The Winner-Take-All (WTA) is an essential neural network operation for locating the most active neuron. Such a procedure has been extensively used in larger application areas. The Winner-Take-All circuit selects the maximum of the inputs inhibiting all other nodes. The efficiency of the analog circuits may well be considerably higher than the digital circuits. Also, analog circuits’ design footprint and processing time can be significantly small. A current-based Winner-Take-All circuit for analog neural networks is presented in this research. A compare and pass (CAP) mechanism has been used, where each input pair is compared, and the winner is selected and passed to another level. The inputs are compared by a sense amplifier which generates high and low voltage signals at the output node. The voltage signal of the sense amplifier is used to select the winner and passed to another level using logic gates. Also, each winner follows a sequence of digital bits to be selected. The findings of the SPICE simulation are also presented. The simulation results on the MNIST, Fashion-MNIST, and CIFAR10 datasets for the memristive deep neural network model show the significantly accurate result of the winner class with an average difference of input and selected winner output current of 0.00795uA, 0.01076uA and 0.02364uA respectively. The experimental result with transient noise analysis is also presented.

Artificial neural networks are widely used for parallel processing of data analysis and visual information. The most prominent example of artificial neural networks is a cellular neural network (CNN), composed from two-dimensional arrays of simple first-order dynamical systems (“cells”) that are interconnected by wires. The information, to be processed by a CNN, represents the initial state of the network, and the parallel information processing is performed by converging to one of the stable spatial equilibrium states of the multi-stable CNN. This thesis studies a specific type of CNNs designed to perform the winner-take-all function of finding the largest among the n numbers, using the network dynamics. In a wider context, this amounts to automatically detecting a target spot in the given visual picture. The research, reported in this thesis, demonstrates that the addition of fast on-off switching (blinking) connections significantly improves the functionality of winner-take-all CNNs. Numerical calculations are performed to reveal the dependence of the probability, that the CNN correctly classifies the largest number, on the switching frequency.

Recently, we observed many networked market are served almost by a single platform, and can called that situation be winner-take-all. We could observed that the top website occupy huge market, and still be the top for long time. Conversely, the other website only shares the tiny market. This paper chooses the biggest Taiwan portal Yahoo!Kimo to be the research case. In addition, the case object is its e-commerce department, which is the Yahoo! only e-commerce department worldwide. Through this case, we could find out the truth of winner-take-all. In this research, we use in-depth interview and combine with secondary data. According to past researches and the situation of Yahoo!Kimo, we address the research question as follow: (1) How does Yahoo!Kimo develop their e-store platforms to maintain their e-commerce leading position in Taiwan. (2) Is there a winner-take-all phenomenon on Yahoo!Kimo? After generalize the data, we found that although Yahoo! first time enters Taiwan not successful. Their strategy is merge different kinds website, such as the leading portal Kimo, the most visiting blog Wretch, and Monday.Tech. They got their human resource and technology sooner, then become the top one portal in Taiwan provides variety services for users. For foreign website and companies enter a new market will be a good role model. Moreover, we prove Yahoo!Kimo is role model of winner-take-all.

Ce mémoire est le résultat d'une recherche purement exploratoire concernant la définition d'une application de réseaux de neurones à base de transistors monoélectroniques (Single-Electron Transistor, SET). Il dresse un portait de l'état de l'art actuel, et met de l'avant la possibilité d'associer les SET avec la technologie actuelle (Field Electron Transistor, FET). La raison de cette association est que les SET peuvent être perçus comme un moyen de changement de paradigme, c'est-à-dire remplacer une fonction CMOS occupant une grande place par un dispositif alternatif présentant de meilleures performances ou équivalentes. Par l'intermédiaire de leurs caractéristiques électriques peu ordinaires au synonyme de"l'effet de blocage de Coulomb", les SET ont le potentiel d'être exploités intelligemment afin de tirer profit sur la consommation énergétique essentiellement. Cette problématique est présentée comme une des propositions alternatives"Beyond CMOS" aux termes de la diminution géométrique des transistors FET à la lumière de l'ITRS. Cette recherche propose d'exposer des circuits électroniques de technologie MOS complétés à l'aide de SET (circuits hybrides) et de montrer que l'on est capable de les remplacer ou les compléter (partiellement) dans des architectures à réseau de neurones. Pour cela, des simulations sous logiciel Cadence Environnement permettront de valider le comportement des circuits sur plusieurs critères tels que la vitesse de réponse et la consommation énergétique, par exemple. En résultat, seront proposées deux architectures à réseaux de neurones de fonctions différentes : une architecture Winner-Take-All et un générateur de spikes en tension. La première étant inspirée d'une publication provenant de GUIMARAES et al., veut démontrer qu'à partir d'une architecture SET existante, il est envisageable de se l'approprier et de l'appliquer aux paramètres des SET du CRN[indice supérieur 2] augmentant donc nos chances de pouvoir les concevoir dans notre groupe de recherche. Le second axe est la simulation d'un circuit capable de générer des signaux à spikes sans perte d'information, ce qui requerrait un nombre considérable de transistors FET sans l'utilisation de SET, mettant donc en valeur la réduction de composants.

