{"title":"A reconfigurable continuous time recurrent neural network for evolvable hardware applications","authors":"J. Gallagher, S. Boddhu, S. Vigraham","doi":"10.1109/CEC.2005.1555002","DOIUrl":"https://doi.org/10.1109/CEC.2005.1555002","url":null,"abstract":"Evolvable hardware is reconfigurable hardware plus an evolutionary algorithm. Continuous time recurrent neural networks (CTRNNs) have been proposed for use as the reconfigurable hardware component. Until recently, however, nearly all CTRNN based EH was simulation based. This poster details a design for a reconfigurable analog CTRNN computer that supports both extrinsic and intrinsic CTRNN evolvable hardware.","PeriodicalId":448208,"journal":{"name":"2005 NASA/DoD Conference on Evolvable Hardware (EH'05)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121529225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Development brings scalability to hardware evolution","authors":"Timothy G. W. Gordon, P. Bentley","doi":"10.1109/EH.2005.18","DOIUrl":"https://doi.org/10.1109/EH.2005.18","url":null,"abstract":"The scalability problem is a major impediment to the use of hardware evolution for real-world circuit design problems. A potential solution is to model the map between genotype and phenotype on biological development. Although development has been shown to improve scalability for a few toy problems, it has not been demonstrated for any circuit design problems. This paper presents such a demonstration for two problems, the n-bit adder with carry and even n-bit parity problems, and shows that development imposes, and benefits from, fewer constraints on evolutionary innovation than other approaches to scalability.","PeriodicalId":448208,"journal":{"name":"2005 NASA/DoD Conference on Evolvable Hardware (EH'05)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127289743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Evolutionary discovering of the concept of the discrete state at the transistor level","authors":"L. Sekanina, R. Zebulum","doi":"10.1109/EH.2005.25","DOIUrl":"https://doi.org/10.1109/EH.2005.25","url":null,"abstract":"This paper shows that the evolutionary approach can discover the concept of the discrete state in a physical hardware which can be reconfigured at the transistor level. Evolution is able to recognize that the required output values are not pure combinations of the input values and to build internal structures to store the state. In particular, the reset-set circuit and the D-latch circuit are investigated using the field programmable transistor array FPTA-2.","PeriodicalId":448208,"journal":{"name":"2005 NASA/DoD Conference on Evolvable Hardware (EH'05)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116459940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Survivability of embryonic memories: analysis and design principles","authors":"L. Prodan, M. Udrescu, M. Vladutiu","doi":"10.1109/EH.2005.44","DOIUrl":"https://doi.org/10.1109/EH.2005.44","url":null,"abstract":"This paper proposes an original approach to the reliability analysis for Embryonics (Mange and Tomassini, 1998), by introducing the accuracy threshold measure, borrowed from fault-tolerant quantum computing theory, as one of the main parameters for our qualitative assessment. The validity of this technique is proven by comparison with the classical reliability results; furthermore, it brings new perspectives on designing reliable embryonic memory structures at both the molecular and the cellular levels. Appropriate design principles are provided on both information encoding (concatenated codes) and storage (fault tolerant memory structures).","PeriodicalId":448208,"journal":{"name":"2005 NASA/DoD Conference on Evolvable Hardware (EH'05)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115980508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A hardware implementation of the cell matrix self-configurable architecture: the Cell Matrix MOD 88/spl trade/","authors":"N. Macias, L. Durbeck","doi":"10.1109/EH.2005.2","DOIUrl":"https://doi.org/10.1109/EH.2005.2","url":null,"abstract":"A hardware version of the Cell Matrix self-configurable architecture is described. Its main features are summarized, and the advantages of the hardware system over software simulators are discussed. Further details of the MOD 88's operation and software are given. An overview of the relation of the Cell Matrix and the MOD 88 to the field of evolvable hardware is given. Research and educational ideas are presented. A freely available, shared, online MOD 88 system is discussed.","PeriodicalId":448208,"journal":{"name":"2005 NASA/DoD Conference on Evolvable Hardware (EH'05)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121827237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Evolution of asynchronous sequential circuits","authors":"A. P. Shanthi, L. Singaram, R. Parthasarathi","doi":"10.1109/EH.2005.23","DOIUrl":"https://doi.org/10.1109/EH.2005.23","url":null,"abstract":"Asynchronous systems are being viewed as an increasingly viable alternative to purely synchronous systems, due to their inherent benefits. At the same time, the complexities involved in such designs make manual designs challenging and suggest the use of evolutionary design procedures. Yet, surprisingly, there has not been an attempt so far to evolve asynchronous sequential circuits. This paper pioneers this attempt and proposes an evolutionary approach for the first time. The evolution is done at two levels using a developmental approach called the developmental Cartesian genetic programming (DCGP) technique. The first level evolution aims at evolving race-free stable circuits, satisfying the input/output combinations, with no hazards or minimal number of hazards. The second level evolution modifies/adds more components to the circuits, in order to make them hazard-free, both with respect to static as well as dynamic hazards. Experimental results for a modulo-six counter and an ISCAS'89 benchmark circuit, 'lion', are provided as a proof of