Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

September 1993, Vol. 5, No. 5, Pages 783-794
(doi: 10.1162/neco.1993.5.5.783)
© 1993 Massachusetts Institute of Technology
Construction of Minimal n-2-n Encoders for Any n
Article PDF (660.56 KB)
Abstract

The encoding problem (Rumelhart and McClelland 1986) is an important canonical problem. It has been widely used as a benchmark. Here, we have analytically derived minimal-sized nets necessary and sufficient to solve encoding problems of arbitrary size. The proofs are constructive: we construct n-2-n encoders and show that two hidden units are also necessary for n > 2. Moreover, the geometric approach employed is general and has much wider applications. For example, this method has also helped us derive lower bounds on the redundancy necessary for achieving complete fault tolerance (Phatak and Koren 1992a,b).