Method for improving classification performance of neural network based on fuzzy input and network inversion

In order to effectively improve the classification performance of neural network, first architecture of fuzzy neural network with fuzzy input was proposed. Next a cost function of fuzzy outputs and non-fuzzy targets was defined. Then a learning algorithm from the cost function for adjusting weights was derived. And then the fuzzy neural network was inversed and fuzzified inversion algorithm was proposed. Finally, computer simulations on real-world pattern classification problems examine the effectives of the proposed approach. The experiment results show that the proposed approach has the merits of high learning efficiency, high classification accuracy and high generalization capability.

The design algorithm of an associative memory neural network

A design algorithm of an associative memory neural network is proposed. The benefit of this design algorithm is to make the designed associative memory model can implement the hoped situation. On the one hand, the designed model has realized the nonlinear association of infinite value pattern from n dimension space to m dimension space. The result has improved the ones of some old associative memory neural network. On the other hand, the memory samples are in the centers of the fault-tolerant. In average significance the radius of the memory sample fault-tolerant field is maximum.

The image coding scheme based on neural network and SVM

This paper applies data coding thought, which based on the virtual information source modeling put forward by the author, to propose the image coding (compression) scheme based on neural network and SVM. This scheme is composed by "the image coding (compression) scheme based oil SVM" embedded "the lossless data compression scheme based oil neural network". The experiments show that the scheme has high compression ratio under the slightly damages condition, partly solve the contradiction which 'high fidelity' and 'high compression ratio' cannot unify in image coding system.

Lossless data compression scheme based on neural network and SVM

First, the compression-awaited data are regarded Lis character strings which are produced by virtual information source mapping M. then the model of the virtual information source M is established by neural network and SVM. Last we construct a lossless data compression (coding) scheme based oil neural network and SVM with the model, an integer function and a SVM discriminant. The scheme differs from the old entropy coding (compressions) inwardly, and it can compress some data compressed by the old entropy coding.

SOC dynamic power management using artificial neural network

Dynamic Power Management (DPM) is a technique to reduce power consumption of electronic system by selectively shutting down idle components. In this article we try to introduce back propagation network and radial basis network into the research of the system-level power management policies. We proposed two PM policies-Back propagation Power Management (BPPM) and Radial Basis Function Power Management (RBFPM) which are based on Artificial Neural Networks (ANN). Our experiments show that the two power management policies greatly lowered the system-level power consumption and have higher performance than traditional Power Management(PM) techniques-BPPM is 1.09-competitive and RBFPM is 1.08-competitive vs. 1.79, 1.45, 1.18-competitive separately for traditional timeout PM, adaptive predictive PM and stochastic PM.

A novel face recognition method based on hypersausage neural networks

In this paper, we firstly give the nature of 'hypersausages', study its structure and training of the network, then discuss the nature of it by way of experimenting with ORL face database, and finally, verify its unsurpassable advantages compared with other means.

A micromachined SiO2/silicon probe for neural signal recordings

The development of an implantable five channel microelectrode array is presented for neural signal recordings. The detailed fabrication process is outlined with four masked used. The SEM images show that the probe shank is 1.2mm long, 100 mu m wide and 30 mu m thick with the recording sites spaced 200 mu m apart for good signal isolation. The plot of the single recording site impedance versus frequency is shown by test in vitro and the ompedence declines with the increasing frequency. Experiment in vivo using this probe is under way.

Modeling and optimization of semiconductor manufacturing process with neural networks

A neural network-based process model is proposed to optimize the semiconductor manufacturing process. Being different from some works in several research groups which developed neural network-based models to predict process quality with a set of process variables of only single manufacturing step, we applied this model to wafer fabrication parameters control and wafer lot yield optimization. The original data are collected from a wafer fabrication line, including technological parameters and wafer test results. The wafer lot yield is taken as the optimization target. Learning from historical technological records and wafer test results, the model can predict the wafer yield. To eliminate the "bad" or noisy samples from the sample set, an experimental method was used to determine the number of hidden units so that both good learning ability and prediction capability can be obtained.

Structure approximate based on double weighted neural network

Double weighted neural network; is a kind of new general used neural network, which, compared with BP and RBF network, may approximate the training samples with a move complicated geometric figure and possesses a even greater approximation. capability. we study structure approximate based on double weighted neural network and prove its rationality.

