| |
| | Activationist Learning |
 | | The neurophysiological basis for this novel learning algorithm is based upon the evidence from In-Vitro Reinforcement or IVR (Stein, 1997; Stein, 1995; Stein, 1994; Stein and Belluzzi, 1989), rather than the usual connectionist method based upon the neurophysiological evidence from Long-Term Potentiation or LTP (Bliss and Lømø, 1973; Bliss and Collingridge, 1993). |
 | | Because Clavier only accepts binary (yes/no) feedback on each cycle, the percentile reinforcement calculation is required to convert the latest distance measure into a binary signal by comparing how good or bad the current match is to the most recent matches on previous cycles. |
 | | A binary vector modeling the sensory inputs and the negative image of that vector are both transmitted from the second input layer to the emitter layer. |
| www.unc.edu /~skemp/documents/connectionist/ActLearn/smkActLearn.html (14356 words) |
|