Atomistic learning in non-modular systems
Philosophical Psychology 18 (3):313-325 (2005)
| Abstract | We argue that atomistic learning?learning that requires training only on a novel item to be learned?is problematic for networks in which every weight is available for change in every learning situation. This is potentially significant because atomistic learning appears to be commonplace in humans and most non-human animals. We briefly review various proposed fixes, concluding that the most promising strategy to date involves training on pseudo-patterns along with novel items, a form of learning that is not strictly atomistic, but which looks very much like it ?from the outside? | |||||||||
| Keywords | Epistemology Learning Network Nonmodular | |||||||||
| Categories | No categories specified (fix it) | |||||||||
| Options |
|
|||||||||
| PhilPapers Archive |
Upload a copy of this paper Check publisher's policy on self-archival Papers currently archived: 5,653 |
| External links |
|
| Through your library | Configure |
Kuo-Chin Chang, Tzung-Pei Hong & Shian-Shyong Tseng (1996). Machine Learning by Imitating Human Learning. Minds and Machines 6 (2):203-228.
Sunbin Song, Howard Jr, James H. & Darlene V. Howard (2007). Implicit Probabilistic Sequence Learning is Independent of Explicit Awareness. Learning and Memory 14 (1-6):167-176.
Stephen Downes (2010). Learning Networks and Connective Knowledge. In Harrison Hao Yang & Steve Chi-Yin Yuen (eds.), Collective Intelligence and E-Learning 2.0: Implications of Web-Based Communities and Networking. IGI Global.
Rosemary J. Stevenson (1998). Training Quality and Learning Goals: Towards Effective Learning for All. Behavioral and Brain Sciences 21 (3):426-427.
Pierre Poirier (2005). Atomistic Learning in Non-Modular Systems. Philosophical Psychology 18 (3):313-325.
Monthly downloads |
Added to index2009-01-28Total downloads10 ( #106,150 of 548,979 )Recent downloads (6 months)1 ( #63,511 of 548,979 )How can I increase my downloads? |