Dynamic power management approaches based on neural network

Dynamic Power Management (DPM) is a technique to reduce power consumption of electronic system. by selectively shutting down idle components. In this article we try to introduce back propagation network and radial basis network into the research of the system-level policies. We proposed two PAY policies-Back propagation Power Management (BPPM) and Radial Basis Function Power management (RBFPM) which are based on Artificial Neural Networks (ANN). Our experiments show that the two power management policies greatly lowered the system-level power consumption and have higher performance than traditional Power Management(PM) techniques-BPPM is 1.09-competitive and RBFPM is 1.08-competitive vs. 1.79,145,1.18-competitive separately for traditional timeout PM, adaptive predictive PM and stochastic PM.

Cancer classification based on direction-basis-function neural networks

Automatic molecular classification of cancer based on DNA microarray has many advantages over conventional classification based on morphological appearance of the tumor. Using artificial neural networks is a general approach for automatic classification. In this paper, Direction-Basis-Function neuron and Priority-Ordered algorithm are applied to neural networks. And the leukemia gene expression dataset is used as an example to testify the classifier. The result of our method is compared to that of SVM. It shows that our method makes a better performance than SVM.

Low Power Integrated Circuits for Wireless Neural Recording Applications

A group of prototype integrated circuits are presented for a wireless neural recording micro-system. An inductive link was built for transcutaneous wireless power transfer and data transmission. Power and data were transmitted by a pair of coils on a same carrier frequency. The integrated receiver circuitry was composed of a full-wave bridge rectifier, a voltage regulator, a date recovery circuit, a clock recovery circuit and a power detector. The amplifiers were designed with a limited bandwidth for neural signals acquisition. An integrated FM transmitter was used to transmit the extracted neural signals to external equipments. 16.5 mW power and 50 bps - 2.5 Kbps command data can be received over 1 MHz carrier within 10 mm. The total gain of 60 dB was obtained by the preamplifier and a main amplifier at 0.95Hz - 13.41 KHz with 0.215 mW power dissipation. The power consumption of the 100 MHz ASK transmitter is 0.374 mW. All the integrated circuits operated under a 3.3 V power supply except the voltage regulator.

Multi channel micro neural probe fabricated with SOI

Extracellular neural recording requires neural probes having more recording sites as well as limited volumes. With its mechanical characteristic and abundant process method, Silicon is a kind of material fit for producing neural probe. Silicon on insulator (SOI) is adopted in this paper to fabricate neural probes. The uniformity and manufacturability are improved. The fabricating process and testing results of a series of Multi channel micro neural probes were reported. The thickness of the probe is 15 mu m-30 mu m. The typical impedance characteristics of the record sites are around 2M Omega at 1k Hz. The performance of the neural probe in-vivo was tested on anesthetic rat. The recorded neural spike was typically around 140 mu V. Spike recorded from individual site could exceed 700 mu V. The average signal noise ratio was 7 or more.

Implantable Microsystem for Wireless Neural Recording Applications

A prototype microsystem is presented for wireless neural recording application. An inductive link was built for transcutaneous wireless power transfer and data transmission. Total 16.5 mW power and 50 bps - 2.5 Kbps command data can be received over 1 - 5 MHz with a distance of 0-10 mm. The integrated amplifiers were designed with a limited bandwidth for neural signals acquisition. The gain of 60 dB was obtained by preamplifier at 7 Hz - 3 KHz. An integrated FM transmitter was used to transmit the extracted neural signals to external equipments with 0.374 - 2 mW power comsumption and a maximum data rate of 500 Kbps at 100 MHz. All the integrated circuits modules except the power recovery circuit were tested or stimulated under a 3.3 V power supply, and fabricated in standard CMOS processing.

SOC dynamic power management using artificial neural network

Dynamic Power Management (DPM) is a technique to reduce power consumption of electronic system by selectively shutting down idle components. In this article we try to introduce back propagation network and radial basis network into the research of the system-level power management policies. We proposed two PM policies-Back propagation Power Management (BPPM) and Radial Basis Function Power Management (RBFPM) which are based on Artificial Neural Networks (ANN). Our experiments show that the two power management policies greatly lowered the system-level power consumption and have higher performance than traditional Power Management(PM) techniques-BPPM is 1.09-competitive and RBFPM is 1.08-competitive vs. 1.79 . 1.45 . 1.18-competitive separately for traditional timeout PM . adaptive predictive PM and stochastic PM.