Cargando…
Neural Modularity Helps Organisms Evolve to Learn New Skills without Forgetting Old Skills
A long-standing goal in artificial intelligence is creating agents that can learn a variety of different skills for different problems. In the artificial intelligence subfield of neural networks, a barrier to that goal is that when agents learn a new skill they typically do so by losing previously a...
Autores principales: | Ellefsen, Kai Olav, Mouret, Jean-Baptiste, Clune, Jeff |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2015
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4383335/ https://www.ncbi.nlm.nih.gov/pubmed/25837826 http://dx.doi.org/10.1371/journal.pcbi.1004128 |
Ejemplares similares
-
The evolutionary origins of modularity
por: Clune, Jeff, et al.
Publicado: (2013) -
Diffusion-based neuromodulation can eliminate catastrophic forgetting in simple neural networks
por: Velez, Roby, et al.
Publicado: (2017) -
Curiosity Search: Producing Generalists by Encouraging Individuals to Continually Explore and Acquire Skills throughout Their Lifetime
por: Stanton, Christopher, et al.
Publicado: (2016) -
Correction: Curiosity Search: Producing Generalists by Encouraging Individuals to Continually Explore and Acquire Skills Throughout Their Lifetime
por: Stanton, Christopher, et al.
Publicado: (2016) -
Helping skills : facilitating exploration, insight, and action /
por: Hill, Clara E., 1948-
Publicado: (2004)