1
|
Zhu M, Yang Q, Dong J, Zhang G, Gou X, Rong H, Paul P, Neri F. An Adaptive Optimization Spiking Neural P System for Binary Problems. Int J Neural Syst 2020; 31:2050054. [PMID: 32938261 DOI: 10.1142/s0129065720500549] [Citation(s) in RCA: 47] [Impact Index Per Article: 11.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Optimization Spiking Neural P System (OSNPS) is the first membrane computing model to directly derive an approximate solution of combinatorial problems with a specific reference to the 0/1 knapsack problem. OSNPS is composed of a family of parallel Spiking Neural P Systems (SNPS) that generate candidate solutions of the binary combinatorial problem and a Guider algorithm that adjusts the spiking probabilities of the neurons of the P systems. Although OSNPS is a pioneering structure in membrane computing optimization, its performance is competitive with that of modern and sophisticated metaheuristics for the knapsack problem only in low dimensional cases. In order to overcome the limitations of OSNPS, this paper proposes a novel Dynamic Guider algorithm which employs an adaptive learning and a diversity-based adaptation to control its moving operators. The resulting novel membrane computing model for optimization is here named Adaptive Optimization Spiking Neural P System (AOSNPS). Numerical result shows that the proposed approach is effective to solve the 0/1 knapsack problems and outperforms multiple various algorithms proposed in the literature to solve the same class of problems even for a large number of items (high dimensionality). Furthermore, case studies show that a AOSNPS is effective in fault sections estimation of power systems in different types of fault cases: including a single fault, multiple faults and multiple faults with incomplete and uncertain information in the IEEE 39 bus system and IEEE 118 bus system.
Collapse
Affiliation(s)
- Ming Zhu
- School of Control Engineering, Chengdu University of Information Technology, Chengdu 610225, P. R. China
| | - Qiang Yang
- School of Control Engineering, Chengdu University of Information Technology, Chengdu 610225, P. R. China
| | - Jianping Dong
- College of Information Science and Technology, Chengdu University of Technology, Chengdu 610059, P. R. China
| | - Gexiang Zhang
- College of Information Science and Technology, Chengdu University of Technology, Chengdu 610059, P. R. China
| | - Xiantai Gou
- School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, P. R. China
| | - Haina Rong
- School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, P. R. China
| | - Prithwineel Paul
- School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, P. R. China
| | - Ferrante Neri
- COL Laboratory, School of Computer Science, University of Nottingham, Nottingham, UK
| |
Collapse
|
2
|
Zhang G, Rong H, Paul P, He Y, Neri F, Pérez-Jiménez MJ. A Complete Arithmetic Calculator Constructed from Spiking Neural P Systems and its Application to Information Fusion. Int J Neural Syst 2020; 31:2050055. [PMID: 32938262 DOI: 10.1142/s0129065720500550] [Citation(s) in RCA: 49] [Impact Index Per Article: 12.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Several variants of spiking neural P systems (SNPS) have been presented in the literature to perform arithmetic operations. However, each of these variants was designed only for one specific arithmetic operation. In this paper, a complete arithmetic calculator implemented by SNPS is proposed. An application of the proposed calculator to information fusion is also proposed. The information fusion is implemented by integrating the following three elements: (1) an addition and subtraction SNPS already reported in the literature; (2) a modified multiplication and division SNPS; (3) a novel storage SNPS, i.e. a method based on SNPS is introduced to calculate basic probability assignment of an event. This is the first attempt to apply arithmetic operation SNPS to fuse multiple information. The effectiveness of the presented general arithmetic SNPS calculator is verified by means of several examples.
Collapse
Affiliation(s)
- Gexiang Zhang
- Research Center for Artificial Intelligence, Chengdu University of Technology, Chengdu 610059, P. R. China
| | - Haina Rong
- School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, P. R. China
| | - Prithwineel Paul
- School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, P. R. China
| | - Yangyang He
- School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, P. R. China
| | - Ferrante Neri
- COL Laboratory, School of Computer Science, University of Nottingham, Nottingham, UK
| | - Mario J Pérez-Jiménez
- Department of Computer Science and Artificial Intelligence, University of Sevilla, Avda. Reina Mercedes s/n 41012, Spain
| |
Collapse
|
3
|
Wu T, Bîlbîe FD, Păun A, Pan L, Neri F. Simplified and Yet Turing Universal Spiking Neural P Systems with Communication on Request. Int J Neural Syst 2018; 28:1850013. [DOI: 10.1142/s0129065718500132] [Citation(s) in RCA: 82] [Impact Index Per Article: 13.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Spiking neural P systems are a class of third generation neural networks belonging to the framework of membrane computing. Spiking neural P systems with communication on request (SNQ P systems) are a type of spiking neural P system where the spikes are requested from neighboring neurons. SNQ P systems have previously been proved to be universal (computationally equivalent to Turing machines) when two types of spikes are considered. This paper studies a simplified version of SNQ P systems, i.e. SNQ P systems with one type of spike. It is proved that one type of spike is enough to guarantee the Turing universality of SNQ P systems. Theoretical results are shown in the cases of the SNQ P system used in both generating and accepting modes. Furthermore, the influence of the number of unbounded neurons (the number of spikes in a neuron is not bounded) on the computation power of SNQ P systems with one type of spike is investigated. It is found that SNQ P systems functioning as number generating devices with one type of spike and four unbounded neurons are Turing universal.
