The competitive learning technique is a well-known algorithm used in neuralnetworks which classifies the input vectors, so that the vectors (samples) belonging to the same class have similar characteristics. Each cla...
详细信息
ISBN:
(纸本)0819405787
The competitive learning technique is a well-known algorithm used in neuralnetworks which classifies the input vectors, so that the vectors (samples) belonging to the same class have similar characteristics. Each class is represented by one unit. Dynamic competitive learning is an unsupervised learning technique consisting of two additional parts related to conventional competitive learning: a method of generation of new units within a cluster and a method of generating new clusters. As seen in a description of the multilayered neuralnetworks, the number of clusters, their connections, and the generation of new units is determined dynamically during learning. The model is capable of high-level storage of complex data structures and their classification, including exception handling.
This conference proceedings contains 81 papers. The main subjects are: neuralnetworks theory, neuralnetworks architecture, neuralnetworks implementation, imageprocessingapplications, dynamical systems, control an...
详细信息
This conference proceedings contains 81 papers. The main subjects are: neuralnetworks theory, neuralnetworks architecture, neuralnetworks implementation, imageprocessingapplications, dynamical systems, control and robotics applications, speech and natural language processingapplications, medical applications, and character recognition.
A mathematical structure used to express imageprocessing transforms, the AFATL image algebra has proven itself useful in a wide variety of applications. The theoretical foundation for the image algebra includes many ...
详细信息
ISBN:
(纸本)081940697X
A mathematical structure used to express imageprocessing transforms, the AFATL image algebra has proven itself useful in a wide variety of applications. The theoretical foundation for the image algebra includes many important constructs for handling a wide variety of imageprocessing problems: questions relating to linear and nonlinear transforms, including decomposition techniques; mapping of transformations to computer architectures; neuralnetworks; recursive transforms; and data manipulation on hexagonal arrays. However, statistical notions have been included only on a very elementary level and on a more sophisticated level in the literature. This paper presents an extension of the current image algebra that includes a Bayesian statistical approach. It is shown how images are modeled as random vectors, probability functions or mass functions are modeled as images, and conditional probability functions are modeled as templates. The remainder of the paper gives a brief discussion of the current image algebra, an example of the use of image algebra to express high-level imageprocessing transforms, and the presentation of the statistical development of the image algebra.
The theory of control is being widely used in optimization of dynamical systems. Learning algorithms in neural nets or in statistics have, however, seldom used the techniques of control. One reason for this is that th...
详细信息
ISBN:
(纸本)0819405787
The theory of control is being widely used in optimization of dynamical systems. Learning algorithms in neural nets or in statistics have, however, seldom used the techniques of control. One reason for this is that the neural network parameters (synaptic weights) are used quasi- statically during processing after a learning phase, while control theory determines an optimal trajectory in time for the parameters. This issue is addressed in the context of a neural network dynamics introduced in previous publications as part of an image recognition system designed to integrate model-based and data-driven approaches in a connectionist framework. An important feature of this approach is that recognition must be achieved explicitly through the short- rather than the long-time behavior of the dynamics of the system. The dynamics arises naturally from requirements on the system which include incorporation of prior knowledge such as in inference rules, locality of inferences, and full parallelism. This system is also shown to be effective in image recognition. After reviewing the dynamical system, the authors compare new algorithms for learning the dynamics with Boltzmann-machine-like formulas. Interesting implications of this approach are pointed out, namely, that of a processing strategy that uses a dynamics for the weights as well as the states of the neurons. We conclude by mentioning the difficulties that remain with a control-theoretic strategy.
artificialneuralnetworks are systems composed of interconnected simple computing units known as artificial neurons which simulate some properties of their biological counter- parts. They have been developed and stud...
artificialneuralnetworks are systems composed of interconnected simple computing units known as artificial neurons which simulate some properties of their biological counter- parts. They have been developed and studied for understanding how brains function, and for computational purposes. In order to use a neural network for computation, the network has to be designed in such a way that it performs a useful function. Currently, the most popular method of de- signing a network to perform a function is to adjust the parameters of a specified network until the network approximates the input-output behaviour of the function. Although some analytical knowledge about the function is sometimes available or obtainable, it is usually not used. Some neural network paradigms exist where such knowledge is utilized; however, there is no systematical method to do so. The objective of this research is to develop such a method. A systematic method of neural network design, which we call algebraic derivation methodology, is proposed and developed in this thesis. It is developed with an emphasis on designing neuralnetworks to implement imageprocessing algorithms. A key feature of this methodology is that neurons and neuralnetworks are represented symbolically such that a network can be algebraically derived from a given function and the resulting network can be simplified. By simplification we mean finding an equivalent network (i. e., performing the same function) with fewer layers and fewer neurons. A type of neuralnetworks, which we call LQT networks, are chosen for implementing imageprocessing al- gorithms. Theorems for simplifying such networks are developed. Procedures for deriving such networks to realize both single-input and multiple-input functions are given. To show the merits of the algebraic derivation methodology, LQT networks for im- plementing some well-known algorithms in imageprocessing and some other areas are developed by using the above mentioned theorems
This conference proceedings contains 43 papers. The topics included are applications of neuralnetworks to medical imaging, imageprocessing, coding, speech processing, aerospace, character recognition, physics, commu...
详细信息
ISBN:
(纸本)0819405787
This conference proceedings contains 43 papers. The topics included are applications of neuralnetworks to medical imaging, imageprocessing, coding, speech processing, aerospace, character recognition, physics, communications, and in computers. Learning algorithms and machine learning are discussed in detail.
The architecture of an intelligent imageprocessing system (IIMS) is analyzed, and the main problems related to its practical implementation are discussed. The need for imaging systems and processing methodologies inc...
详细信息
ISBN:
(纸本)0818621419
The architecture of an intelligent imageprocessing system (IIMS) is analyzed, and the main problems related to its practical implementation are discussed. The need for imaging systems and processing methodologies increases as data storage, retrieval, processing, communication, and compression requirements grow. A recent trend in imageprocessing and analysis is borrowing from the fields of artificial intelligence, pattern recognition, and neuralnetworks in order to make it possible to automatically extract various kinds of information from static and dynamic images. The fundamental paradigms relative to the intelligent processing of images are analyzed.
Well-known techniques for image segmentation and edge detection involve the Sobel operators. A single slab function link extended neural net trained using the back propagation delta rule to perform edge detection with...
详细信息
ISBN:
(纸本)0819405787
Well-known techniques for image segmentation and edge detection involve the Sobel operators. A single slab function link extended neural net trained using the back propagation delta rule to perform edge detection without a priori knowledge of any particular detection algorithm is described.
An overview of ongoing research related to the development of an image data compression algorithm using artificialneuralnetworks (ANNs) is presented. The data compression technique under study uses an ANN to perform...
详细信息
ISBN:
(纸本)0780301730
An overview of ongoing research related to the development of an image data compression algorithm using artificialneuralnetworks (ANNs) is presented. The data compression technique under study uses an ANN to perform vector quantization (VQ). A good predictor is one of the essential components of the image compression technique being explored. The performance of the various predictors are compared including an average predictor, a median predictor, a recurrent artificialneural network (RANN) predictor, and a second-order optimal linear predictor. It is shown that, for some cases, a relatively simple recurrent artificialneural network predictor performs close to the second-order optimal linear predictor and better than the average and the median predictors.
暂无评论