1995
DOI: 10.1142/s0129183195000423
|View full text |Cite
|
Sign up to set email alerts
|

Totem: A Highly Parallel Chip for Triggering Applications With Inductive Learning Based on the Reactive Tabu Search

Abstract: The training of a Multi-Layer Perceptron (MLP) classifier is considered as a Combinatorial Optimization task and solved using the Reactive Tabu Search (RTS) method. RTS needs only forward passes (no derivatives) and does not require high precision network parameters. TOTEM, a special-purpose VLSI chip, was developed to take advantage of the limited memory and processing requirements of RTS: the final system effects a very close match between hardware and training algorithm. The RTS algorithm and the design of … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
20
0

Year Published

1997
1997
2018
2018

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 27 publications
(20 citation statements)
references
References 0 publications
0
20
0
Order By: Relevance
“…This is manily because most combinatorial optimization problems have a very rich internal structure relating the configuration and the value [8]. In the neighborhood the vector containing the partial derivatives is the gradient, and the change of after a small displacement is approximated by the scalar product between the gradient and the displacement [38].…”
Section: Improving-neighbor [8]mentioning
confidence: 99%
“…This is manily because most combinatorial optimization problems have a very rich internal structure relating the configuration and the value [8]. In the neighborhood the vector containing the partial derivatives is the gradient, and the change of after a small displacement is approximated by the scalar product between the gradient and the displacement [38].…”
Section: Improving-neighbor [8]mentioning
confidence: 99%
“…repeat until no improvement or max CPU time elapsed 3. k ← 1 // index of the default neighborhood 4.…”
Section: Reacting On the Neighborhoodmentioning
confidence: 99%
“…Applications considered are in the area of pattern recognition (Optical Character Recognition), event triggering in High Energy Physics [3], control of non-linear systems [28], compression of EEG signals [24]. The first product of a joint project between University of Trento, INFN and IRST was the TOTEM chip [16,18], and more general special-purpose VLSI realizations are described in [4,3].…”
Section: Neural Network and Vlsi Systems With Learning Capabilitiesmentioning
confidence: 99%
See 2 more Smart Citations