Made available in DSpace on 2014-12-17T14:25:22Z (GMT). No. of bitstreams: 1 MarcoVMN_TESE.pdf: 3982733 bytes, checksum: 381ae79721c75a30e3373fe4487512c7 (MD5) Previous issue date: 2014-02-05 / In this paper artificial neural network (ANN) based on supervised and unsupervised algorithms were investigated for use in the study of rheological parameters of solid pharmaceutical excipients, in order to develop computational tools for manufacturing solid dosage forms. Among four supervised neural networks investigated, the best learning performance was achieved by a feedfoward multilayer perceptron whose architectures was composed by eight neurons in the input layer, sixteen neurons in the hidden layer and one neuron in the output layer. Learning and predictive performance relative to repose angle was poor while to Carr index and Hausner ratio (CI and HR, respectively) showed very good fitting capacity and learning, therefore HR and CI were considered suitable descriptors for the next stage of development of supervised ANNs. Clustering capacity was evaluated for five unsupervised strategies. Network based on purely unsupervised competitive strategies, classic "Winner-Take-All", "Frequency-Sensitive Competitive Learning" and "Rival-Penalize Competitive Learning" (WTA, FSCL and RPCL, respectively) were able to perform clustering from database, however this classification was very poor, showing severe classification errors by grouping data with conflicting properties into the same cluster or even the same neuron. On the other hand it could not be established what was the criteria adopted by the neural network for those clustering. Self-Organizing Maps (SOM) and Neural Gas (NG) networks showed better clustering capacity. Both have recognized the two major groupings of data corresponding to lactose (LAC) and cellulose (CEL). However, SOM showed some errors in classify data from minority excipients, magnesium stearate (EMG) , talc (TLC) and attapulgite (ATP). NG network in turn performed a very consistent classification of data and solve the misclassification of SOM, being the most appropriate network for classifying data of the study. The use of NG network in pharmaceutical technology was still unpublished. NG therefore has great potential for use in the development of software for use in automated classification systems of pharmaceutical powders and as a new tool for mining and clustering data in drug development / Neste trabalho foram estudadas redes neurais artificiais (RNAs) baseadas em algoritmos supervisionados e n?o supervisionados para emprego no estudo de par?metros reol?gicos de excipientes farmac?uticos s?lidos, visando desenvolver ferramentas computacionais para o desenvolvimento de formas farmac?uticas s?lidas. Foram estudadas quatro redes neurais artificiais supervisionadas e cinco n?o supervisionadas. Todas as RNAs supervisionadas foram baseadas em arquitetura de rede perceptron multicamada alimentada ? frente (feedfoward MLP). Das cinco RNAs n?o supervisionadas, tr?s foram baseadas em estrat?gias puramente competitivas, "Winner-Take- All" cl?ssica, "Frequency-Sensitive Competitive Learning" e "Rival-Penalize Competitive Learning" (WTA, FSCL e RPCL, respectivamente). As outras duas redes n?o supervisionadas, Self- Organizing Map e Neural Gas (SOM e NG) foram baseadas estrat?gias competitivo-cooperativas. O emprego da rede NG em tecnologia farmac?utica ? ainda in?dito e pretende-se avaliar seu potencial de emprego como nova ferramenta de minera??o e classifica??o de dados no desenvolvimento de medicamentos. Entre os prot?tipos de RNAs supervisionadas o melhor desempenho foi conseguido com uma rede de arquitetura composta por 8 neur?nios de entrada, 16 neur?nios escondidos e 1 neur?nio de sa?da. O aprendizado de rede e a capacidade preditiva em rela??o ao ?ngulo de repouso (α) foi deficiente, e muito boa para o ?ndice de Carr e fator de Hausner (IC, FH). Por esse motivo IC e FH foram considerados bons descritores para uma pr?xima etapa de desenvolvimento das RNAs supervisionadas. As redes, WTA, RPCL e FSCL, foram capazes de estabelecer agrupamentos dentro da massa de dados, por?m apresentaram erros grosseiros de classifica??o caracterizados pelo agrupamento de dados com propriedades conflitantes, e tamb?m n?o foi poss?vel estabelecer qual o crit?rio de classifica??o adotado. Tais resultados demonstraram a inviabilidade pr?tica dessas redes para os sistemas estudados sob nossas condi??es experimentais. As redes SOM e NG mostraram uma capacidade de classifica??o muito superior ?s RNAs puramente competitivas. Ambas as redes reconheceram os dois agrupamentos principais de dados correspondentes ? lactose (LAC) e celulose (CEL). Entretanto a rede som demonstrou defici?ncia na classifica??o de dados relativos aos excipientes minorit?rios, estearato de magn?sio (EMG), talco (TLC) e atapulgita (ATP). A rede NG, por sua vez, estabeleceu uma classifica??o muito consistente dos dados e resolveu o erro de classifica??o apresentados pela rede SOM, mostrando-se a rede mais adequada para a classifica??o dos dado do presente estudo. A rede Neural Gas, portanto, mostrou- se promissora para o desenvolvimento de softwares para uso na classifica??o automatizada de sistemas pulverulentos farmac?uticos