concept.","PeriodicalId":448208,"journal":{"name":"2005 NASA/DoD Conference on Evolvable Hardware (EH'05)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127243606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Evolutionary design of analog circuits with a uniform-design based multi-objective adaptive genetic algorithm","authors":"Shuguang Zhao, L. Jiao, Jianxun Zhao, Yuping Wang","doi":"10.1109/EH.2005.48","DOIUrl":"https://doi.org/10.1109/EH.2005.48","url":null,"abstract":"A novel multi-objective genetic algorithm based approach for evolvable hardware (EHW) is proposed in this paper. It features intensive applications of the Uniform Design Technique (UDT) to fitness function composing and crossover operator construction for the sake of multiple uniform search directions, better quality of offspring and higher computation efficiency. With an efficient and universal representation scheme based on standard component values and PSpice Net-list, it supports generation and optimization of circuit structures and component values. Moreover, its search efficiency is enhanced by an adaptation technique of genetic parameters, which pays attention to both population diversity, loci' effects and development of evolution. Both theoretic analyses and experimental results demonstrated its capability in finding out a set of Pareto-optimal solutions or effective design results via a shorter execution, and showed its potential in fully automated design of circuits concerning multi-objective requirements and preferences.","PeriodicalId":448208,"journal":{"name":"2005 NASA/DoD Conference on Evolvable Hardware (EH'05)","volume":"223 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115488435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. Bickford, S. George, J. Manobianco, M. Adams, D. Manobianco
{"title":"Large scale deployment and operation of distributed sensor assets optimized for robust Mars exploration","authors":"J. Bickford, S. George, J. Manobianco, M. Adams, D. Manobianco","doi":"10.1109/EH.2005.33","DOIUrl":"https://doi.org/10.1109/EH.2005.33","url":null,"abstract":"The large scale dispersal of distributed sensor arrays across planetary surfaces has been proposed by several groups for the exploration of Mars. We survey a number of these concepts and discuss their intrinsic advantages as well as technical challenges relative to more traditional exploration modalities. Specifically, distributed sensors working in conjunction with traditional surface vehicles enable critical phenomena to be measured in previously inaccessible terrain over temporal and spatial scales not obtainable otherwise. We discuss how this strategy can be integrated into an overall science campaign and address several key issues in regards to returning the acquired data. Dispersion and data extraction studies performed for the global environmental micro sensors (GEMS) project will be presented in the context of Mars exploration and the search for life. The modeling results provide insight into optimum strategies for distributing probes and then extracting measured data either via an ad hoc network or direct exfiltration to an orbital asset.","PeriodicalId":448208,"journal":{"name":"2005 NASA/DoD Conference on Evolvable Hardware (EH'05)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115428860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Robust neural networks using motes","authors":"J. Hereford, Tüze Kuyucu","doi":"10.1109/EH.2005.42","DOIUrl":"https://doi.org/10.1109/EH.2005.42","url":null,"abstract":"The goal of this research is to derive circuits that can recover from component failure. Our approach is to replace a single monolithic computing element with a system of simple, redundant, interconnected processing nodes such as a neural net. Each node will be a hardware device called a mote that can sense data, do simple processing and wirelessly transmit and receive data from its neighbors. The neural net is trained using an evolutionary algorithm called particle swarm optimization (PSO). This paper discusses the PSO algorithm, simulated results using the algorithm, and its application to the mote-based neural net. We also describe and show results for a new algorithm called dispersive PSO, which is useful when a neural net needs to be retrained to a different function or when a neural net needs to be retrained due to a node failure.","PeriodicalId":448208,"journal":{"name":"2005 NASA/DoD Conference on Evolvable Hardware (EH'05)","volume":"22 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123726347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Evolution in materio: a real-time robot controller in liquid crystal","authors":"Simon Harding, J. Miller","doi":"10.1109/EH.2005.22","DOIUrl":"https://doi.org/10.1109/EH.2005.22","url":null,"abstract":"Although intrinsic evolution has been shown to be capable of exploiting the physical properties of materials to solve problems, most researchers have chosen to limit themselves to using standard electronic components. However, it has been previously argued that because such components are human designed and intentionally have predictable responses, they may not be the most suitable medium to use when trying to get a naturally inspired search technique to solve a problem. Indeed allowing computer controlled evolution (CCE) to manipulate novel physical media can allow much greater scope for the discovery of unconventional solutions. Last year the authors demonstrated, for the first time, that CCE could manipulate liquid crystal to perform signal processing tasks (i.e frequency discrimination). In this paper we show that CCE can use liquid crystal to solve the much harder problem of controlling a robot in real time to navigate in an environment to reach an obstructed destination point.","PeriodicalId":448208,"journal":{"name":"2005 NASA/DoD Conference on Evolvable Hardware (EH'05)","volume":"88 23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114167468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}