Biomedical subjects

Donald C Wunsch

Publications and source records attributed to Donald C Wunsch.

8 recordsLinked to original sources

PubMed2006

Neural network explanation using inversion.

An important drawback of many artificial neural networks (ANN) is their lack of explanation capability [Andrews, R., Diederich, J., & Tickle, A. B. (1996). A survey and critique of techniques for extracting rules from trained artificial neural networks. Knowledge-Based Systems, 8, 373-389]. This paper starts with a survey of algorithms which attempt to explain the ANN output. We then present HYPINV, a new explanation algorithm which relies on network inversion; i.e. calculating the ANN input which produces a desired output. HYPINV is a pedagogical algorithm, that extracts rules, in the form of hyperplanes. It is able to generate rules with arbitrarily desired fidelity, maintaining a fidelity-complexity tradeoff. To our knowledge, HYPINV is the only pedagogical rule extraction method, which extracts hyperplane rules from continuous or binary attribute neural networks. Different network inversion techniques, involving gradient descent as well as an evolutionary algorithm, are presented. An information theoretic treatment of rule extraction is presented. HYPINV is applied to example synthetic problems, to a real aerospace problem, and compared with similar algorithms using benchmark problems.

Algorithms↗

PubMed2006

Permutation coding technique for image recognition systems.

A feature extractor and neural classifier for image recognition systems are proposed. The proposed feature extractor is based on the concept of random local descriptors (RLDs). It is followed by the encoder that is based on the permutation coding technique that allows to take into account not only detected features but also the position of each feature on the image and to make the recognition process invariant to small displacements. The combination of RLDs and permutation coding permits us to obtain a sufficiently general description of the image to be recognized. The code generated by the encoder is used as an input data for the neural classifier. Different types of images were used to test the proposed image recognition system. It was tested in the handwritten digit recognition problem, the face recognition problem, and the microobject shape recognition problem. The results of testing are very promising. The error rate for the Modified National Institute of Standards and Technology (MNIST) database is 0.44% and for the Olivetti Research Laboratory (ORL) database it is 0.1%.

Algorithms↗

PubMed2004

Detection of basal cell carcinoma using electrical impedance and neural networks.

Variations in electrical impedance over frequency might be used to distinguish basal cell carcinoma (BCC) from benign skin lesions, although the patterns that separate the two are nonobvious. Artificial neural networks (ANNs) may be good pattern classifiers for this application. A preliminary study to show the potential of neural networks to distinguish benign from malignant skin lesions using electrical impedance is presented. Electrical impedance was measured in vivo from 1 kHz to 1 MHz at five virtual depths on 18 BCC and 16 benign or premalignant lesions. A feed-forward neural network was trained using back propagation to classify these lesions. Two methods of preprocessing were used to account for the impedance of normal skin and the size of the lesion, one based on estimating the impedance of the lesion relative to adjacent normal skin and one based on estimating the impedance of the lesion independent of size or surrounding normal skin. Neural networks were able to classify measurements in a test set with 100% accuracy for the first preprocessing technique and 85% accuracy for the second. These results indicate electrical impedance may be a promising clinical diagnostic tool for basal cell carcinoma or other forms of skin cancer.

Algorithms↗

PubMed2004

Generalization of features in the assembly neural networks.

The purpose of the paper is an experimental study of the formation of class descriptions, taking place during learning, in assembly neural networks. The assembly neural network is artificially partitioned into several sub-networks according to the number of classes that the network has to recognize. The features extracted from input data are represented in neural column structures of the sub-networks. Hebbian neural assemblies are formed in the column structure of the sub-networks by weight adaptation. A specific class description is formed in each sub-network of the assembly neural network due to intersections between the neural assemblies. The process of formation of class descriptions in the sub-networks is interpreted as feature generalization. A set of special experiments is performed to study this process, on a task of character recognition using the MNIST database.

Algorithms↗

PubMedDate not supplied

Recurrent neural networks with backtrack-points and negative reinforcement applied to cost-based abduction.

Abduction is the process of proceeding from data describing a set of observations or events, to a set of hypotheses which best explains or accounts for the data. Cost-based abduction (CBA) is an AI formalism in which evidence to be explained is treated as a goal to be proven, proofs have costs based on how much needs to be assumed to complete the proof, and the set of assumptions needed to complete the least-cost proof are taken as the best explanation for the given evidence. In this paper, we present two techniques for improving the performance of high order recurrent networks (HORN) applied to cost-based abduction. In the backtrack-points technique, we use heuristics to recognize early that the network trajectory is moving in the wrong direction; we then restore the network state to a previously stored point, and apply heuristic perturbations to nudge the network trajectory in a different direction. In the negative reinforcement technique, we add hyperedges to the network to reduce the attractiveness of local minima. We apply these techniques to a suite of six large CBA instances, systematically generated to be difficult.

Algorithms↗

PubMedDate not supplied

Abductive reasoning with recurrent neural networks.

Abduction is the process of proceeding from data describing a set of observations or events, to a set of hypotheses which best explains or accounts for the data. Cost-based abduction (CBA) is a formalism in which evidence to be explained is treated as a goal to be proven, proofs have costs based on how much needs to be assumed to complete the proof, and the set of assumptions needed to complete the least-cost proof are taken as the best explanation for the given evidence. In previous work, we presented a method for using high order recurrent networks to find least cost proofs for CBA instances. Here, we present a method that significantly reduces the size of the neural network that is produced for a given CBA instance. We present experimental results describing the performance of this method and comparing its performance to that of the previous method.

Artificial Intelligence↗

PubMedDate not supplied

Design of an adaptive neural network based power system stabilizer.

Power system stabilizers (PSS) are used to generate supplementary control signals for the excitation system in order to damp the low frequency power system oscillations. To overcome the drawbacks of conventional PSS (CPSS), numerous techniques have been proposed in the literature. Based on the analysis of existing techniques, this paper presents an indirect adaptive neural network based power system stabilizer (IDNC) design. The proposed IDNC consists of a neuro-controller, which is used to generate a supplementary control signal to the excitation system, and a neuro-identifier, which is used to model the dynamics of the power system and to adapt the neuro-controller parameters. The proposed method has the features of a simple structure, adaptivity and fast response. The proposed IDNC is evaluated on a single machine infinite bus power system under different operating conditions and disturbances to demonstrate its effectiveness and robustness.

Electric Power Supplies↗

PubMedDate not supplied

Million city traveling salesman problem solution by divide and conquer clustering with adaptive resonance neural networks.

The Traveling Salesman Problem (TSP) is a very hard optimization problem in the field of operations research. It has been shown to be NP-complete, and is an often-used benchmark for new optimization techniques. One of the main challenges with this problem is that standard, non-AI heuristic approaches such as the Lin-Kernighan algorithm (LK) and the chained LK variant are currently very effective and in wide use for the common fully connected, Euclidean variant that is considered here. This paper presents an algorithm that uses adaptive resonance theory (ART) in combination with a variation of the Lin-Kernighan local optimization algorithm to solve very large instances of the TSP. The primary advantage of this algorithm over traditional LK and chained-LK approaches is the increased scalability and parallelism allowed by the divide-and-conquer clustering paradigm. Tours obtained by the algorithm are lower quality, but scaling is much better and there is a high potential for increasing performance using parallel hardware.

Cluster Analysis↗