A method for training recurrent neural networks for classification by building basins of attraction

Brouwer, Roelof K.

doi:10.1016/0893-6080(94)00102-r

Cited by 15 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using this concept has allowed researchers to derive methods of reducing the energy, and thus the errors, of the system (Brouwer 1995). Various extensions of this concept have been investigated, including Lyapunov Functions (François and Zaharie 1999) and stored pattern capacity (Lin et al 1998a,b).…”

Section: Neural Networkmentioning

confidence: 98%

The state of play in machine/environment interactions

Aitkenhead

McDonald

2006

Artif Intell Rev

View full text Add to dashboard Cite

Due to the breadth of the subject, it is no longer possible to provide a review of all of the work being carried out in the field of Artificial Intelligence. However, a more localised review of research taking place in the overlap between engineering, AI and psychology can be meaningfully performed. We show here that while there have been marked successes in the past few years, there is an identifiable set of 'classic' problems that remain to be solved, and which largely direct the work ongoing in this area. This review aims to discuss the directions being taken at the current time, in particular the developing and maturing possibilities provided by neural networks and evolutionary computation, and by the use of our knowledge of the mind in developing artificial agents capable of mimicking our abilities to interact with the environment.

show abstract

Section: Neural Networkmentioning

confidence: 98%

The state of play in machine/environment interactions

Aitkenhead

McDonald

2006

Artif Intell Rev

View full text Add to dashboard Cite

show abstract

“…Thus the vector (4, 6, 2) is represented by the string 111100111111011000 assuming field widths of 6 for the first component, 7 for the second component and 5 for the third component. The string 1110001111010010 with field width vector (6,5,3,2) represents the vector (3, 4, 1, 1). The field width vector is required to partition the binary vector.…”

Section: From Vectors Of Natural Numbers To Binary and Bipolar Vectorsmentioning

confidence: 99%

“…Thus 1010100111101001 with field width vector (6,5,3,2) would also represent the vector (3, 4, 1, 1). The usefulness of the nonstandard representation is that it is more robust.…”

Section: From Vectors Of Natural Numbers To Binary and Bipolar Vectorsmentioning

confidence: 99%

See 1 more Smart Citation

An Integer Recurrent Artificial Neural Network for Classifying Feature Vectors

Brouwer¹

2000

Int. J. Patt. Recogn. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

The main contribution of this paper is the development of an Integer Recurrent Artificial Neural Network (IRANN) for classification of feature vectors. The network consists both of threshold units or perceptrons and of counters, which are non-threshold units with binary input and integer output. Input and output of the network consists of vectors of natural numbers that may be used to represent feature vectors. For classification purposes, representatives of sets are stored by calculating a connection matrix such that all the elements in a training set are attracted to members of the same training set. The class of its attractor then classifies an arbitrary element if the attractor is a member of one of the original training sets. The network is successfully applied to the classification of sugar diabetes data, credit application data, and the iris data set.

show abstract

“…The derived set of decision rules can be used to reveal the basic relations and laws in the problem domain in an explicit and transparent form and, of course, can be used for diagnosing new patients. In several medical domains the inductive learning systems [Kononenko et al, 1984, Horn et al, 1985, Roskar et al, 1986, Kukar et al, 1996 and neural network based algorithms [Alpsan et al, 1995, Baxt, 1991, Brouwer, 1994, Roy et al, 1995, Ster et al, 1995, Ster and Dobnikar, 1995 were applied.…”

Section: Introductionmentioning

confidence: 99%