Search |  Contact |  SRI Home Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap.A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A ASRI International.  333 Ravenswood Avenue.  Menlo Park, CA 94025-3493. SRI International is a nonprofit corporation.

AIC Seminar Series

Towards AGI

Miguel Lazaro GredillaVicarious[Home Page]

Notice:  Hosted by Richard Waldinger

Date:  Thursday, October 17th 2019 at 4:00pm

Location:  EK255 (SRI E building)  (Directions)

   Abstract

Being able to recognize an object, learning to play a computer game or understanding a new concept from demonstrations are all tasks that current AI technology can already address, at least in simple cases. However, most of the time the amount of data required to accomplish these tasks far exceeds what an untrained human would need. Furthermore, trained humans can immediately generalize to a number of variations of the original task, or answer queries about the data that they were not trained for.

This is due to our brain being equipped with an adequate set of representations and inductive biases. In this talk, I will cover how we try to replicate these human-like abilities in multiple domains at Vicarious: vision, planning, concept acquisition, etc. The overarching theme is translating observations from neuroscience and biology into probabilistic graphical models. I will show how this brings the performance and capabilities of our models closer to those of humans.

   Bio for Miguel Lazaro Gredilla

Miguel is the director of research at Vicarious, a startup developing artificial general intelligence for robots. He is interested in translating insights from system neuroscience into practical and scalable machine learning approaches that enable robots to be trained much faster, better understand their environment and adapt to novel scenarios. His work on brain-inspired perception and reasoning has been published in both machine learning and neuroscience venues, including both Science and Science robotics. He previously earned his PhD in machine learning at Universidad Carlos III de Madrid and has been a visiting scholar at the University of Cambridge. For the last ten years, he has been an author and regular reviewer for NIPS, ICML, and JMLR.

   Note for Visitors to SRI

Photography or broadcast of the event is prohibited unless specifically authorized by SRI. Reporters must coordinate with SRI 24 hours in advance before attending.
Please arrive at least 10 minutes early as you will need to sign in by following instructions by the lobby phone at Building E (or call Wilma Lenz at 650 859 4904, or Eunice Tseng at 650 859 2799). SRI is located at 333 Ravenswood Avenue in Menlo Park. Visitors may park in the parking lots off Fourth Street. Detailed directions to SRI, as well as maps, are available from the Visiting AIC web page. There are two entrances to SRI International located on Ravenswood Ave. Please check the Building E entrance signage.

SRI International
©2019 SRI International 333 Ravenswood Avenue, Menlo Park, CA 94025-3493
SRI International is an independent, nonprofit corporation. Privacy policy