Collapse
Affiliation(s)
- Tingfang Wu
- Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China, School of Automation, Huazhong University of Science and Technology, Wuhan, Hubei 430074, P. R. China
| | - Florin-Daniel Bîlbîe
- Department of Computer Science, Faculty of Mathematics and Computer Science, University of Bucharest, Str. Academiei Nr. 14, Sector 1, C.P. 010014, Bucharest, Romania
| | - Andrei Păun
- Department of Computer Science, Faculty of Mathematics and Computer Science, University of Bucharest, Str. Academiei Nr. 14, Sector 1, C.P. 010014, Bucharest, Romania
- Department of Bioinformatics, National Institute of Research and Development for Biological Sciences, Splaiul Independenţei, Nr. 296, Sector 6, Bucharest, Romania
| | - Linqiang Pan
- Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China, School of Automation, Huazhong University of Science and Technology, Wuhan, Hubei 430074, P. R. China
- School of Electric and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou, Henan 450002, P. R. China
| | - Ferrante Neri
- Centre for Computational Intelligence, School of Computer Science and Informatics, De Montfort University, The Gateway, Leicester LE1 9BH, UK
| |
Collapse
|
4
|
Tchapet Njafa JP, Nana Engo S. Quantum associative memory with linear and non-linear algorithms for the diagnosis of some tropical diseases. Neural Netw 2018; 97:1-10. [DOI: 10.1016/j.neunet.2017.09.002] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2017] [Revised: 08/29/2017] [Accepted: 09/01/2017] [Indexed: 10/18/2022]
|
5
|
Montani F, Oliynyk A, Fadiga L. Superlinear Summation of Information in Premotor Neuron Pairs. Int J Neural Syst 2015; 27:1650009. [PMID: 26906455 DOI: 10.1142/s012906571650009x] [Citation(s) in RCA: 18] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Whether premotor/motor neurons encode information in terms of spiking frequency or by their relative time of firing, which may display synchronization, is still undetermined. To address this issue, we used an information theory approach to analyze neuronal responses recorded in the premotor (area F5) and primary motor (area F1) cortices of macaque monkeys under four different conditions of visual feedback during hand grasping. To evaluate the sensitivity of spike timing correlation between single neurons, we investigated the stimulus dependent synchronization in our population of pairs. We first investigated the degree of correlation of trial-to-trial fluctuations in response strength between neighboring neurons for each condition, and second estimated the stimulus dependent synchronization by means of an information theoretical approach. We compared the information conveyed by pairs of simultaneously recorded neurons with the sum of information provided by the respective individual cells. The information transmission across pairs of cells in the primary motor cortex seems largely independent, whereas information transmission across pairs of premotor neurons is summed superlinearly. The brain could take advantage of both the accuracy provided by the independency of F1 and the synergy allowed by the superlinear information population coding in F5, distinguishing thus the generalizing role of F5.
Collapse
Affiliation(s)
- Fernando Montani
- 1 Iflysib, Conicet & Universidad Nacional de La Plata, 59-789 La Plata, Argentina
| | - Andriy Oliynyk
- 2 Section of Human Physiology, Department of Biomedical Sciences and Advanced Therapies, Faculty of Medicine, University of Ferrara, Via Fossato di Mortara 17/19, 44121 Ferrara, Italy
| | - Luciano Fadiga
- 3 IIT@UNIFE Center for Translational Neurophysiology, Istituto Italiano di Tecnologia, Ferrara, Italy.,4 Section of Human Physiology, University of Ferrara, Italy
| |
Collapse
|
6
|
ZHANG GEXIANG, RONG HAINA, NERI FERRANTE, PÉREZ-JIMÉNEZ MARIOJ. AN OPTIMIZATION SPIKING NEURAL P SYSTEM FOR APPROXIMATELY SOLVING COMBINATORIAL OPTIMIZATION PROBLEMS. Int J Neural Syst 2014; 24:1440006. [DOI: 10.1142/s0129065714400061] [Citation(s) in RCA: 231] [Impact Index Per Article: 23.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Membrane systems (also called P systems) refer to the computing models abstracted from the structure and the functioning of the living cell as well as from the cooperation of cells in tissues, organs, and other populations of cells. Spiking neural P systems (SNPS) are a class of distributed and parallel computing models that incorporate the idea of spiking neurons into P systems. To attain the solution of optimization problems, P systems are used to properly organize evolutionary operators of heuristic approaches, which are named as membrane-inspired evolutionary algorithms (MIEAs). This paper proposes a novel way to design a P system for directly obtaining the approximate solutions of combinatorial optimization problems without the aid of evolutionary operators like in the case of MIEAs. To this aim, an extended spiking neural P system (ESNPS) has been proposed by introducing the probabilistic selection of evolution rules and multi-neurons output and a family of ESNPS, called optimization spiking neural P system (OSNPS), are further designed through introducing a guider to adaptively adjust rule probabilities to approximately solve combinatorial optimization problems. Extensive experiments on knapsack problems have been reported to experimentally prove the viability and effectiveness of the proposed neural system.
