In recent years the Probabilistic Neural Network (PPN) has been used in a large number of applications due to its simplicity and efficiency. PNN assigns the test data to the class with maximum likelihood compared with other classes. Likelihood of the test data to each training data is computed in the pattern layer through a kernel density estimation using a simple Bayesian rule. The kernel is usually a standard probability distribution function such as a Gaussian function. A spread parameter is used as a global parameter which determines the width of the kernel. The Bayesian rule in the pattern layer estimates the conditional probability of each class given an input vector without considering any probable local densities or heterogeneity in the training data. In this paper, an enhanced and generalized PNN (EPNN) is presented using local decision circles (LDCs) to overcome the aforementioned shortcoming and improve its robustness to noise in the data. Local decision circles enable EPNN to incorporate local information and non-homogeneity existing in the training population. The circle has a radius which limits the contribution of the local decision. In the conventional PNN the spread parameter can be optimized for maximum classification accuracy. In the proposed EPNN two parameters, the spread parameter and the radius of local decision circles, are optimized to maximize the performance of the model. Accuracy and robustness of EPNN are compared with PNN using three different benchmark classification problems, iris data, diabetic data, and breast cancer data, and five different ratios of training data to testing data: 90:10, 80:20, 70:30, 60:40, and 50:50. EPNN provided the most accurate results consistently for all ratios. Robustness of PNN and EPNN is investigated using different values of signal to noise ratio (SNR). Accuracy of EPNN is consistently higher than accuracy of PNN at different levels of SNR and for all ratios of training data to testing data.

Enhanced probabilistic neural network with local decision circles: A robust classifier

Digital Hardware Evolution.- An Online EHW Pattern Recognition System Applied to Sonar Spectrum Classification.- Design of Electronic Circuits Using a Divide-and-Conquer Approach.- Implementing Multi-VRC Cores to Evolve Combinational Logic Circuits in Parallel.- An Intrinsic Evolvable Hardware Based on Multiplexer Module Array.- Estimating Array Connectivity and Applying Multi-output Node Structure in Evolutionary Design of Digital Circuits.- Research on the Online Evaluation Approach for the Digital Evolvable Hardware.- Research on Multi-objective On-Line Evolution Technology of Digital Circuit Based on FPGA Model.- Evolutionary Design of Generic Combinational Multipliers Using Development.- Analog Hardware Evolution.- Automatic Synthesis of Practical Passive Filters Using Clonal Selection Principle-Based Gene Expression Programming.- Research on Fault-Tolerance of Analog Circuits Based on Evolvable Hardware.- Analog Circuit Evolution Based on FPTA-2.- Bio-inspired Systems.- Knowledge Network Management System with Medicine Self Repairing Strategy.- Design of a Cell in Embryonic Systems with Improved Efficiency and Fault-Tolerance.- Design on Operator-Based Reconfigurable Hardware Architecture and Cell Circuit.- Bio-inspired Systems with Self-developing Mechanisms.- Development of a Tiny Computer-Assisted Wireless EEG Biofeedback System.- Steps Forward to Evolve Bio-inspired Embryonic Cell-Based Electronic Systems.- Evolution of Polymorphic Self-checking Circuits.- Mechanical Hardware Evolution.- Sliding Algorithm for Reconfigurable Arrays of Processors.- System-Level Modeling and Multi-objective Evolutionary Design of Pipelined FFT Processors for Wireless OFDM Receivers.- Reducing the Area on a Chip Using a Bank of Evolved Filters.- Evolutionary Design.- Walsh Function Systems: The Bisectional Evolutional Generation Pattern.- Extrinsic Evolvable Hardware on the RISA Architecture.- Evolving and Analysing "Useful" Redundant Logic.- Adaptive Transmission Technique in Underwater Acoustic Wireless Communication.- Autonomous Robot Path Planning Based on Swarm Intelligence and Stream Functions.- Research on Adaptive System of the BTT-45 Air-to-Air Missile Based on Multilevel Hierarchical Intelligent Controller.- The Design of an Evolvable On-Board Computer.- Evolutionary Algorithms in Hardware Design.- Extending Artificial Development: Exploiting Environmental Information for the Achievement of Phenotypic Plasticity.- UDT-Based Multi-objective Evolutionary Design of Passive Power Filters of a Hybrid Power Filter System.- Designing Electronic Circuits by Means of Gene Expression Programming II.- Designing Polymorphic Circuits with Evolutionary Algorithm Based on Weighted Sum Method.- Robust and Efficient Multi-objective Automatic Adjustment for Optical Axes in Laser Systems Using Stochastic Binary Search Algorithm.- Minimization of the Redundant Sensor Nodes in Dense Wireless Sensor Networks.- Evolving in Extended Hamming Distance Space: Hierarchical Mutation Strategy and Local Learning Principle for EHW.- Hardware Implementation of Evolutionary Algorithms.- Adaptive and Evolvable Analog Electronics for Space Applications.- Improving Flexibility in On-Line Evolvable Systems by Reconfigurable Computing.- Evolutionary Design of Resilient Substitution Boxes: From Coding to Hardware Implementation.- A Sophisticated Architecture for Evolutionary Multiobjective Optimization Utilizing High Performance DSP.- FPGA-Based Genetic Algorithm Kernel Design.- Using Systolic Technique to Accelerate an EHW Engine for Lossless Image Compression.

