Number of the records: 1
Training a Single Sigmoidal Neuron is Hard
- 1.
SYSNO ASEP 0404583 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title Training a Single Sigmoidal Neuron is Hard Author(s) Šíma, Jiří (UIVT-O) RID, SAI, ORCID Source Title Neural Computation - ISSN 0899-7667
Roč. 14, č. 11 (2002), s. 2709-2729Number of pages 20 s. Language eng - English Country US - United States Keywords sigmoidal neuron ; loading problem ; NP-hardness Subject RIV BA - General Mathematics R&D Projects LN00A056 GA MŠMT - Ministry of Education, Youth and Sports (MEYS) UT WOS 000178882900009 EID SCOPUS 0036835735 DOI 10.1162/089976602760408035 Annotation We first present a brief survey of hardness results for training feedforward neural networks. These results are then completed by the proof that the simplest architecture containing only a single neuron that applies a sigmoidal activation function \sigma:R-->[\alpha,ta], satisfying certain natural axioms, e.g. the standard (logistic) sigmoid or saturated-linear function, to the weighted sum of $n$ inputs is hard to train. In particular, the problem of finding the weights of such a unit that minimize... Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2003
Number of the records: 1