Collapse
Affiliation(s)
- GEXIANG ZHANG
- School of Electrical Engineering, Southwest Jiaotong University, Chengdu, 610031, China
| | - HAINA RONG
- School of Electrical Engineering, Southwest Jiaotong University, Chengdu, 610031, China
| | - FERRANTE NERI
- Centre for Computational Intelligence, De Montfort University, Leicester, UK
| | - MARIO J. PÉREZ-JIMÉNEZ
- Department of Computer Science and Artificial Intelligence, University of Sevilla, Avda. Reina Mercedes s/n, 41012, Spain
| |
Collapse
|
7
|
FRIEDRICH JOHANNES, URBANCZIK ROBERT, SENN WALTER. CODE-SPECIFIC LEARNING RULES IMPROVE ACTION SELECTION BY POPULATIONS OF SPIKING NEURONS. Int J Neural Syst 2014; 24:1450002. [DOI: 10.1142/s0129065714500026] [Citation(s) in RCA: 35] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Population coding is widely regarded as a key mechanism for achieving reliable behavioral decisions. We previously introduced reinforcement learning for population-based decision making by spiking neurons. Here we generalize population reinforcement learning to spike-based plasticity rules that take account of the postsynaptic neural code. We consider spike/no-spike, spike count and spike latency codes. The multi-valued and continuous-valued features in the postsynaptic code allow for a generalization of binary decision making to multi-valued decision making and continuous-valued action selection. We show that code-specific learning rules speed up learning both for the discrete classification and the continuous regression tasks. The suggested learning rules also speed up with increasing population size as opposed to standard reinforcement learning rules. Continuous action selection is further shown to explain realistic learning speeds in the Morris water maze. Finally, we introduce the concept of action perturbation as opposed to the classical weight- or node-perturbation as an exploration mechanism underlying reinforcement learning. Exploration in the action space greatly increases the speed of learning as compared to exploration in the neuron or weight space.
Collapse
Affiliation(s)
- JOHANNES FRIEDRICH
- Institute of Physiology, University of Bern, Bühlplatz 5, 3012 Bern, Switzerland
- Computational and Biological Learning Lab, Department of Engineering, University of Cambridge, Trumpington Street, Cambridge CB2 1PZ, UK
| | - ROBERT URBANCZIK
- Institute of Physiology, University of Bern, Bühlplatz 5, 3012 Bern, Switzerland
- Center for Cognition, Learning and Memory, University of Bern, Factory Street 8, CH-3012 Bern, Switzerland
| | - WALTER SENN
- Institute of Physiology, University of Bern, Bühlplatz 5, 3012 Bern, Switzerland
- Center for Cognition, Learning and Memory, University of Bern, Factory Street 8, CH-3012 Bern, Switzerland
| |
Collapse
|
8
|
Kasabov NK. NeuCube: A spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data. Neural Netw 2014; 52:62-76. [PMID: 24508754 DOI: 10.1016/j.neunet.2014.01.006] [Citation(s) in RCA: 132] [Impact Index Per Article: 13.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/11/2013] [Revised: 12/29/2013] [Accepted: 01/07/2014] [Indexed: 11/24/2022]
|
9
|
Carlson KD, Nageswaran JM, Dutt N, Krichmar JL. An efficient automated parameter tuning framework for spiking neural networks. Front Neurosci 2014; 8:10. [PMID: 24550771 PMCID: PMC3912986 DOI: 10.3389/fnins.2014.00010] [Citation(s) in RCA: 26] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2013] [Accepted: 01/17/2014] [Indexed: 11/13/2022] Open
Abstract
As the desire for biologically realistic spiking neural networks (SNNs) increases, tuning the enormous number of open parameters in these models becomes a difficult challenge. SNNs have been used to successfully model complex neural circuits that explore various neural phenomena such as neural plasticity, vision systems, auditory systems, neural oscillations, and many other important topics of neural function. Additionally, SNNs are particularly well-adapted to run on neuromorphic hardware that will support biological brain-scale architectures. Although the inclusion of realistic plasticity equations, neural dynamics, and recurrent topologies has increased the descriptive power of SNNs, it has also made the task of tuning these biologically realistic SNNs difficult. To meet this challenge, we present an automated parameter tuning framework capable of tuning SNNs quickly and efficiently using evolutionary algorithms (EA) and inexpensive, readily accessible graphics processing units (GPUs). A sample SNN with 4104 neurons was tuned to give V1 simple cell-like tuning curve responses and produce self-organizing receptive fields (SORFs) when presented with a random sequence of counterphase sinusoidal grating stimuli. A performance analysis comparing the GPU-accelerated implementation to a single-threaded central processing unit (CPU) implementation was carried out and showed a speedup of 65× of the GPU implementation over the CPU implementation, or 0.35 h per generation for GPU vs. 23.5 h per generation for CPU. Additionally, the parameter value solutions found in the tuned SNN were studied and found to be stable and repeatable. The automated parameter tuning framework presented here will be of use to both the computational neuroscience and neuromorphic engineering communities, making the process of constructing and tuning large-scale SNNs much quicker and easier.
