Dr. Richard Granger from Dartmouth College will be presenting on the "Principles of Brain Design." Abstract: Extant artificial neural networks (deep, recurrent, etc.) represent a surprisingly modest subset of brain-like algorithms, perhaps accounting for the current wide gap between the capabilities of even the most advanced artificial systems versus human capabilities in e.g., rapid learning from few instances, learning by being taught, attention, navigation, structure, temporal sequence, semantic language meaning ... i.e., in realms other than statistical “big data” analyses such as search-based games. Meanwhile, mammalian brain circuits convey a diverse yet biologically constrained array of candidate algorithms, comprising an “instruction set” that can be composed to underlie perceptual and cognitive computations. Theoretical analyses indicate the broad scope of these algorithms, and empirical testing has directly demonstrated their power against current approaches, in range of well-studied applications domains. Notably, some longstanding challenges may be explained by these circuit methods. Recent findings have shown that the deceptively simple question of “when do two things look alike” leads to new algorithms, outperforming widely-used systems that are dependent on human similarity evaluations, including, surprisingly, JPEG compression and Image Quality Analysis (Rodriguez & Granger 2017). Bio: Richard Granger is a Professor at Dartmouth College with positions in the Psychological and Brain Sciences Department, the Thayer School of Engineering, and the Cognitive Science Program; he also is the director of the Brain Engineering Laboratory (BrainEngineering.org). He received his Bachelor’s and Ph.D. from MIT and Yale. His research ranges from computation and robotics to basic neuroscience, and he is the author of more than 100 scientific papers and numerous patents. He is a consultant to, and on the boards of, a number of technology corporations and government research agencies, and he has been the principal architect of fielded computational systems for military, commercial, and medical applications, and co-inventor of FDA-approved devices and drugs in active clinical trials.