Never-Ending Learning

Mitchell, T and Cohen, W and Hruschka, E and Talukdar, P and Yang, B and Betteridge, J and Carlson, A and Dalvi, B and Gardner, M and Kisiel, B and Krishnamurthy, J and Lao, N and Mazaitis, K and Mohamed, T and Nakashole, N and Platanios, E and Ritter, A and Samadi, M and Settles, B and Wang, R and Wijaya, D and Gupta, A and Chen, X and Saparov, A and Greaves, M and Welling, J (2018) Never-Ending Learning. In: COMMUNICATIONS OF THE ACM, 61 (5). pp. 103-115.

PDF Com_ACM_61-5_105_2018.pdf - Published Version Restricted to Registered users only Download (3MB) | Request a copy

Abstract

Whereas people learn many different types of knowledge from diverse experiences over many years, and become better learners over time, most current machine learning systems are much more narrow, learning just a single function or data model based on statistical analysis of a single data set. We suggest that people learn better than computers precisely because of this difference, and we suggest a key direction for machine learning research is to develop software architectures that enable intelligent agents to also learn many types of knowledge, continuously over many years, and to become better learners over time. In this paper we define more precisely this never-ending learning paradigm for machine learning, and we present one case study: the Never-Ending Language Learner (NELL), which achieves a number of the desired properties of a never-ending learner. NELL has been learning to read the Web 24hrs/day since January 2010, and so far has acquired a knowledge base with 120mn diverse, confidence-weighted beliefs (e.g., servedWith(tea, biscuits)), while learning thousands of interrelated functions that continually improve its reading competence over time. NELL has also learned to reason over its knowledge base to infer new beliefs it has not yet read from those it has, and NELL is inventing new relational predicates to extend the ontology it uses to represent beliefs. We describe the design of NELL, experimental results illustrating its behavior, and discuss both its successes and shortcomings as a case study in never-ending learning. NELL can be tracked online at http://rtw.ml.cmu.edu, and followed on Twitter at @CMUNELL.

Item Type:	Journal Article
Publication:	COMMUNICATIONS OF THE ACM
Publisher:	ASSOC COMPUTING MACHINERY, 2 PENN PLAZA, STE 701, NEW YORK, NY 10121-0701 USA
Additional Information:	Copy right for this article belong to ASSOC COMPUTING MACHINERY, 2 PENN PLAZA, STE 701, NEW YORK, NY 10121-0701 USA
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	23 May 2018 14:55
Last Modified:	25 Aug 2022 08:37
URI:	https://eprints.iisc.ac.in/id/eprint/59921

Actions (login required)

View Item