Collapse
Affiliation(s)
- Kristofor D Carlson
- Department of Cognitive Sciences, University of California Irvine Irvine, CA, USA
| | | | - Nikil Dutt
- Department of Computer Science, University of California Irvine Irvine, CA, USA
| | - Jeffrey L Krichmar
- Department of Cognitive Sciences, University of California Irvine Irvine, CA, USA ; Department of Computer Science, University of California Irvine Irvine, CA, USA
| |
Collapse
|
10
|
Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognition. Neural Netw 2013; 41:188-201. [DOI: 10.1016/j.neunet.2012.11.014] [Citation(s) in RCA: 235] [Impact Index Per Article: 21.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2012] [Revised: 11/20/2012] [Accepted: 11/25/2012] [Indexed: 11/21/2022]
|
11
|
Abstract
The quantron is a hybrid neuron model related to perceptrons and spiking neurons. The activation of the quantron is determined by the maximum of a sum of input signals, which is difficult to use in classical learning algorithms. Thus, training the quantron to solve classification problems requires heuristic methods such as direct search. In this paper, we present an approximation of the quantron trainable by gradient search. We show this approximation improves the classification performance of direct search solutions. We also compare the quantron and the perceptron's performance in solving the IRIS classification problem.
Collapse
Affiliation(s)
- Richard Labib
- Department of Mathematics and Industrial Engineering, Polytechnique Montreal, 2900 boul. Édouard-Montpetit, Campus de l'Université de Montréal, 2500 Chemin de Polytechnique, Montreal, Quebec, H3T 1J4, Canada.
| | | |
Collapse
|
12
|
|
13
|
Ahmadlou M, Adeli H, Adeli A. Fuzzy Synchronization Likelihood-wavelet methodology for diagnosis of autism spectrum disorder. J Neurosci Methods 2012; 211:203-9. [PMID: 22968137 DOI: 10.1016/j.jneumeth.2012.08.020] [Citation(s) in RCA: 109] [Impact Index Per Article: 9.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/13/2012] [Revised: 07/29/2012] [Accepted: 08/21/2012] [Indexed: 11/18/2022]
Abstract
This paper presents a methodology for investigation of functional connectivity in patients with autism spectrum disorder (ASD) using Fuzzy Synchronization Likelihood (Fuzzy SL). Fuzzy SLs between and within brain regions are calculated in all EEG sub-bands produced by the wavelet decomposition as well as in the full-band EEG. Then, discriminative Fuzzy SLs between and within different regions and different EEG sub-bands or full-band EEG for distinguishing autistic children from healthy control children are determined based on Analysis of Variation (ANOVA). Finally, the selected features are used as input to an Enhanced Probabilistic Neural Network classifier to make an accurate diagnosis of ASD based on the detected differences in the regional functional connectivity of autistic and healthy EEGs. The methodology is validated using EEG data obtained from 9 autistic and 9 healthy children. The ANOVA test showed high ability of the regional Fuzzy SLs in low frequency bands, delta and theta, as well as alpha band for discriminating the two groups. A high classification accuracy of 95.5% was achieved for distinguishing autistic EEGs from healthy EEGs. It is concluded that the methodology presented in this paper can be used as an effective tool for diagnosis of the autism. Further, the regional Fuzzy SLs discovered in this research can be used as reliable markers in neurofeedback treatments to improve neuronal plasticity and connectivity in autistic patients.
