We introduce a novel neural network with a trigonometric interconnection called the T-Model neural network in this paper. A VLSI implementation of the T-Model neural network based on CMOS current-mode circuits is also presented. The circuit is completely compatible with standard VLSI technology. A set of neuron-type elements of CMOS current-mode circuits is described and a very large scale neural network is also synthesized. The feasibility and the operation principle of the synthesis of the T-Model neural network using CMOS current-mode circuits are demonstrated and confirmed by experimental results of fabricated CMOS VLSI neural chips.

Based on the clonal selection principle proposed by Burnet, in the immune response process there is no crossover of genetic material between members of the repertoire, i.e., there is no knowledge communication during different elite pools in the previous clonal selection models. As a result, the search performance of these models is ineffective. To solve this problem, inspired by the concept of the idiotypic network theory, an expanded lateral interactive clonal selection algorithm (LICS) is put forward. In LICS, an antibody is matured not only through the somatic hypermutation and the receptor editing from the B cell, but also through the stimuli from other antibodies. The stimuli is realized by memorizing some common gene segment on the idiotypes, based on which a lateral interactive receptor editing operator is also introduced. Then, LICS is applied to several benchmark instances of the traveling salesman problem. Simulation results show the efficiency and robustness of LICS when compared to other traditional algorithms.

In this paper, a threshold voltage (VT) cancellation circuit for neuron-MOS (νMOS) analog circuits is described. By connecting the output terminal of this circuit with one of the input terminals of the νMOS transistor, cancellation ofVT is realized. The circuit has advantages of ground-referenced output and is insensitive to the fluctuation of bias and supply voltages. Second-order effects, such as the channel length modulation effect, the mobility reduction effect and device mismatch of the proposed circuit are analyzed in detail. Low-power and high-swing νMOS cascode current mirror is presented as an application. Performance of the proposed circuits is confirmed by HSPICE simulation with MOSIS 2. 0 µ p-well double-poly and double-metal CMOS device parameters.

A near-optimum parallel algorithm for bipartite subgraph problem using gradient ascent learning algorithm of the Hopfield neural networks is presented. This parallel algorithm, uses the Hopfield neural network updating to get a near-maximum bipartite subgraph and then performs gradient ascent learning on the Hopfield network to help the network escape from the state of the near-maximum bipartite subgraph until the state of the maximum bipartite subgraph or better one is obtained. A large number of instances have been simulated to verify the proposed algorithm, with the simulation result showing that our algorithm finds the solution quality is superior to that of best existing parallel algorithm. We also test the proposed algorithm on maximum cut problem. The simulation results also show the effectiveness of this algorithm.

An improved algorithm of Guided Local Search called objective function adjustment algorithm is proposed for combinatorial optimization problems. The performance of Guided Local Search is improved by objective function adjustment algorithm using multipliers which can be adjusted during the search process. Moreover, the idea of Tabu Search is introduced into the objective function adjustment algorithm to further improve the performance. The simulation results based on some TSPLIB benchmark problems showed that the objective function adjustment algorithm could find better solutions than Local Search, Guided Local Search and Tabu Search.

In this paper, we propose a learning fuzzy network (LFN) which can be used to implement most of fuzzy logic functions and is much available for hardware implementations. A learning algorithm largely borrowed from back propagation algorithm is introduced and used to train the LFN systems for several typical fuzzy logic problems. We also demonstrate the availability of the LFN hardware implementations by realizing them with CMOS current-mode circuits and the capability of the LFN systems by testing them on a benchmark problem in intelligent control-the inverted pendulum system. Simulations show that a learning fuzzy network can be realized with the proposed LFN system, learning algorithm, and hardware implementations.

Both the clonal selection algorithm (CSA) and the ant colony optimization (ACO) are inspired by natural phenomena and are effective tools for solving complex problems. CSA can exploit and explore the solution space parallely and effectively. However, it can not use enough environment feedback information and thus has to do a large redundancy repeat during search. On the other hand, ACO is based on the concept of indirect cooperative foraging process via secreting pheromones. Its positive feedback ability is nice but its convergence speed is slow because of the little initial pheromones. In this paper, we propose a pheromone-linker to combine these two algorithms. The proposed hybrid clonal selection and ant colony optimization (CSA-ACO) reasonably utilizes the superiorities of both algorithms and also overcomes their inherent disadvantages. Simulation results based on the traveling salesman problems have demonstrated the merit of the proposed algorithm over some traditional techniques.