Evolvable systems : from biology to hardware : 7th International Conference, ICES 2007, Wuhan, China, September 21-23, 2007 : proceedings

Complex-valued neural networks is a rapidly developing neural network framework that utilizes complex arithmetic, exhibiting specific characteristics in its learning, self-organizing, and processing dynamics. They are highly suitable for processing complex amplitude, composed of amplitude and phase, which is one of the core concepts in physical systems to deal with electromagnetic, light, sonic/ ultrasonic waves as well as quantum waves, namely, electron and superconducting waves. This fact is a critical advantage in practical applications in diverse fields of engineering, where signals are routinely analyzed and processed in time/space, frequency, and phase domains.

Complex-Valued Neural Networks: Advances and Applications

Deep neural network (DNN), being able to effectively learn from a training set and provide highly accurate classification results, has become the de-facto technique used in many mission-critical systems. The security of DNN itself is therefore of great concern. In this paper, we investigate the impact of fault injection attacks on DNN, wherein attackers try to misclassify a specified input pattern into an adversarial class by modifying the parameters used in DNN via fault injection. We propose two kinds of fault injection attacks to achieve this objective. Without considering stealthiness of the attack, single bias attack (SBA) only requires to modify one parameter in DNN for misclassification, based on the observation that the outputs of DNN may linearly depend on some parameters. Gradient descent attack (GDA) takes stealthiness into consideration. By controlling the amount of modification to DNN parameters, GDA is able to minimize the fault injection impact on input patterns other than the specified one. Experimental results demonstrate the effectiveness and efficiency of the proposed attacks.

Fault injection attack on deep neural network

To solve learning problems with vast number of inputs, this paper proposes a novel learning structure merging a number of small fuzzy neural networks (FNNs) into a hierarchical learning structure called a merged-FNN. In this paper, the merged-FNN is proved to be a universal approximator. This computing approach uses a fusion of FNNs using B-spline membership functions (BMFs) with a reduced-form genetic algorithm (RGA). RGA is employed to tune all free parameters of the merged-FNN, including both the control points of the BMFs and the weights of the small FNNs. The merged-FNN can approximate a continuous nonlinear function to any desired degree of accuracy. For a practical application, a battery state-of-charge (BSOC) estimator, which is a twelve input, one output system, in a lithium-ion battery string is proposed to verify the effectiveness of the merged-FNN. From experimental results, the learning ability of the newly proposed merged-FNN with RGA is superior to that of the traditional neural networks with back-propagation learning.

A Merged Fuzzy Neural Network and Its Applications in Battery State-of-Charge Estimation

Associative memory networks based on quaternionic Hopfield neural network are investigated in this paper. These networks are composed of quaternionic neurons, and input, output, threshold, and connection weights are represented in quaternions, which is a class of hypercomplex number systems. The energy function of the network and the Hebbian rule for embedding patterns are introduced. The stable states and their basins are explored for the networks with three neurons and four neurons. It is clarified that there exist at most 16 stable states, called multiplet components, as the degenerated stored patterns, and each of these states has its basin in the quaternionic networks.

Associative memory in quaternionic Hopfield neural network.

We analyze a discrete-time quaternionic Hopfield neural network with continuous state variables updated asynchronously. The state of a neuron takes quaternionic value which is four-dimensional hypercomplex number. Two types of the activation function for updating neuron states are introduced and examined. The stable states of the networks are demonstrated through an example of small network.

Dynamics of discrete-time quaternionic hopfield neural networks

Data detection based on self organizing maps is presented for hematopoietic tumor patients Learning data for the maps are generated from the screening data of examinees The incomplete screening data without some item values is then supplemented by substituting averaged non-missing item values In addition, redundant items, which are common to all the data and tend to have an unfavorable influence on data detection, are eliminated by a genetic algorithm and/or an immune algorithm It is basically judged, by observing the label of a winner neuron in the map, whether the data presented to the map belongs to the class of hematopoietic tumors Some experimental results are provided to show that the proposed methods achieve the high probability of correctly identifying examinees as hematopoietic tumor patients

Self-Organizing Map Based Data Detection of Hematopoietic Tumors

For the manufacturing of computers built by nanotechnology, defects are expected to be a major problem. This paper explores this issue for nanocomputers based on cellular automata. Known for their regular structure, such architectures promise cost-effective manufacturing based on molecular self-organization. We show how a cellular automaton can detect defects in a self-contained way, and how it configures circuits on its cells while avoiding the defects. The employed cellular automaton is asynchronous, i.e., it does not require a central clock to synchronize the updates of its cells. This mode of timing is especially suitable for the high integration densities of nanotechnology implementations, since it potentially causes less heat dissipation.

Defect-tolerance in cellular nanocomputers

https://www.jstage.jst.go.jp/article/sicetr1965/41/7/41_7_587/_pdf

Naotake Kamiura

Papers

Associative memory in quaternionic Hopfield neural network.

Dynamics of discrete-time quaternionic hopfield neural networks

Self-Organizing Map Based Data Detection of Hematopoietic Tumors

Defect-tolerance in cellular nanocomputers

A Self-Organizing Map Approach for Detecting Confusion between Blood Samples