Collapse
|
14
|
ROSSELLÓ JOSEPL, CANALS VINCENT, MORRO ANTONI, OLIVER ANTONI. HARDWARE IMPLEMENTATION OF STOCHASTIC SPIKING NEURAL NETWORKS. Int J Neural Syst 2012; 22:1250014. [DOI: 10.1142/s0129065712500141] [Citation(s) in RCA: 31] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Spiking Neural Networks, the last generation of Artificial Neural Networks, are characterized by its bio-inspired nature and by a higher computational capacity with respect to other neural models. In real biological neurons, stochastic processes represent an important mechanism of neural behavior and are responsible of its special arithmetic capabilities. In this work we present a simple hardware implementation of spiking neurons that considers this probabilistic nature. The advantage of the proposed implementation is that it is fully digital and therefore can be massively implemented in Field Programmable Gate Arrays. The high computational capabilities of the proposed model are demonstrated by the study of both feed-forward and recurrent networks that are able to implement high-speed signal filtering and to solve complex systems of linear equations.
Collapse
Affiliation(s)
- JOSEP L. ROSSELLÓ
- Physics Department, Universitat de les Illes Balears, Cra. Valldemossa km. 7.5, Palma de Mallorca, Balears, 07122, Spain
| | - VINCENT CANALS
- Physics Department, Universitat de les Illes Balears, Cra. Valldemossa km. 7.5, Palma de Mallorca, Balears, 07122, Spain
| | - ANTONI MORRO
- Physics Department, Universitat de les Illes Balears, Cra. Valldemossa km. 7.5, Palma de Mallorca, Balears, 07122, Spain
| | - ANTONI OLIVER
- Physics Department, Universitat de les Illes Balears, Cra. Valldemossa km. 7.5, Palma de Mallorca, Balears, 07122, Spain
| |
Collapse
|
15
|
WONG WK, WANG Z, ZHEN B, LEUNG SYS. RELATIONSHIP BETWEEN APPLICABILITY OF CURRENT-BASED SYNAPSES AND UNIFORMITY OF FIRING PATTERNS. Int J Neural Syst 2012; 22:1250017. [DOI: 10.1142/s0129065712500177] [Citation(s) in RCA: 17] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
The purpose of this paper is to identify situations in neural network modeling where current-based synapses are applicable. The applicability of current-based synapse model for studying post-transient behavior of neural networks is discussed in terms of average synaptic current strength induced by per spike during one firing cycle of a neuron (or briefly per spike synaptic current strength). It was found that current-based synapse models are applicable in both situations where both the interspike intervals of the neurons and the distribution of firing times of the neurons are uniform, and where the firing of all neurons is synchronized. If neither the interspike intervals nor the distribution of firing times of the neurons is uniform or the reversal potential is between the rest and threshold potentials, current-based synapse models may be oversimplified.
Collapse
Affiliation(s)
- W. K. WONG
- Institute of Textiles and Clothing, The Hong Kong Polytechnic University, Hunghom, Kowloon, Hong Kong, China
| | - Z. WANG
- College of Information Science and Technology, Donghua University, Shanghai, China
| | - B. ZHEN
- Institute of Textiles and Clothing, The Hong Kong Polytechnic University, Hunghom, Kowloon, Hong Kong, China
| | - SYS. LEUNG
- Institute of Textiles and Clothing, The Hong Kong Polytechnic University, Hunghom, Kowloon, Hong Kong, China
| |
Collapse
|
16
|
LUQUE NICETOR, GARRIDO JESÚSA, RALLI JARNO, LAREDO JUANLUJ, ROS EDUARDO. FROM SENSORS TO SPIKES: EVOLVING RECEPTIVE FIELDS TO ENHANCE SENSORIMOTOR INFORMATION IN A ROBOT-ARM. Int J Neural Syst 2012; 22:1250013. [DOI: 10.1142/s012906571250013x] [Citation(s) in RCA: 21] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
In biological systems, instead of actual encoders at different joints, proprioception signals are acquired through distributed receptive fields. In robotics, a single and accurate sensor output per link (encoder) is commonly used to track the position and the velocity. Interfacing bio-inspired control systems with spiking neural networks emulating the cerebellum with conventional robots is not a straight forward task. Therefore, it is necessary to adapt this one-dimensional measure (encoder output) into a multidimensional space (inputs for a spiking neural network) to connect, for instance, the spiking cerebellar architecture; i.e. a translation from an analog space into a distributed population coding in terms of spikes. This paper analyzes how evolved receptive fields (optimized towards information transmission) can efficiently generate a sensorimotor representation that facilitates its discrimination from other "sensorimotor states". This can be seen as an abstraction of the Cuneate Nucleus (CN) functionality in a robot-arm scenario. We model the CN as a spiking neuron population coding in time according to the response of mechanoreceptors during a multi-joint movement in a robot joint space. An encoding scheme that takes into account the relative spiking time of the signals propagating from peripheral nerve fibers to second-order somatosensory neurons is proposed. Due to the enormous number of possible encodings, we have applied an evolutionary algorithm to evolve the sensory receptive field representation from random to optimized encoding. Following the nature-inspired analogy, evolved configurations have shown to outperform simple hand-tuned configurations and other homogenized configurations based on the solution provided by the optimization engine (evolutionary algorithm). We have used artificial evolutionary engines as the optimization tool to circumvent nonlinearity responses in receptive fields.
