Mind, Technology, and Society Talk Series

Speaker:
Emre Neftci
Assistant Professor, UC Irvine
Time/Date: 3-4:30 p.m. Monday, February 1, 2016

Location:
KL232

Title:
Neuromorphic Cognition

Abstract:
Our ability to evoke intelligent processing on artificial neural systems goes hand in hand with a confluence of neuroscience, machine learning and engineering. I will describe recent advances in neuromimetic inference and learning algorithms that address this challenge from a neuromorphic systems perspective. These algorithms range from finite state machines synthesized with neural models of working memory, attention and action selection for solving cognitive tasks; to the learning of probabilistic generative models with models of stochastic sampling and plasticity in spiking neural networks. These advances form the groundwork for a domain-specific language for probabilistic models that can be compiled against neural substrates. Combined with state-of-the-art neuromorphic electronic hardware, this framework will provide a unique technology for studying the processes of the mind at multiple levels of investigation.

Recommended reading:
Memory and Information Processing in Neuromorphic Systems, Proc. IEEE. Indiveri and Liu, 2015. http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7159144&tag=1

Bio:
Emre Neftci received his degree in Physics at EPF Lausanne and his PhD with Prof. Indiveri in Neuroinformatics at the Institute of Neuroinformatics, ETH Zurich. His thesis described a methodology for synthesizing state-dependent computations in mixed-signal neuromorphic systems. In 2012, Dr. Neftci joined the Insitute of Neural Computation (INC), UC San Diego as a post-doctoral fellow in the lab of Gert Cauwenberghs to investigate models for probabilistic state-dependent sensorimotor processing in large-scale multi-neuron systems. In 2015, he joined the faculty of the department of Cognitive Sciences at UC Irvine. His current research focuses on theoretical and computational modeling of learning in neural systems that exploit the features of neuromorphic hardware.