Hostname: page-component-8448b6f56d-tj2md Total loading time: 0 Render date: 2024-04-24T22:21:50.469Z Has data issue: false hasContentIssue false
  • English
  • Français

Digging deeper on “deep” learning: A computational ecology approach

Published online by Cambridge University Press:  10 November 2017

Massimo Buscema  and
Pier Luigi Sacco
Massimo Buscema
Affiliation:
Semeion Research Center, 00128 Rome, Italy. m.buscema@semeion.it. www.semeion.itwww.researchgate.net/profile/Massimo_Buscema University of Colorado at Denver, Denver, CO 80217
Pier Luigi Sacco
Affiliation:
IULM University of Milan, 20143 Milan, Italy. pierluigi.sacco@iulm.itwww.researchgate.net/profile/Pier_Sacco Harvard University Department of Romance Languages and Literatures, Cambridge, MA 02138. pierluigi@metalab.harvard.edupierluigi_sacco@fas.harvard.edu
Get access Rights & Permissions [Opens in a new window]

Abstract

We propose an alternative approach to “deep” learning that is based on computational ecologies of structurally diverse artificial neural networks, and on dynamic associative memory responses to stimuli. Rather than focusing on massive computation of many different examples of a single situation, we opt for model-based learning and adaptive flexibility. Cross-fertilization of learning processes across multiple domains is the fundamental feature of human intelligence that must inform “new” artificial intelligence.

Type
Open Peer Commentary
Information
Behavioral and Brain Sciences , Volume 40 , 2017 , e256
Copyright
Copyright © Cambridge University Press 2017 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Bengio, J. (2009) Learning deep architectures for AI. Foundations and Trends in Machine Learning 2(1):1–127.Google Scholar
Buscema, M. (1995) Self-reflexive networks: Theory – topology – Applications. Quality and Quantity 29(4):339–403.CrossRefGoogle Scholar
Buscema, M. (1998) Metanet*: The theory of independent judges. Substance Use and Misuse 32(2):439–61.CrossRefGoogle Scholar
Buscema, M. (2013) Artificial adaptive system for parallel querying of multiple databases. In: Intelligent data mining in law enforcement analytics, ed. Buscema, M. & Tastle, W. J., pp. 481–511. Springer.Google Scholar
Buscema, M., Grossi, E., Montanini, L. & Street, M. E. (2015) Data mining of determinants of intrauterine growth retardation revisited using novel algorithms generating semantic maps and prototypical discriminating variable profiles. PLoS One 10(7):e0126020.Google Scholar
Buscema, M., Tastle, W. J. & Terzi, S. (2013) Meta net: A new meta-classifier family. In: Data mining applications using artificial adaptive systems, ed. Tastle, W. J., pp. 141–82. Springer.Google Scholar
Buscema, M., Terzi, S. & Tastle, W.J. (2010). A new meta-classifier. In: 2010 Annual Meeting of the North American Fuzzy Information Processing Society (NAFIPS), Toronto, ON, Canada, pp. 1–7. IEEE.Google Scholar
Gazzaniga, M. (2004) Cognitive neuroscience. MIT Press.Google Scholar
Minsky, M. (1986) The society of mind. Simon and Schuster.Google Scholar