days, months, or years, and short-term, stored for shorter intervals of seconds or minutes. There is a consensus that these two types of memories involve different brain systems and have different underlying mechanisms. In this talk I will present data from different experiments in non-human primates examining brain circuits and mechanisms of both short-term memory and long-term memory.

Biography: Julio Martinez-Trujillo is Professor in the Department of Physiology and Pharmacology and Scientist at the Robarts Research Institute. He holds an Academic Chair in Autism. Prior to joining Western University in 2014, he was Associate Professor in the Department of Physiology and Canada Research Chair in Neuroscience at McGill University.

Abstract: Our sensory systems are unable to directly sense all the aspects of the world we perceive. For example, our perception of the world as three-dimensional (3D) is compelling, but our eyes only detect two-dimensional (2D) projections of our surroundings. Creating accurate and precise 3D percepts is critical for successful interactions with our environment, but how does the brain solve this inverse problem? Using 3D vision in the macaque monkey as the model system, I will show behavioral, neuroimaging, and electrophysiological data that together reveal a hierarchical, cortical pathway specialized for implementing the 2D-to-3D visual transformation. The results of these experiments reveal roles of little explored brain areas in the dorsal visual pathway, including V3A and CIP, and have broader implications for our understanding of how the brain solves nonlinear optimization problems required to perceive what we cannot sense.

Abstract:  Estimating the mode or modal-sets (i.e. extrema points or surfaces) of an unknown density from sample is a basic problem in data analysis. Such estimation is relevant to other problems such as clustering, outlier detection, or can simply serve to identify low-dimensional structures in high dimensional-data (e.g. point-cloud data from medical-imaging, astronomy, etc).  Theoretical work on mode-estimation has largely concentrated on understanding its statistical difficulty, while less attention has been given to implementable procedures. Thus, theoretical estimators, which are often statistically optimal, are for the most part hard to implement. Furthermore for more general modal-sets (general extrema of any dimension and shape) much less is known, although various existing procedures (e.g. for manifold-denoising or density-ridge estimation) have similar practical aim. I’ll present two related contributions of independent interest: (1) practical estimators of modal-sets – based on particular subgraphs of a k-NN graph – which attain minimax-optimal rates under surprisingly general distributional conditions; (2) high-probability finite sample rates for k-NN density estimation which is at the heart of our analysis. Finally, I’ll discuss recent successful work towards the deployment of these modal-sets estimators for various clustering applications.  

Much of the talk is based on a series of work with collaborators S. Dasgupta, K. Chaudhuri, U. von Luxburg, and Heinrich Jiang. 

Speaker Biography:  Samory Kpotufe graduated with a PhD, in Sept 2010, from Computer Science at the University of California, San Diego; his advisor was Dr. Sanjoy Dasgupta. Dr. Kpotufe then joined Max Planck Institute for Intelligent Systems as a research in the department of Bernhard Schoelkopf, in the learning theory group of Ulrike von Luxburg. Following his work at MPI, Dr. Kpotufe was an Assistant Research Professor at the Toyota Technological Institute at Chicago. Prof. Kpotufe is now the Assistant Professor of Operations Research and Financial Engineering at Princeton University.

Speaker's research interests:  I work in machine learning, with an emphasis on nonparametric methods and high-dimensional statistics. Generally, I’m interested in understanding the inherent difficulty of high-dimensional problems, under practical constraints from real-world application domains. The nonparametric setting is attractive in that it captures scenarios where we have little domain knowledge, which is important as data sciences reach into a diverse range of applications.

My main practical aim is to design adaptive procedures, i.e., practical procedures that can self-tune to unknown structure in data (e.g., manifold, sparsity, clusters), while at the same time meeting the various constraints (e.g., time, space, labeling cost) of modern applications.

For more, here is a recent research statement.