Collapse
Affiliation(s)
- NICETO R. LUQUE
- Department of Computer Architecture and Technology, CITIC, University of Granada, Periodista Daniel Saucedo s/n, Granada, Spain
| | - JESÚS A. GARRIDO
- Department of Computer Architecture and Technology, CITIC, University of Granada, Periodista Daniel Saucedo s/n, Granada, Spain
| | - JARNO RALLI
- Department of Computer Architecture and Technology, CITIC, University of Granada, Periodista Daniel Saucedo s/n, Granada, Spain
| | - JUANLU J. LAREDO
- Department of Computer Architecture and Technology, CITIC, University of Granada, Periodista Daniel Saucedo s/n, Granada, Spain
| | - EDUARDO ROS
- Department of Computer Architecture and Technology, CITIC, University of Granada, Periodista Daniel Saucedo s/n, Granada, Spain
| |
Collapse
|
17
|
Yamanishi T, Liu JQ, Nishimura H. Modeling fluctuations in default-mode brain network using a spiking neural network. Int J Neural Syst 2012; 22:1250016. [PMID: 22830966 DOI: 10.1142/s0129065712500165] [Citation(s) in RCA: 22] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Recently, numerous attempts have been made to understand the dynamic behavior of complex brain systems using neural network models. The fluctuations in blood-oxygen-level-dependent (BOLD) brain signals at less than 0.1 Hz have been observed by functional magnetic resonance imaging (fMRI) for subjects in a resting state. This phenomenon is referred to as a "default-mode brain network." In this study, we model the default-mode brain network by functionally connecting neural communities composed of spiking neurons in a complex network. Through computational simulations of the model, including transmission delays and complex connectivity, the network dynamics of the neural system and its behavior are discussed. The results show that the power spectrum of the modeled fluctuations in the neuron firing patterns is consistent with the default-mode brain network's BOLD signals when transmission delays, a characteristic property of the brain, have finite values in a given range.
Collapse
Affiliation(s)
- Teruya Yamanishi
- Department of Management Information Science, Fukui University of Technology, Fukui, 910-8505, Japan.
| | | | | |
Collapse
|
18
|
AKHAND MAH, MURASE K. ENSEMBLES OF NEURAL NETWORKS BASED ON THE ALTERATION OF INPUT FEATURE VALUES. Int J Neural Syst 2012; 22:77-87. [DOI: 10.1142/s0129065712003079] [Citation(s) in RCA: 23] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
An ensemble performs well when the component classifiers are diverse yet accurate, so that the failure of one is compensated for by others. A number of methods have been investigated for constructing ensemble in which some of them train classifiers with the generated patterns. This study investigates a new technique of training pattern generation. The method alters input feature values of some patterns using the values of other patterns to generate different patterns for different classifiers. The effectiveness of neural network ensemble based on the proposed technique was evaluated using a suite of 25 benchmark classification problems, and was found to achieve performance better than or competitive with related conventional methods. Experimental investigation of different input values alteration techniques finds that alteration with pattern values in the same class is better for generalization, although other alteration techniques may offer more diversity.
Collapse
Affiliation(s)
- M. A. H. AKHAND
- Department of Computer Science and Engineering, Khulna University of Engineering & Technology, Khulna 9203, Bangladesh
| | - K. MURASE
- Graduate School of Engineering, University of Fukui, 3-9-1 Bunkyo, Fukui 910-8507, Japan
| |
Collapse
|
19
|
Abstract
This paper presents a novel model for performing classification and visualization of high-dimensional data by means of combining two enhancing techniques. The first is a semi-supervised learning, an extension of the supervised learning used to incorporate unlabeled information to the learning process. The second is an ensemble learning to replicate the analysis performed, followed by a fusion mechanism that yields as a combined result of previously performed analysis in order to improve the result of a single model. The proposed learning schema, termed S 2-Ensemble, is applied to several unsupervised learning algorithms within the family of topology maps, such as the Self-Organizing Maps and the Neural Gas. This study also includes a thorough research of the characteristics of these novel schemes, by means quality measures, which allow a complete analysis of the resultant classifiers from the viewpoint of various perspectives over the different ways that these classifiers are used. The study conducts empirical evaluations and comparisons on various real-world datasets from the UCI repository, which exhibit different characteristics, so to enable an extensive selection of situations where the presented new algorithms can be applied.
