MindPapers: 6.3g. Philosophy of Connectionism, Foundational Empirical Issues

Aizawa, Kenneth (1992). Connectionism and artificial intelligence: History and philosophical interpretation. Journal for Experimental and Theoretical Artificial Intelligence 4:1992. (Cited by 1 | Google | More links | Edit)

Berkeley, Istvan S. N. (online). Connectionism reconsidered: Minds, machines and methodology. (Cited by 1 | Google | More links | Edit)

Abstract: In this paper the issue of drawing inferences about biological cognitive systems on the basis of connectionist simulations is addressed. In particular, the justification of inferences based on connectionist models trained using the backpropagation learning algorithm is examined. First it is noted that a justification commonly found in the philosophical literature is inapplicable. Then some general issues are raised about the relationships between models and biological systems. A way of conceiving the role of hidden units in connectionist networks is then introduced. This, in combination with an assumption about the way evolution goes about solving problems, is then used to suggest a means of justifying inferences about biological systems based on connectionist research

Clark, Andy (1994). Representational trajectories in connectionist learning. Minds and Machines 4 (3):317-32. (Cited by 5 | Annotation | Google | More links | Edit)

Abstract: The paper considers the problems involved in getting neural networks to learn about highly structured task domains. A central problem concerns the tendency of networks to learn only a set of shallow (non-generalizable) representations for the task, i.e., to miss the deep organizing features of the domain. Various solutions are examined, including task specific network configuration and incremental learning. The latter strategy is the more attractive, since it holds out the promise of a task-independent solution to the problem. Once we see exactly how the solution works, however, it becomes clear that it is limited to a special class of cases in which (1) statistically driven undersampling is (luckily) equivalent to task decomposition, and (2) the dangers of unlearning are somehow being minimized. The technique is suggestive nonetheless, for a variety of developmental factors may yield the functional equivalent of both statistical AND informed undersampling in early learning

Clark, Andy & Thornton, S. (1997). Trading spaces: Computation, representation, and the limits of uninformed learning. Behavioral and Brain Sciences 20:57-66. (Cited by 204 | Google | More links | Edit)

Clark, Andy & Thornton, Chris (1997). Relational learning re-examined. Behavioral and Brain Sciences 20 (1):83-90. (Google | Edit)

Cliff, D. (1990). Computational Neuroethology: A Provisional Manifesto. In Jean-Arcady Meyer & Stewart W. Wilson (eds.), From Animals to Animats: Proceedings of The First International Conference on Simulation of Adaptive Behavior (Complex Adaptive Systems). Cambridge University Press. (Cited by 103 | Annotation | Google | More links | Edit)

Dawson, Michael R. W. & Schopflocher, D. P. (1992). Autonomous processing in parallel distributed processing networks. Philosophical Psychology 5:199-219. (Google | Edit)

Franklin, James (1996). How a neural net grows symbols. Proc 7. (Cited by 1 | Google | Edit)

Abstract: Brains, unlike artiï¬cial neural nets, use sym- bols to summarise and reason about percep- tual input. But unlike symbolic AI, they âgroundâ the symbols in the data: the sym- bols have meaning in terms of data, not just meaning imposed by the outside user. If neu- ral nets could be made to grow their own sym- bols in the way that brains do, there would be a good prospect of combining neural networks and symbolic AI, in such a way as to combine the good features of each

Graham, George (1987). Connectionism in Pavlovian harness. Southern Journal of Philosophy (Suppl.) 73:73-91. (Cited by 2 | Google | Edit)

Hanson, Susan & Burr, D. (1990). What connectionist models learn. Behavioral and Brain Sciences. (Cited by 81 | Annotation | Google | Edit)

Kaplan, S.; Weaver, M. & French, Robert M. (1990). Active symbols and internal models: Towards a cognitive connectionism. AI and Society. (Cited by 18 | Annotation | Google | More links | Edit)

Kirsh, David (1987). Putting a price on cognition. Southern Journal of Philosophy Supplement 26:119-35. (Cited by 9 | Annotation | Google | Edit)

Lachter, J. & Bever, Thomas G. (1988). The relation between linguistic structure and associative theories of language learning. Cognition 28:195-247. (Cited by 66 | Annotation | Google | More links | Edit)

Mills, Stephen L. (1989). Connectionism, the classical theory of cognition, and the hundred step constraint. Acta Analytica 4 (4):5-38. (Google | Edit)

Nelson, Raymond J. (1989). Philosophical issues in Edelman's neural darwinism. Journal of Experimental and Theoretical Artificial Intelligence 1:195-208. (Cited by 2 | Annotation | Google | More links | Edit)

O'Brien, Gerard (1998). The role of implementation in connectionist explanation. Psycoloquy 9 (6). (Cited by 8 | Google | More links | Edit)

Oaksford, Mike; Chater, Nick & Stenning, Keith (1990). Connectionism, classical cognitive science and experimental psychology. AI and Society. (Cited by 11 | Annotation | Google | More links | Edit)

Pinker, Steven & Prince, Alan (1988). On language and connectionism. Cognition 28:73-193. (Cited by 612 | Annotation | Google | More links | Edit)

Potrc, Matjaz (1995). Consciousness and connectionism--the problem of compatability of type identity theory and of connectionism. Acta Analytica 13 (13):175-190. (Google | Edit)

Ross, Don (1998). Internal recurrence. Dialogue 37 (1):155-161. (Google | Edit)

Roth, Martin (2005). Program execution in connectionist networks. Mind and Language 20 (4):448-467. (Cited by 1 | Google | Edit)

Abstract: Recently, connectionist models have been developed that seem to exhibit structuresensitive cognitive capacities without executing a program. This paper examines one such model and argues that it does execute a program. The argument proceeds by showing that what is essential to running a program is preserving the functional structure of the program. It has generally been assumed that this can only be done by systems possessing a certain temporalcausal organization. However, counterfactualpreserving functional architecture can be instantiated in other ways, for example geometrically, which are realizable by connectionist networks

6.3g	Philosophy of Connectionism, Foundational Empirical Issues [21]

Search tips