Putting representations to use | Synthese
Are there representations in the brain? It depends on what you mean by representations, and it depends on what you want them to do for you—both in terms of the causal role they play in the system, and in terms of their explanatory value. But ideally, we would like an account of representation that allows us to (a) assign a representational role and content to the appropriate mechanistic precursors of behavior that in fact play that role (if any do) and (b) conversely, search for the mechanistic realizers of representational roles that are posited by our models of behavior and cognition. Such an account would be methodologically valuable in neuroscience. Lately, people have started asking similar questions about deep neural networks. What representations do they learn and use, and what is the relation between those representations and the sometimes impressive capacities these networks exhibit? More philosophically puzzling, perhaps, is the question of why the internal activities or disp
Putting representations to use Original Research Published: 15 April 2022 Volume 200 , article number 151 ( 2022 ) Cite this article Save article View saved research Synthese Aims and scope Submit manuscript Abstract Are there representations in the brain? It depends on what you mean by representations , and it depends on what you want them to do for you—both in terms of the causal role they play in the system, and in terms of their explanatory value. But ideally, we would like an account of representation that allows us to (a) assign a representational role and content to the appropriate mech
Explore this link on the map →related reading
- Toy Models of Superpositiontransformer-circuits.pub
- The Platonic Representation Hypothesisphillipi.github.io
- https://io0.github.ioio0.github.io
- Neuroscience is pre-paradigmatic. Consciousness is whytheintrinsicperspective.com
- The World Inside Neural Networksgoodfire.ai
- A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org
- Interpretability Dreamstransformer-circuits.pub
- A deep learning framework for neuroscience - PMCncbi.nlm.nih.gov
- Representational geometry: integrating cognition, computation, and the brain - PMCncbi.nlm.nih.gov
- Perfectly Normalperfectlynormal.co.uk
- Neural Networks, Types, and Functional Programming -- colah's blogcolah.github.io
- The Philosophy of Neuroscience (Stanford Encyclopedia of Philosophy)plato.stanford.edu