In this paper, a virtual-short circuit which consists of only two MOS transistors operated in the weak-inversion region is proposed. It has the advantages of almost zero power consumption, low voltage operation, small chip area, and no needlessness of bias voltages or currents. The second order effects, such as the device mismatch, the Early effect, and the temperature dependency of the circuit are analyzed in detail. Next, current-controlled and voltage-controlled current sources using the proposed virtual-short circuit are presented as applications. The performance of the proposed circuits is estimated using SPICE simulation with MOSIS 1. 2 µm CMOS device parameters. The results are reported on this paper.

In this paper, we propose a stochastic dynamic local search (SDLS) method for Multiple-Valued Logic (MVL) learning by introducing stochastic dynamics into the traditional local search method. The proposed learning network maintains some trends of quick descent to either global minimum or a local minimum, and at the same time has some chance of escaping from local minima by permitting temporary error increases during learning. Thus the network may eventually reach the global minimum state or its best approximation with very high probability. Simulation results show that the proposed algorithm has the superior abilities to find the global minimum for the MVL network learning within reasonable number of iterations.

A model for a large network with an unidirectional linear respone (ULR) is proposed in this letter. This deterministic system has powerful computing properties in very close correspondence with earlier stochastic model based on McCulloch-Pitts neurons and graded neuron model based on sigmoid input-output relation. The exclusive OR problems and other digital computation properties of the earlier models also are present in the ULR model. Furthermore, many analog and continuous signal processing can also be performed using the simple ULR neural network. Several examples of the ULR neural networks for analog and continuous signal processing are presented and show extemely promising results in terms of performance, density and potential for analog and continuous signal processing. An algorithm for the ULR neural network is also developed and used to train the ULR network for many digital and analog as well as continuous problems successfully.

This paper presents an inertial estimator learning automata scheme by which both the short-term and long-term perspectives of the environment can be incorporated in the stochastic estimator – the long term information crystallized in terms of the running reward-probability estimates, and the short term information used by considering whether the most recent response was a reward or a penalty. Thus, when the short-term perspective is considered, the stochastic estimator becomes pertinent in the context of the estimator algorithms. The proposed automata employ an inertial weight estimator as the short-term perspective to achieve a rapid and accurate convergence when operating in stationary random environments. According to the proposed inertial estimator scheme, the estimates of the reward probabilities of actions are affected by the last response from environment. In this way, actions that have gotten the positive response from environment in the short time, have the opportunity to be estimated as “optimal”, to increase their choice probability and consequently, to be selected. The estimates become more reliable and consequently, the automaton rapidly and accurately converges to the optimal action. The asymptotic behavior of the proposed scheme is analyzed and it is proved to be ε-optimal in every stationary random environment. Extensive simulation results indicate that the proposed algorithm converges faster than the traditional stochastic-estimator-based S ERI scheme, and the deterministic-estimator-based DGPA and DPRI schemes when operating in stationary random environments.

A novel comparator-based switched-capacitor voltage-to-frequency converter is presented. By using the op-amp as the comparator, it can be operated over wide frequency range. Conversion sensitivity is also insensitive to capacitance ratio and parasitic capacitances between each node and ground.

A direct gradient descent learning algorithm of energy function in Hopfield neural networks is proposed. The gradient descent learning is not performed on usual error functions, but the Hopfield energy functions directly. We demonstrate the algorithm by testing it on an analog-to-digital conversion and an associative memory problems.

This paper describes a new learning method for Multiple-Value Logic (MVL) networks using the local search method. It is a "non-back-propagation" learning method which constructs a layered MVL network based on canonical realization of MVL functions, defines an error measure between the actual output value and teacher's value and updates a randomly selected parameter of the MVL network if and only if the updating results in a decrease of the error measure. The learning capability of the MVL network is confirmed by simulations on a large number of 2-variable 4-valued problems and 2-variable 16-valued problems. The simulation results show that the method performs satisfactorily and exhibits good properties for those relatively small problems.

It is generally believed that one major function of the immune system is helping to protect multicellular organisms from foreign pathogens, especially replicating pathogens such as viruses, bacteria and parasites. The relevant events in the immune system are not only the molecules, but also their interactions. The immune cells can respond either positively or negatively to the recognition signal. A positive response would result in cell proliferation, activation and antibody secretion, while a negative response would lead to tolerance and suppression. Depending upon these immune mechanisms, an immune network model (here, we call it the binary immune network) based on the biological immune response network was proposed in our previous work. However, there are some problems like that input and memory were all binary and it did not consider the antigen diversity of immune system. To improve these problems, in this paper we propose a fuzzy immune network model by considering the antigen diversity of immune system that is the most important property to be exhibited in the immune system. As an application, the proposed fuzzy immune network is applied to pattern recognition problem. Computer simulations illustrate that the proposed fuzzy immune network model not only can improve the problems existing in the binary immune network but also is capable of clustering arbitrary sequences of large-scale analog input patterns into stable recognition categories.

This paper describes an MOS charge-mode version of a T-Model neural-based PCM encoder. The neural-based PCM encoding networks are designed, simulated and implemented using MOS charge-mode circuits. Simulation results are given for both the T-Model and the Hopfield model CMOS charge-mode PCM encoders, and demonstrate the T-Model neural-based one performs the PCM encoding perfectly, while the Hopfield one fails to.

This paper presents an adaptive magnification transformation based particle swarm optimizer (AMT-PSO) that provides an adaptive search strategy for each particle along the search process. Magnification transformation is a simple but very powerful mechanism, which is inspired by using a convex lens to see things much clearer. The essence of this transformation is to set a magnifier around an area we are interested in, so that we could inspect the area of interest more carefully and precisely. An evolutionary factor, which utilizes the information of population distribution in particle swarm, is used as an index to adaptively tune the magnification scale factor for each particle in each dimension. Furthermore, a perturbation-based elitist learning strategy is utilized to help the swarm's best particle to escape the local optimum and explore the potential better space. The AMT-PSO is evaluated on 15 unimodal and multimodal benchmark functions. The effects of the adaptive magnification transformation mechanism and the elitist learning strategy in AMT-PSO are studied. Results show that the adaptive magnification transformation mechanism provides the main contribution to the proposed AMT-PSO in terms of convergence speed and solution accuracy on four categories of benchmark test functions.

This paper presents a child verb learning model mainly based on syntactic bootstrapping. The model automatically learns 4-5-year-old children's linguistic knowledge of verbs, including subcategorization frames and thematic roles, using a text in dialogue format. Subcategorization frame acquisition of verbs is guided by the assumption of the existence of nine verb prototypes. These verb prototypes are extracted based on syntactic bootstrapping and some psycholinguistic studies. Thematic roles are assigned by syntactic bootstrapping and other psycholinguistic hypotheses. The experiments are performed on the data from the CHILDES database. The results show that the learning model successfully acquires linguistic knowledge of verbs and also suggest that psycholinguistic studies of child verb learning may provide important hints for linguistic knowledge acquisition in natural language processing (NLP).

The clonal selection algorithm (CS), inspired by the basic features of adaptive immune response to antigenic stimulus, can exploit and explore the solution space parallelly and effectively. However, antibody initialization and premature convergence are two problems of CS. To overcome these two problems, we propose a chaotic distance-based clonal selection algorithm (CDCS). In this novel algorithm, we introduce a chaotic initialization mechanism and a distance-based somatic hypermutation to improve the performance of CS. The proposed algorithm is also verified for numerous benchmark traveling salesman problems. Experimental results show that the improved algorithm proposed in this paper provides better performance when compared to other metaheuristics.

A novel buffer-based switched-capacitor (SC) integrator integrable by a method of reducing capacitance ratio is presented. By this method, high Q sc filter can be made by realizable capacitance ratio on CMOS process. The proposed integrator can also be operated over wide frequency range because it uses a unity gain buffer (UGB).