Collapse
Affiliation(s)
- BRUNO BARUQUE
- Civil Engineering Department, University of Burgos, Spain
| | - EMILIO CORCHADO
- Departamento de Informática y Automática, University of Salamanca, Spain
- VŠB-Technical, University of Ostrava, Czech Republic
| | - HUJUN YIN
- School of Electrical and Electronic Engineering, The University of Manchester, United Kingdom
| |
Collapse
|
20
|
NeuCube EvoSpike Architecture for Spatio-temporal Modelling and Pattern Recognition of Brain Signals. ARTIFICIAL NEURAL NETWORKS IN PATTERN RECOGNITION 2012. [DOI: 10.1007/978-3-642-33212-8_21] [Citation(s) in RCA: 32] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/25/2022]
|
21
|
Kasabov N. Evolving Spiking Neural Networks and Neurogenetic Systems for Spatio- and Spectro-Temporal Data Modelling and Pattern Recognition. ADVANCES IN COMPUTATIONAL INTELLIGENCE 2012. [DOI: 10.1007/978-3-642-30687-7_12] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/06/2023]
|
22
|
Kasabov N, Schliebs R, Kojima H. Probabilistic Computational Neurogenetic Modeling: From Cognitive Systems to Alzheimer's Disease. ACTA ACUST UNITED AC 2011. [DOI: 10.1109/tamd.2011.2159839] [Citation(s) in RCA: 29] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
|
23
|
MARCANO-CEDEÑO ALEXIS, MARIN-DE-LA-BARCENA A, JIMENEZ-TRILLO J, PIÑUELA JA, ANDINA D. ARTIFICIAL METAPLASTICITY NEURAL NETWORK APPLIED TO CREDIT SCORING. Int J Neural Syst 2011; 21:311-7. [DOI: 10.1142/s0129065711002857] [Citation(s) in RCA: 33] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
The assessment of the risk of default on credit is important for financial institutions. Different Artificial Neural Networks (ANN) have been suggested to tackle the credit scoring problem, however, the obtained error rates are often high. In the search for the best ANN algorithm for credit scoring, this paper contributes with the application of an ANN Training Algorithm inspired by the neurons' biological property of metaplasticity. This algorithm is especially efficient when few patterns of a class are available, or when information inherent to low probability events is crucial for a successful application, as weight updating is overemphasized in the less frequent activations than in the more frequent ones. Two well-known and readily available such as: Australia and German data sets has been used to test the algorithm. The results obtained by AMMLP shown have been superior to state-of-the-art classification algorithms in credit scoring.
Collapse
Affiliation(s)
- ALEXIS MARCANO-CEDEÑO
- Group for Automation in Signals and Communications, Technical University of Madrid, ETSI Telecomunciación, Ciudad Universitaria, Madrid 28040, Spain
| | - A. MARIN-DE-LA-BARCENA
- Group for Automation in Signals and Communications, Technical University of Madrid, ETSI Telecomunciación, Ciudad Universitaria, Madrid 28040, Spain
| | - J. JIMENEZ-TRILLO
- Group for Automation in Signals and Communications, Technical University of Madrid, ETSI Telecomunciación, Ciudad Universitaria, Madrid 28040, Spain
| | - J. A. PIÑUELA
- Group for Automation in Signals and Communications, Technical University of Madrid, ETSI Telecomunciación, Ciudad Universitaria, Madrid 28040, Spain
| | - D. ANDINA
- Group for Automation in Signals and Communications, Technical University of Madrid, ETSI Telecomunciación, Ciudad Universitaria, Madrid 28040, Spain
| |
Collapse
|
24
|
LUQUE NR, GARRIDO JA, CARRILLO RR, TOLU S, ROS E. ADAPTIVE CEREBELLAR SPIKING MODEL EMBEDDED IN THE CONTROL LOOP: CONTEXT SWITCHING AND ROBUSTNESS AGAINST NOISE. Int J Neural Syst 2011; 21:385-401. [DOI: 10.1142/s0129065711002900] [Citation(s) in RCA: 64] [Impact Index Per Article: 4.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
This work evaluates the capability of a spiking cerebellar model embedded in different loop architectures (recurrent, forward, and forward&recurrent) to control a robotic arm (three degrees of freedom) using a biologically-inspired approach. The implemented spiking network relies on synaptic plasticity (long-term potentiation and long-term depression) to adapt and cope with perturbations in the manipulation scenario: changes in dynamics and kinematics of the simulated robot. Furthermore, the effect of several degrees of noise in the cerebellar input pathway (mossy fibers) was assessed depending on the employed control architecture. The implemented cerebellar model managed to adapt in the three control architectures to different dynamics and kinematics providing corrective actions for more accurate movements. According to the obtained results, coupling both control architectures (forward&recurrent) provides benefits of the two of them and leads to a higher robustness against noise.
