File(s) not publicly available
Compact Neural Network: Parameter Reduction using Sign Combinations
journal contribution
posted on 2023-07-26, 13:56 authored by David ChikOne problem of using neural network to learn real life data is that there are too many parameters (weights) to tune. Here, a new method of reducing the number of parameters is proposed. The basic idea is to represent individual nodes by vectors of different combinations of positive or negative signs. Nonlinear relationship between the nodes can therefore be encoded in their sign combinations. This Compact Neural Network can implement Parity without hidden nodes. It can also achieve the same generalization performance on real life data using a fewer number of hidden layers and nodes. More importantly, this network does not need heuristics (e.g. manually design a polynomial form as in functional link neural network) and can be scaled up easily to become a deep network for solving very complicated classification problems.
History
Refereed
- Yes
Volume
8Issue number
8Publication title
ICIC Express LettersISSN
1881-803XPublisher
ICIC InternationalLanguage
- other
Legacy posted date
2016-10-12Legacy creation date
2016-09-29Legacy Faculty/School/Department
ARCHIVED Faculty of Science & Technology (until September 2018)Usage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC