Learning and evolution are two fundamental forms of adaptation. There has been a great interest in combining learning and evolution with artificial neural networks (ANNs) in recent years. This paper: 1) reviews different combinations between ANNs and evolutionary algorithms (EAs), including using EAs to evolve ANN connection weights, architectures, learning rules, and input features; 2) discusses different search operators which have been used in various EAs; and 3) points out possible future research directions. It is shown, through a considerably large literature review, that combinations between ANNs and EAs can lead to significantly better intelligent systems than relying on ANNs or EAs alone.

/pdf/evolving-artificial-neural-networks-4kzrbu7pkn.pdf

Evolving artificial neural networks

artificial neural networks , artificial neural networks , مرکز فناوری اطلاعات و اطلاع رسانی کشاورزی

Artificial Neural Networks

Model selection strategies for machine learning algorithms typically involve the numerical optimisation of an appropriate model selection criterion, often based on an estimator of generalisation performance, such as k-fold cross-validation. The error of such an estimator can be broken down into bias and variance components. While unbiasedness is often cited as a beneficial quality of a model selection criterion, we demonstrate that a low variance is at least as important, as a non-negligible variance introduces the potential for over-fitting in model selection as well as in training the model. While this observation is in hindsight perhaps rather obvious, the degradation in performance due to over-fitting the model selection criterion can be surprisingly large, an observation that appears to have received little attention in the machine learning literature to date. In this paper, we show that the effects of this form of over-fitting are often of comparable magnitude to differences in performance between learning algorithms, and thus cannot be ignored in empirical evaluation. Furthermore, we show that some common performance evaluation practices are susceptible to a form of selection bias as a result of this form of over-fitting and hence are unreliable. We discuss methods to avoid over-fitting in model selection and subsequent selection bias in performance evaluation, which we hope will be incorporated into best practice. While this study concentrates on cross-validation based model selection, the findings are quite general and apply to any model selection practice involving the optimisation of a model selection criterion evaluated over a finite sample of data, including maximisation of the Bayesian evidence and optimisation of performance bounds.

/pdf/on-over-fitting-in-model-selection-and-subsequent-selection-3to4mouyqd.pdf

On Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation

This paper examines the theory of kernel Fisher discriminant analysis (KFD) in a Hilbert space and develops a two-phase KFD framework, i.e., kernel principal component analysis (KPCA) plus Fisher linear discriminant analysis (LDA). This framework provides novel insights into the nature of KFD. Based on this framework, the authors propose a complete kernel Fisher discriminant analysis (CKFD) algorithm. CKFD can be used to carry out discriminant analysis in "double discriminant subspaces." The fact that, it can make full use of two kinds of discriminant information, regular and irregular, makes CKFD a more powerful discriminator. The proposed algorithm was tested and evaluated using the FERET face database and the CENPARMI handwritten numeral database. The experimental results show that CKFD outperforms other KFD algorithms.

/pdf/kpca-plus-lda-a-complete-kernel-fisher-discriminant-540vxq5jmz.pdf

KPCA plus LDA: a complete kernel Fisher discriminant framework for feature extraction and recognition

Identification and classification of chromosomal aberrations in human induced pluripotent stem cells

Radial basis function network configuration using genetic algorithms

Nonlinear Fisher discriminant analysis using a minimum squared error cost function and the orthogonal least squares algorithm

Recurrent radial basis function networks for adaptive noise cancellation

The temporal relationship between changes in cerebral blood flow (CBF) and cerebral blood volume (CBV) is important in the biophysical modeling and interpretation of the hemodynamic response to activation, particularly in the context of magnetic resonance imaging and the blood oxygen level-dependent signal. measured the steady state relationship between changes in CBV and CBF after hypercapnic challenge. The relationship CBV is proportional to CBFphi has been used extensively in the literature. Two similar models, the Balloon and the Windkessel , have been proposed to describe the temporal dynamics of changes in CBV with respect to changes in CBF. In this study, a dynamic model extending the Windkessel model by incorporating delayed compliance is presented. The extended model is better able to capture the dynamics of CBV changes after changes in CBF, particularly in the return-to-baseline stages of the response.

Steve A. Billings

Papers

Radial basis function network configuration using genetic algorithms

Nonlinear Fisher discriminant analysis using a minimum squared error cost function and the orthogonal least squares algorithm

Recurrent radial basis function networks for adaptive noise cancellation

A Model of the Dynamic Relationship between Blood Flow and Volume Changes during Brain Activation

Modeling the evolution of culture-adapted human embryonic stem cells.