Collapse
Affiliation(s)
- N. R. LUQUE
- Department of Computer Architecture and Technology, CITIC, University of Granada, Periodista Daniel Saucedo s/n, Granada, Spain
| | - J. A. GARRIDO
- Department of Computer Architecture and Technology, CITIC, University of Granada, Periodista Daniel Saucedo s/n, Granada, Spain
| | - R. R. CARRILLO
- Department of Computer Architecture and Electronics, University of Almería, Ctra. Sacramento s/n, La Cañada de San Urbano, Almería, Spain
| | - S. TOLU
- Department of Computer Architecture and Technology, CITIC, University of Granada, Periodista Daniel Saucedo s/n, Granada, Spain
| | - E. ROS
- Department of Computer Architecture and Technology, CITIC, University of Granada, Periodista Daniel Saucedo s/n, Granada, Spain
| |
Collapse
|
25
|
HAN FANG, WIERCIGROCH MARIAN, FANG JIANAN, WANG ZHIJIE. EXCITEMENT AND SYNCHRONIZATION OF SMALL-WORLD NEURONAL NETWORKS WITH SHORT-TERM SYNAPTIC PLASTICITY. Int J Neural Syst 2011; 21:415-25. [DOI: 10.1142/s0129065711002924] [Citation(s) in RCA: 29] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Excitement and synchronization of electrically and chemically coupled Newman-Watts (NW) small-world neuronal networks with a short-term synaptic plasticity described by a modified Oja learning rule are investigated. For each type of neuronal network, the variation properties of synaptic weights are examined first. Then the effects of the learning rate, the coupling strength and the shortcut-adding probability on excitement and synchronization of the neuronal network are studied. It is shown that the synaptic learning suppresses the over-excitement, helps synchronization for the electrically coupled network but impairs synchronization for the chemically coupled one. Both the introduction of shortcuts and the increase of the coupling strength improve synchronization and they are helpful in increasing the excitement for the chemically coupled network, but have little effect on the excitement of the electrically coupled one.
Collapse
Affiliation(s)
- FANG HAN
- College of Information Science and Technology, Donghua University, Shanghai, 201620, P. R. China
| | - MARIAN WIERCIGROCH
- Centre for Applied Dynamics Research, University of Aberdeen, Aberdeen, AB24 3UE, U.K
| | - JIAN-AN FANG
- College of Information Science and Technology, Donghua University, Shanghai, 201620, P. R. China
| | - ZHIJIE WANG
- College of Information Science and Technology, Donghua University, Shanghai, 201620, P. R. China
| |
Collapse
|
26
|
VIDYBIDA ALEXANDER. TESTING OF INFORMATION CONDENSATION IN A MODEL REVERBERATING SPIKING NEURAL NETWORK. Int J Neural Syst 2011; 21:187-98. [DOI: 10.1142/s0129065711002742] [Citation(s) in RCA: 22] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Information about external world is delivered to the brain in the form of structured in time spike trains. During further processing in higher areas, information is subjected to a certain condensation process, which results in formation of abstract conceptual images of external world, apparently, represented as certain uniform spiking activity partially independent on the input spike trains details. Possible physical mechanism of condensation at the level of individual neuron was discussed recently. In a reverberating spiking neural network, due to this mechanism the dynamics should settle down to the same uniform/ periodic activity in response to a set of various inputs. Since the same periodic activity may correspond to different input spike trains, we interpret this as possible candidate for information condensation mechanism in a network. Our purpose is to test this possibility in a network model consisting of five fully connected neurons, particularly, the influence of geometric size of the network, on its ability to condense information. Dynamics of 20 spiking neural networks of different geometric sizes are modelled by means of computer simulation. Each network was propelled into reverberating dynamics by applying various initial input spike trains. We run the dynamics until it becomes periodic. The Shannon's formula is used to calculate the amount of information in any input spike train and in any periodic state found. As a result, we obtain explicit estimate of the degree of information condensation in the networks, and conclude that it depends strongly on the net's geometric size.
Collapse
Affiliation(s)
- ALEXANDER VIDYBIDA
- Department of Synergetics, Bogolyubov Institute for Theoretical Physics, Metrologichna Str., 14-B, 03680 Kyiv, Ukraine
| |
Collapse
|
27
|
Evolving Probabilistic Spiking Neural Networks for Spatio-temporal Pattern Recognition: A Preliminary Study on Moving Object Recognition. ACTA ACUST UNITED AC 2011. [DOI: 10.1007/978-3-642-24965-5_25] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register]
|
28
|
Nuntalid N, Dhoble K, Kasabov N. EEG Classification with BSA Spike Encoding Algorithm and Evolving Probabilistic Spiking Neural Network. NEURAL INFORMATION PROCESSING 2011. [DOI: 10.1007/978-3-642-24955-6_54] [Citation(s) in RCA: 27] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/02/2022]
|