A sum-product network (SPN) is a probabilistic model, based on a rooted acyclic directed graph, in which terminal nodes represent probability distributions and non-terminal nodes represent convex sums (weighted averag...
详细信息
A sum-product network (SPN) is a probabilistic model, based on a rooted acyclic directed graph, in which terminal nodes represent probability distributions and non-terminal nodes represent convex sums (weighted averages) and products of probability distributions. They are closely related to probabilistic graphical models, in particular to Bayesian networks with multiple context-specific independencies. Their main advantage is the possibility of building tractable models from data, i.e., models that can perform several inference tasks in time proportional to the number of edges in the graph. They are somewhat similar to neuralnetworks and can address the same kinds of problems, such as imageprocessing and natural language understanding. This paper offers a survey of SPNs, including their definition, the main algorithms for inference and learning from data, several applications, a brief review of software libraries, and a comparison with related models.
The incorporation of information-processing technology into analytical systems in the form of standard computing software has recently been advanced by the introduction of artificial intelligence (AI), both as expert ...
The incorporation of information-processing technology into analytical systems in the form of standard computing software has recently been advanced by the introduction of artificial intelligence (AI), both as expert systems and as neuralnetworks. This paper considers the role of software in system operation, control and automation, and attempts to define intelligence. AI is characterized by its ability to deal with incomplete and imprecise information and to accumulate knowledge. Expert systems, building on standard computing techniques, depend heavily on the domain experts and knowledge engineers that have programmed them to represent the real world. neuralnetworks are intended to emulate the pattern-recognition and parallel processing capabilities of she human brain and are taught rather than programmed. The future may lie in a combination of the recognition ability of the neural network and the rationalization capability of the expert system. In the second part of the paper, examples are given of applications of AI in stand-alone systems for knowledge engineering and medical diagnosis and in embedded systems for failure detection, image analysis, user interfacing, natural language processing, robotics and machine learning, as related to clinical laboratories. It is concluded that AI constitutes a collective form of intellectual property, and that there is a need for better documentation, evaluation and regulation of the systems already being used in clinical laboratories.
In the last 40 years, remote sensing technology has evolved, significantly advancing ocean observation and catapulting its data into the big data era. How to efficiently and accurately process and analyze ocean big da...
详细信息
In the last 40 years, remote sensing technology has evolved, significantly advancing ocean observation and catapulting its data into the big data era. How to efficiently and accurately process and analyze ocean big data and solve practical problems based on ocean big data constitute a great challenge. artificial intelligence (AI) technology has developed rapidly in recent years. Numerous deep learning (DL) models have emerged, becoming prevalent in big data analysis and practical problem solving. Among these, convolutional neuralnetworks (CNNs) stand as a representative class of DL models and have established themselves as one of the premier solutions in various research areas, including computer vision and remote sensing applications. In this study, we first discuss the model architectures of CNNs and some of their variants as well as how they can be applied to the processing and analysis of ocean remote sensing data. Then, we demonstrate that CNNs can fulfill most of the requirements for ocean remote sensing applications across the following six categories: reconstruction of the 3D ocean field, information extraction, image superresolution, ocean phenomena forecast, transfer learning method, and CNN model interpretability method. Finally, we discuss the technical challenges facing the application of CNN-based ocean remote sensing big data and summarize future research directions.
Restricted Boltzmann machine (RBM) is an energy-based artificialneural network (ANN), applied in several applications like imageprocessing, topic modeling, classification, regression, and pattern recognition. The fu...
详细信息
Restricted Boltzmann machine (RBM) is an energy-based artificialneural network (ANN), applied in several applications like imageprocessing, topic modeling, classification, regression, and pattern recognition. The fuzzy version of RBM is a new approach in this field, with parameters considered as fuzzy numbers. In this article, a fuzzy RBM is extended through interval type-2 membership functions, named the interval type-2 fuzzy RBM (IT2FRBM). The additional uncertainties in the structures of the membership functions are embedded in this model. This is formulated as a maximum likelihood problem which allows the parameters of the type-2 fuzzy numbers to be learned. The capabilities of this proposed approach as a discriminative or generative model are assessed. The robustness of this method against noise is analyzed. The results indicate that this IT2FRBM outperforms RBM and its different fuzzy versions.
In recent years, functional networks have emerged as an extension of artificialneuralnetworks (ANNs). In this article, we apply both network techniques to predict the catches of the Prionace Glauca (a class of shark...
详细信息
In recent years, functional networks have emerged as an extension of artificialneuralnetworks (ANNs). In this article, we apply both network techniques to predict the catches of the Prionace Glauca (a class of shark) and the Katsowonus Pelamis (a variety of tuna, more commonly known as the Skipjack). We have developed an application that will help reduce the search time for good fishing zones and thereby increase the fleet's competitivity. Our results show that, thanks to their superior learning and generalisation capacities, functional networks are more efficient than ANNs. Our data proceeds from remote sensors. Their spectral signatures allow us to calculate products that are useful for ecological modelling. After an initial phase of digital imageprocessing, we created a database that provides all the necessary patterns to train both network types.
