Approximate logic neuron model trained by states of matter search algorithm

Ji, Junkai; Song, Shuangbao; Tang, Yajiao; Gao, Shangce; Tang, Zheng; Todo, Yuki

doi:10.1016/j.knosys.2018.08.020

Cited by 41 publications

(25 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to our previous studies [16], [24], [33], the constant paramaters c, c soma , and γ of ALDNM are set to 5, 5, and 0.5, respectively. Each dataset is randomly split into two subsets in one experiment.…”

Section: Experimental Studymentioning

confidence: 99%

“…In [32], the authors conducted a comprehensive study of randomized algorithms for training ANNs. Additional research in [33] employed a states of matter search (SMS) for training a dendritic neuron model. These successful applications motivate our attempts to investigate the efficiencies of heuristic optimization methods in training neuron models.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Training an Approximate Logic Dendritic Neuron Model Using Social Learning Particle Swarm Optimization Algorithm

et al. 2019

Self Cite

View full text Add to dashboard Cite

With the rapid development of artificial neural networks, recent studies have shown that dendrites play a vital role in neural computations. In this study, we propose a dendritic neuron model called the approximate logic dendritic neuron model (ALDNM) to solve classification problems. The ALDNM can be divided into four layers: the synaptic layer, the dendritic layer, the membrane layer, and the soma body. Considering the limitation of the back-propagation (BP) algorithm, we employ a heuristic optimization called the social learning particle swarm optimization algorithm (SL-PSO) to train the ALDNM. In order to investigate the effectiveness of SL-PSO for training the ALDNM, we compare this training method with BP and four other typical heuristic optimization methods. Moreover, the proposed ALDNM is also compared with seven classifiers to verify its performance. The experimental results and statistical analysis on four classification problems indicate that the proposed ALDNM trained by SL-PSO can provide a competitive performance for solving the classification problems. It is worth emphasizing that the structure of the trained ALDNM can be greatly simplified owing to the unique pruning operations. Furthermore, the simplified ALDNM for a specific problem can be converted into a corresponding logic circuit classifier for a fast classification.INDEX TERMS dendritic neuron model, heuristic optimization, classification, pruning, logic circuit.

show abstract

Section: Experimental Studymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Training an Approximate Logic Dendritic Neuron Model Using Social Learning Particle Swarm Optimization Algorithm

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…The functions of Mr 2 DNM approximately correspond to the “comparator,” logical “NOT,” “AND,” and “OR” operation, respectively [32, 45]. Thence, the simplified neuron morphology can be replaced by the logic circuits, and the corresponding logic circuits for the BUPA as an example are shown in Figure 10.…”

Section: Experiments and Analysismentioning

confidence: 99%

Mr2DNM: A Novel Mutual Information-Based Dendritic Neuron Model

Qian

Wang

Cao

et al. 2019

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

By employing a neuron plasticity mechanism, the original dendritic neuron model (DNM) has been succeeded in the classification tasks with not only an encouraging accuracy but also a simple learning rule. However, the data collected in real world contain a lot of redundancy, which causes the process of analyzing data by DNM become complicated and time-consuming. This paper proposes a reliable hybrid model which combines a maximum relevance minimum redundancy (Mr2) feature selection technique with DNM (namely, Mr2DNM) for classifying the practical classification problems. The mutual information-based Mr2 is applied to evaluate and rank the most informative and discriminative features for the given dataset. The obtained optimal feature subset is used to train and test the DNM for classifying five different problems arisen from medical, physical, and social scenarios. Experimental results suggest that the proposed Mr2DNM outperforms DNM and other six classification algorithms in terms of accuracy and computational efficiency.

show abstract

“…Most recently, a dendritic neuron model (DNM) with nonlinear synapses has been proposed [12][13][14]. Different from DMNN, DNM only considers a single neuron rather than the network of a couple of neurons and has shown great information processing capacity [15][16][17][18][19]. e DNM uses a pruning technique derived from an interesting biological phenomenon: in the early stages of neuron triggering, the selective removal of unnecessary synapses and dendrites does not cause neuron cell death [20,21].…”

Section: Introductionmentioning

confidence: 99%

A Dendritic Neuron Model with Adaptive Synapses Trained by Differential Evolution Algorithm

Wang

Gao

Wang

et al. 2020

Computational Intelligence and Neuroscience

Self Cite

View full text Add to dashboard Cite

A dendritic neuron model with adaptive synapses (DMASs) based on differential evolution (DE) algorithm training is proposed. According to the signal transmission order, a DNM can be divided into four parts: the synaptic layer, dendritic layer, membrane layer, and somatic cell layer. It can be converted to a logic circuit that is easily implemented on hardware by removing useless synapses and dendrites after training. This logic circuit can be designed to solve complex nonlinear problems using only four basic logical devices: comparators, AND (conjunction), OR (disjunction), and NOT (negation). To obtain a faster and better solution, we adopt the most popular DE for DMAS training. We have chosen five classification datasets from the UCI Machine Learning Repository for an experiment. We analyze and discuss the experimental results in terms of the correct rate, convergence rate, ROC curve, and the cross-validation and then compare the results with a dendritic neuron model trained by the backpropagation algorithm (BP-DNM) and a neural network trained by the backpropagation algorithm (BPNN). The analysis results show that the DE-DMAS shows better performance in all aspects.

show abstract

Approximate logic neuron model trained by states of matter search algorithm

Cited by 41 publications

References 35 publications

Training an Approximate Logic Dendritic Neuron Model Using Social Learning Particle Swarm Optimization Algorithm

Training an Approximate Logic Dendritic Neuron Model Using Social Learning Particle Swarm Optimization Algorithm

Mr2DNM: A Novel Mutual Information-Based Dendritic Neuron Model

A Dendritic Neuron Model with Adaptive Synapses Trained by Differential Evolution Algorithm

Contact Info

Product

Resources

About