Self-Optimizing Neural Networks

Horzyk, Adrian; Tadeusiewicz, Ryszard

doi:10.1007/978-3-540-28647-9_26

Cited by 34 publications

(13 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ontogenic artificial neural networks [46,47] are examples of models of such systems. Alivon-expandor-an alivon that is an expandor.…”

Section: A Hypothetical Techno-industrial System Considered Bymentioning

confidence: 99%

The general entity of life: a cybernetic approach

Bielecki

2015

Biol Cybern

View full text Add to dashboard Cite

Life, not only in the well-known context of biochemical metabolism but also in the context of hypothetical life synthesized laboratorially or possibly found on other planets, is considered in this paper. The three-component information-energetic-structural irreducible processing in autonomous systems is the core of the proposed approach. The cybernetic organization of a general entity of life--the alivon--is postulated. The crucial properties of life and evolution are derived from the proposed approach. Information encoded in biological structures is also studied.

show abstract

“…Ontogenic artificial neural networks [46,47] are examples of models of such systems. Alivon-expandor-an alivon that is an expandor.…”

Section: A Hypothetical Techno-industrial System Considered Bymentioning

confidence: 99%

The general entity of life: a cybernetic approach

Bielecki

2015

Biol Cybern

View full text Add to dashboard Cite

show abstract

“…The construction process distinguishes the most general and discriminating features of the data. This network can adapt the topology and its weights in the deterministic process ( Horzyk & Tadeusiewicz, 2004 ).…”

Section: Classification—self Optimizing Neural Networkmentioning

confidence: 99%

“…The article presents the classification method, which belongs to the second group (shallow learning) of presented techniques, although called historically after Neural Networks. It is based on ideas presented in the works ( Horzyk & Tadeusiewicz, 2004 ; Horzyk, 2012 ). The crucial idea is to minimize the size of the neural network by pruning the unnecessary connections, which is called self-optimizing neural networks (SONN).…”

Section: Introductionmentioning

confidence: 99%

Self-optimizing neural network in the classification of real valued data

Miniak-Górecka

Podlaski

Gwizdałła

2022

PeerJ Computer Science

View full text Add to dashboard Cite

The classification of multi-dimensional patterns is one of the most popular and often most challenging problems of machine learning. That is why some new approaches are being tried, expected to improve existing ones. The article proposes a new technique based on the decision network called self-optimizing neural networks (SONN). The proposed approach works on discretized data. Using a special procedure, we assign a feature vector to each element of the real-valued dataset. Later the feature vectors are analyzed, and decision patterns are created using so-called discriminants. We focus on how these discriminants are used and influence the final classifier prediction. Moreover, we also discuss the influence of the neighborhood topology. In the article, we use three different datasets with different properties. All results obtained by derived methods are compared with those obtained with the well-known support vector machine (SVM) approach. The results prove that the proposed solutions give better results than SVM. We can see that the information obtained from a training set is better generalized, and the final accuracy of the classifier is higher.

show abstract

“…The Kohonen network ( [13,14,15,16,17,18]) (or "self-organizing map" or SOM, for short) was developed by Teuvo Kohonen. The basic idea behind the Kohonen network is to establish a structure of interconnected processing units ("neurons") which compete for the signal.…”

Section: Windowingmentioning

confidence: 99%

Automatic disordered sound repetition recognition in continuous speech using CWT and kohonen network

Codello¹,

Kuniszyk-Jóźkowiak²,

Smołka³

et al. 2012

Annales UMCS, Informatica

View full text Add to dashboard Cite

Automatic disorders recognition in speech can be very helpful for a therapist while monitoring therapy progress of patients with disordered speech. This article is focused on sound repetitions. The signal is analyzed using Continuous Wavelet Transform with 16 bark scales. Using the silence finding algorithm, only speech fragments are automatically found and cut. Each cut fragment is converted into a fixed-length vector and passed into the Kohonen network. Finally, the Kohonen winning neuron result is put on the 3-layer perceptron. Most of the analysis was performed and the results were obtained using the authors' program WaveBlaster. We use the STATISTICA package for finding the best perceptron which was then imported back into WaveBlaster and used for automatic blockades finding. The problem presented in this article is a part of our research work aimed at creating an automatic disordered speech recognition system.

show abstract

Self-Optimizing Neural Networks

Cited by 34 publications

References 2 publications

The general entity of life: a cybernetic approach

The general entity of life: a cybernetic approach

Self-optimizing neural network in the classification of real valued data

Automatic disordered sound repetition recognition in continuous speech using CWT and kohonen network

Contact Info

Product

Resources

About