How to learn multiple tasks
| Abstract | The article examines the question of how learning multiple tasks interacts with neural architectures and the flow of information through those architectures. It approaches the question by using the idealization of an artificial neural network where it is possible to ask more precise questions about the effects of modular versus nonmodular architectures as well as the effects of sequential versus simultaneous learning of tasks. A prior work has demonstrated a clear advantage of modular architectures when the two tasks must be learned at the same time from the start, but this advantage may disappear when one task is first learned to a criterion before the second task is undertaken. Indeed, in some cases of sequential learning, nonmodular networks achieve success levels comparable to those of modular networks. In particular, if a nonmodular network is to learn two tasks of different difficulty and the more difficult task is presented first and learned to a criterion, then the network will learn the second, easier one without permanent degradation of the first one. In contrast, if the easier task is learned first, a nonmodular task may perform significantly less well than a modular one. It seems that the reason for this difference has to do with the fact that the sequential presentation of the more difficult task first minimizes interference between the two tasks. More broadly, the studies summarized in this article seem to imply that no single learning architecture is optimal for all situations. | |||||||||
| Keywords | No keywords specified (fix it) | |||||||||
| Categories | ||||||||||
| Options |
|
|||||||||
Download options| PhilPapers Archive |
Upload a copy of this paper Check publisher's policy on self-archival Papers currently archived: 5,653 |
| External links |
  Try with proxy. |
| Through your library | Only published papers are available at libraries |
Similar books and articlesJeremy Gwiazda (2012). A Proof of the Impossibility of Completing Infinitely Many Tasks. Pacific Philosophical Quarterly 93 (1):1-7.
Juyang Weng (2009). Task Muddiness, Intelligence Metrics, and the Necessity of Autonomous Mental Development. Minds and Machines 19 (1):93-115.
James Blackmon, David Byrd, Robert C. Cummins, Pierre Poirier & Martin Roth (2005). Atomistic Learning in Non-Modular Systems. Philosophical Psychology 18 (3):313-325.
Andy Clark (1994). Representational Trajectories in Connectionist Learning. Minds and Machines 4 (3):317-32.
Sam Rakover (1993). Empirical Criteria for Task Susceptibility to Introspective Awareness and Awareness Effects. Philosophical Psychology 6 (4):451 – 467.
Leendert van Maanen, Hedderik van Rijn & Niels Taatgen (2012). RACE/A: An Architectural Account of the Interactions Between Learning, Task Control, and Retrieval Dynamics. Cognitive Science 36 (1):62-101.
Chester Wolfsont, Sara Nora Ross, Patrice Marie Miller, Michael Lamport Commons & Miriam Chernoff (2008). Domain-Specific Increases in Stage of Performance in a Complete Theory of the Evolution of Human Intelligence. World Futures 64 (5 - 7):416 – 429.
Reiko Yakushijin & Robert A. Jacobs (2011). Are People Successful at Learning Sequences of Actions on a Perceptual Matching Task? Cognitive Science 35 (5):939-962.
Analytics
Monthly downloads |
Added to index2009-04-23Total downloads11 ( #99,430 of 548,984 )Recent downloads (6 months)1 ( #63,327 of 548,984 )How can I increase my downloads? |
My notes
Discussion
