Implementing linearly nonseparable Boolean functions (non-LSBF) has been an important and yet challenging task due to the extremely high complexity of this kind of functions and the exponentially increasing percentage of the number of non-LSBF in the entire set of Boolean functions as the number of input variables increases. In this paper, an algorithm named DNA-like learning and decomposing algorithm (DNA-like LDA) is proposed, which is capable of effectively implementing non-LSBF. The novel algorithm first trains the DNA-like offset sequence and decomposes non-LSBF into logic XOR operations of a sequence of LSBF, and then determines the weight-threshold values of the multilayer perceptron (MLP) that perform both the decompositions of LSBF and the function mapping the hidden neurons to the output neuron. The algorithm is validated by two typical examples about the problem of approximating the circular region and the well-known n-bit parity Boolean function (PBF).
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TNN.2009.2023122 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A General DNA-Like Hybrid Symbiosis Framework: An EEG Cognitive Recognition Method.
IEEE J Biomed Health Inform
November 2024
In electroencephalogram (EEG) cognitive recognition research, the combined use of artificial neural networks (ANNs) and spiking neural networks (SNNs) plays an important role to realize different categories of recognition tasks. However, most of the existing studies focus on the unidirectional interaction between an ANN and a SNN, which may be overly dependent on the performance of ANNs or SNNs. Inspired by the symbiosis phenomenon in nature, in this study, we propose a general DNA-like Hybrid Symbiosis (DNA-HS) framework, which enables mutual learning between the ANN and the SNN generated by this ANN through parametric genetic algorithm and bidirectional interaction mechanism to enhance the optimization ability of the model parameters, resulting in a significant improvement of the performance of the DNA-HS framework in all aspects.
View Article and Find Full Text PDFNanoCon: contrastive learning-based deep hybrid network for nanopore methylation detection.
Bioinformatics
February 2024
School of Software, Shandong University, Jinan, China.
Motivation: 5-Methylcytosine (5mC), a fundamental element of DNA methylation in eukaryotes, plays a vital role in gene expression regulation, embryonic development, and other biological processes. Although several computational methods have been proposed for detecting the base modifications in DNA like 5mC sites from Nanopore sequencing data, they face challenges including sensitivity to noise, and ignoring the imbalanced distribution of methylation sites in real-world scenarios.
Results: Here, we develop NanoCon, a deep hybrid network coupled with contrastive learning strategy to detect 5mC methylation sites from Nanopore reads.
DNA-like Photophysics in Self-Assembled Silver(I)-Nucleobase Nanofibers.
J Phys Chem B
July 2019
Department of Chemistry and Biochemistry , The Ohio State University, 100 West 18th Avenue , Columbus , Ohio 43210 , United States.
Supramolecular assemblies form when silver nitrate is added to an aqueous solution of adenine (Ade) or 2-aminopurine (2AP) in a 2:1 mole ratio. Atomic force microscopy images reveal nanofibers that are ∼30 nm in diameter and micrometers in length in the dried film formed from a room-temperature solution. Femtosecond broadband transient absorption spectroscopy was used to investigate the dynamics of excited states formed by UV excitation of the nanofibers in room-temperature aqueous solutions in an effort to learn how nonradiative decay pathways of the uncomplexed nucleobases are altered in the silver-ion-mediated assemblies.
View Article and Find Full Text PDFUniversal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.
IEEE Trans Neural Netw
October 2009
School of Science, Hangzhou Dianzi University, Zhejiang 310018, China.
Universal perceptron (UP), a generalization of Rosenblatt's perceptron, is considered in this paper, which is capable of implementing all Boolean functions (BFs). In the classification of BFs, there are: 1) linearly separable Boolean function (LSBF) class, 2) parity Boolean function (PBF) class, and 3) non-LSBF and non-PBF class. To implement these functions, UP takes different kinds of simple topological structures in which each contains at most one hidden layer along with the smallest possible number of hidden neurons.
View Article and Find Full Text PDFUniversal perceptron and DNA-like learning algorithm for binary neural networks: non-LSBF implementation.
IEEE Trans Neural Netw
August 2009
School of Science, Hangzhou Dianzi University, Zhejiang 310018, China.
Implementing linearly nonseparable Boolean functions (non-LSBF) has been an important and yet challenging task due to the extremely high complexity of this kind of functions and the exponentially increasing percentage of the number of non-LSBF in the entire set of Boolean functions as the number of input variables increases. In this paper, an algorithm named DNA-like learning and decomposing algorithm (DNA-like LDA) is proposed, which is capable of effectively implementing non-LSBF. The novel algorithm first trains the DNA-like offset sequence and decomposes non-LSBF into logic XOR operations of a sequence of LSBF, and then determines the weight-threshold values of the multilayer perceptron (MLP) that perform both the decompositions of LSBF and the function mapping the hidden neurons to the output neuron.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!