Graduate studies at Western
|Abstract||It is widely appreciated that the difficulty of a particluar computation varies according to how the input data are presented. What is less understood is the effect of this computation/representation tradeoff within familiar learning paradigms. We argue that existing learning algoritms are often poorly equipped to solve problems involving a certain type of important and widespread regularity, which we call 'type-2' regularity. The solution in these cases is to trade achieved representation against computational search. We investigate several ways in which such a trade-off may be pursued including simple incremental learning, modular connectionism, and the developmental hypothesis of 'representational redescription'. In addition, the most distinctive features of human cognition- language and culture- may themselves be viewed as adaptions enabling this representation/computation trade-off to be pursued on an even grander scale.|
|Keywords||No keywords specified (fix it)|
|Categories||categorize this paper)|
|Through your library||Only published papers are available at libraries|
Similar books and articles
George Graham (1987). Connectionism in Pavlovian Harness. Southern Journal of Philosophy (Suppl.) 73 (S1):73-91.
Alison Gopnik & Laura Schulz (eds.) (2007). Causal Learning: Psychology, Philosophy, and Computation. Oxford University Press.
Susan Hanson & D. Burr (1990). What Connectionist Models Learn. Behavioral and Brain Sciences.
Robert C. Cummins & Georg Schwarz (1987). Radical Connectionism. Southern Journal of Philosophy Supplement 26 (S1):43-61.
Andy Clark (1994). Representational Trajectories in Connectionist Learning. Minds and Machines 4 (3):317-32.
Robert S. Stufflebeam (1997). Why Computation Need Not Be Traded Only for Internal Representation. Behavioral and Brain Sciences 20 (1):80-81.
Matthew Elton (1997). Cognitive Success and Exam Preparation. Behavioral and Brain Sciences 20 (1):72-73.
Andy Clark & S. Thornton (1997). Trading Spaces: Computation, Representation, and the Limits of Uninformed Learning. Behavioral and Brain Sciences 20 (1):57-66.
Chris Thornton & Andy Clark (1997). Relational Learning Re-Examined. Behavioral and Brain Sciences 20 (1):83-83.
Added to index2010-07-22
Total downloads8 ( #131,909 of 738,687 )
Recent downloads (6 months)1 ( #61,778 of 738,687 )
How can I increase my downloads?