In the present paper, a new synthesis approach is developed for associative memories based on a modified relaxation algorithm. The design (synthesis) problem of feedback neuralnetworks for associative memories is for...
详细信息
In the present paper, a new synthesis approach is developed for associative memories based on a modified relaxation algorithm. The design (synthesis) problem of feedback neuralnetworks for associative memories is formulated as a set of linear inequalities such that the use of pseudo relaxation method is evident. The pseudo relaxation training in the synthesis algorithms is guaranteed to converge for the design of neuralnetworks without any constraints on the connection matrix. To demonstrate the applicability of the present results and to compare the present synthesis approach with existing design methods, a pattern recognition example is considered.
The detection of image segmented objects in video sequences is constrained by the a priori information available with a classifier. An object recogniser labels image regions based on texture and shape information abou...
详细信息
ISBN:
(纸本)0819435805
The detection of image segmented objects in video sequences is constrained by the a priori information available with a classifier. An object recogniser labels image regions based on texture and shape information about objects for which historical data is available. The introduction of a new object would culminate in its misclassification as the closest possible object known to the recogniser. neuralnetworks can be used to develop a strategy to automatically recognise new objects in image scenes that can be separated from other data for manual labelling. In this paper, one such strategy is presented for natural scene analysis of FLIR images. Appropriate threshold tests for classification are developed for separating known from unknown information. The results show that very high success rates can be obtained using neuralnetworks for the labelling of new objects in scene analysis.
Deep neuralnetworks (DNNs) have been vastly and successfully employed in various artificial intelligence and machine learning applications (e.g., imageprocessing and natural language processing). As DNNs become deep...
详细信息
Deep neuralnetworks (DNNs) have been vastly and successfully employed in various artificial intelligence and machine learning applications (e.g., imageprocessing and natural language processing). As DNNs become deeper and enclose more filters per layer, they incur high computational costs and large memory consumption to preserve their large number of parameters. Moreover, present processing platforms (e.g., CPU, GPU, and FPGA) have not enough internal memory, and hence external memory storage is needed. Hence deploying DNNs on mobile applications is difficult, considering the limited storage space, computation power, energy supply, and real-time processing requirements. In this work, using a method based on tensor decomposition, network parameters were compressed, thereby reducing access to external memory. This compression method decomposes the network layers' weight tensor into a limited number of principal vectors such that (i) almost all the initial parameters can be retrieved, (ii) the network structure did not change, and (iii) the network quality after reproducing the parameters was almost similar to the original network in terms of detection accuracy. To optimize the realization of this method on FPGA, the tensor decomposition algorithm was modified while its convergence was not affected, and the reproduction of network parameters on FPGA was straightforward. The proposed algorithm reduced the parameters of ResNet50, VGG16, and VGG19 networks trained with Cifar10 and Cifar100 by almost 10 times. (C)& nbsp;2022 Elsevier Ltd. All rights reserved.
Based on our research in the last 17 years (with 68 papers published) on the subject of artificialneural network studied from the point of view of N-dimension geometry, a novel neural network system, the dynamic neur...
详细信息
ISBN:
(纸本)9780819474957
Based on our research in the last 17 years (with 68 papers published) on the subject of artificialneural network studied from the point of view of N-dimension geometry, a novel neural network system, the dynamic neural network, is proposed here for detecting an unknown moving (or time-varying) object such that the object will not only be detected by its static images, but also by the way it moves if this object follows a constant moving pattern. The system is designed to identify the unknown object by comparing a few time-separated snapshots of the object to a few standard moving objects learned or memorized in the system. The identification is determined by a user entered accuracy control. It could be very accurate, yet still be quite robust and quite fast in identification (e. g., identification in real-time) because of the simplicity of the algorithm. It is different from most other neural network systems because it employs the ND geometrical concept.
The tremendous backlog of unanalyzed satellite data necessitates the development of improved methods for data cataloging and analysis. Ford Aerospace has developed an image analysis system, Satellite image Analysis us...
The tremendous backlog of unanalyzed satellite data necessitates the development of improved methods for data cataloging and analysis. Ford Aerospace has developed an image analysis system, Satellite image Analysis using neuralnetworks (SIANN), that integrates the technologies necessary to satisfy NASA's science data analysis requirements for the next generation of satellites. SIANN will enable scientists to train a neural network to recognize image data containing scenes of interest and then rapidly search data archives for all such images. The approach combines conventional imageprocessing technology with recent advances in neuralnetworks to provide improved classification capabilities. SIANN allows users to proceed through a four-step process of image classification: filtering and enhancement, creation of neural network training data via application of feature extraction algorithms, configuring and training a neural network model, and classification of images by application of the trained neural network. A prototype experimentation testbed has been completed and applied to climatological data.
暂无评论