Much of our understanding of human thinking is based on probabilistic models. This innovative book by Jerome R. Busemeyer and Peter D. Bruza argues that, actually, the underlying mathematical structures from quantum theory provide a much better account of human thinking than traditional models. They introduce the foundations for modelling probabilistic-dynamic systems using two aspects of quantum theory. The first, 'contextuality', is a way to understand interference effects found with inferences and decisions under conditions of uncertainty. The second, 'quantum entanglement', allows cognitive phenomena to be modeled in non-reductionist ways. Employing these principles drawn from quantum theory allows us to view human cognition and decision in a totally new light. Introducing the basic principles in an easy-to-follow way, this book does not assume a physics background or a quantum brain and comes complete with a tutorial and fully worked-out applications in important areas of cognition and decision.

/pdf/quantum-models-of-cognition-and-decision-hejlh57vgk.pdf

Quantum Models of Cognition and Decision

Metaheuristic design of feedforward neural networks

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

http://audition.ens.fr/dp/pdfs/pressnitzer-2006-bistable_AV_Authors_Manuscript.pdf

Temporal dynamics of auditory and visual bistability reveal common principles of perceptual organization

What are quantum fluctuations

Stability of embedded patterns on associative memory is investigated in this paper. The associative memory is composed of complex-valued Hopfield neural network, in which the state of neurons are encoded by the phase values on a unit circle of complex plane. Local iterative learning scheme and Projection rule are used for embedding the patterns onto the network. The retaining performance for embedded patterns are evaluated through storing randomly generated patterns and gray-scaled images with changing the resolution of neuron state.

Pattern stability on complex-valued associative memory by local iterative learning scheme

The numerical method for solving the nonlinear eigenvalue problem has been developed by using the collocation Element-Free Galerkin Method (EFGM) and its performance has been numerically investigated The results of computations show that the approximate solution of the nonlinear eigenvalue problem can be obtained stably by using the developed method Therefore, it can be concluded that the developed method is useful for solving the nonlinear eigenvalue problem

/pdf/application-of-collocation-meshless-method-to-eigenvalue-d8u8oaq8b7.pdf

Application of Collocation Meshless Method to Eigenvalue Problem

A recognition system for three-dimensional objects is proposed in this paper. This system consists of line laser projectors and a web camera in order to collect depth and curvature information of objects, leading to a compact and cost-effective system compared to light coding-based systems such as Microsoft Kinect. Curvature information of objects can be obtained through calculation of Fourier components from deformed lines of laser beam that are projected onto the curves of objects. Self-Organizing Map is used for classification of objects for dealing with multidimensional data of Fourier components. Performances of the proposed system are explored through the recognition of toy blocks with the same size in two-dimensional image and with various curves.

On Recognition of Three-Dimensional Objects Using Curvature Information

This paper presents map-based data classification for hematopoietic tumor patients. A set of squarely arranged neurons in the map is defined as a block, and previously proposed block-matching-based learning constructs the map used for data classification. This paper incorporates pseudo-learning processes, which employ block reference vectors as quasi-training data, in the above training processes. Pseudo-learning improves the accuracy of classification. Experimental results establish that the percentage of missing the screening data of the tumor patients is very low.

Accuracy Improvement of SOM-Based Data Classification for Hematopoietic Tumor Patients

PROBLEM TO BE SOLVED: To provide a data processor for processing three-dimensional data by a neural network to acquire expected processing results. SOLUTION: Three-dimensional data x m are normalized into the values of 0 to 1 by a normalizing part 12, and inputted to a network part 16 of a BP learning type neural network 14. The network part 16 operates predetermined processing to the three-dimensional data x m based on parameters w nm , w pn , θ n and θ p set by a parameter setting part 18. At that time, the three-dimensional data x m are processed as quaternion. That is, three components configuring the three-dimensional data x m are processed in a batch as three-dimensional vector data. Thus, it is possible to maintain the relevancy of those three components. Then, the processed data y p by the network part 16 are outputted to the outside as the output data of a data processor 10. COPYRIGHT: (C)2005,JPO&NCIPI

Nobuyuki Matsui

Papers

Pattern stability on complex-valued associative memory by local iterative learning scheme

Application of Collocation Meshless Method to Eigenvalue Problem

On Recognition of Three-Dimensional Objects Using Curvature Information

Accuracy Improvement of SOM-Based Data Classification for Hematopoietic Tumor Patients

Data processor and data processing method