Publication Details
Title: A Biological Grounding of Recruitment Learning and Vicinal Algorithms
Author: L. Shastri
Group: ICSI Technical Reports
Date: April 1999
PDF: ftp://ftp.icsi.berkeley.edu/pub/techreports/1999/tr-99-009.pdf
Overview:
Biological neural networks are capable of gradual learning based on observing a large number of exemplars over time as well as rapidly memorizing specific events as a result of a single exposure. The primary focus of research in connectionist modeling has been on gradual learning, but some researchers have also attempted the computational modeling of rapid (one-shot) learning within a framework described variably as recruitment learning and vicinal algorithms. While general arguments for the neural plausibility of recruitment learning and vicinal algorithms based on notions of neural plasticity have been presented in the past, a specific neural correlate of such learning has not been proposed. Here it is shown that recruitment learning and vicinal algorithms can be firmly grounded in the biological phenomena of long-term potentiation (LTP) and long-term depression (LTD). Toward this end, a computational abstraction of LTP and LTD is presented, and an "algorithm'' for the recruitment of binding-detector cells is described and evaluated using biologically realistic data. It is shown that binding-detector cells of distinct bindings exhibit low levels of cross-talk even when the bindings overlap. In the proposed grounding, the specification of a vicinal algorithm amounts to specifying an appropriate network architecture and suitable parameter values for the induction of LTP and LTD. Keywords: one-shot learning; memorization; recruitment learning; dynamic bindings; long-term potentiation; binding detection.
Bibliographic Information:
ICSI Technical Report TR-99-009
Bibliographic Reference:
L. Shastri. A Biological Grounding of Recruitment Learning and Vicinal Algorithms. ICSI Technical Report TR-99-009, April 1999
Author: L. Shastri
Group: ICSI Technical Reports
Date: April 1999
PDF: ftp://ftp.icsi.berkeley.edu/pub/techreports/1999/tr-99-009.pdf
Overview:
Biological neural networks are capable of gradual learning based on observing a large number of exemplars over time as well as rapidly memorizing specific events as a result of a single exposure. The primary focus of research in connectionist modeling has been on gradual learning, but some researchers have also attempted the computational modeling of rapid (one-shot) learning within a framework described variably as recruitment learning and vicinal algorithms. While general arguments for the neural plausibility of recruitment learning and vicinal algorithms based on notions of neural plasticity have been presented in the past, a specific neural correlate of such learning has not been proposed. Here it is shown that recruitment learning and vicinal algorithms can be firmly grounded in the biological phenomena of long-term potentiation (LTP) and long-term depression (LTD). Toward this end, a computational abstraction of LTP and LTD is presented, and an "algorithm'' for the recruitment of binding-detector cells is described and evaluated using biologically realistic data. It is shown that binding-detector cells of distinct bindings exhibit low levels of cross-talk even when the bindings overlap. In the proposed grounding, the specification of a vicinal algorithm amounts to specifying an appropriate network architecture and suitable parameter values for the induction of LTP and LTD. Keywords: one-shot learning; memorization; recruitment learning; dynamic bindings; long-term potentiation; binding detection.
Bibliographic Information:
ICSI Technical Report TR-99-009
Bibliographic Reference:
L. Shastri. A Biological Grounding of Recruitment Learning and Vicinal Algorithms. ICSI Technical Report TR-99-009, April 1999