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

Deep Adaptive Semantic Logic Networks

Richard RohwerArtificial Intelligence Center, SRI International[Home Page]
John ByrnesArtificial Intelligence Center, SRI International

Date:  Thursday, March 16th 2017 at 4:00pm

Location:  EK255 (SRI E building)  (Directions)

Webex: 

WebEx recording (SRI WebEx access required):

https://sri-meetings.webex.com/sri-meetings/ldr.php?RCID=492c7b1d6e284ec6c05e639b49833c29

Slides (SRI Wiki access required):

https://wiki.sri.com/download/attachments/4919820/AIC_Talk_20170316.pptx?version=1&modificationDate=1489786136268&api=v2
   Abstract

Deep Neural Networks (DNNs) have received a great deal of attention recently and have demonstrated significant new capabilities in machine learning. Unfortunately, DNNs have primarily been applied to a few specific data types and designing a DNN for a new application requires a large amount of engineering from a DNN expert and an extremely large amount of data which usually needs to be manually labeled. Moreover, like the entire field of machine learning, DNNs fail to provide significant reasoning capability of the form provided by Knowledge Representation and Reasoning (KRR) technologies.

We have begun exploring an architecture which combines the formal logical structures underlying KRR and the significant learning potential of DNNs. In particular, we can use formalized knowledge (axioms) to shape the learning of distributed representations for formal symbols, allowing for generalization of vocabulary, greatly increasing the robustness of reasoning systems. We present this novel architecture.

   Bio for Richard Rohwer

   Bio for John Byrnes

  • Automated Deductive Reasoning
  • Text Analytics
  • Bayesian Inference

   Note for Visitors to SRI

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
©2017 SRI International 333 Ravenswood Avenue, Menlo Park, CA 94025-3493
SRI International is an independent, nonprofit corporation. Privacy policy