Book•
Knowledge-Based Intelligent Information and Engineering Systems
17 Sep 2004-
TL;DR: Adaptive Resonance Theory (ART) neural networks model real-time prediction, search, learning, and recognition, and design principles derived from scientific analyses and design constraints imposed by targeted applications have jointly guided the development of many variants of the basic networks.
Abstract: Adaptive Resonance Theory (ART) neural networks model real-time prediction, search, learning, and recognition. ART networks function both as models of human cognitive information processing [1,2,3] and as neural systems for technology transfer [4]. A neural computation central to both the scientific and the technological analyses is the ART matching rule [5], which models the interaction between topdown expectation and bottom-up input, thereby creating a focus of attention which, in turn, determines the nature of coded memories. Sites of early and ongoing transfer of ART-based technologies include industrial venues such as the Boeing Corporation [6] and government venues such as MIT Lincoln Laboratory [7]. A recent report on industrial uses of neural networks [8] states: “[The] Boeing ... Neural Information Retrieval System is probably still the largest-scale manufacturing application of neural networks. It uses [ART] to cluster binary templates of aeroplane parts in a complex hierarchical network that covers over 100,000 items, grouped into thousands of self-organised clusters. Claimed savings in manufacturing costs are in millions of dollars per annum.” At Lincoln Lab, a team led by Waxman developed an image mining system which incorporates several models of vision and recognition developed in the Boston University Department of Cognitive and Neural Systems (BU/CNS). Over the years a dozen CNS graduates (Aguilar, Baloch, Baxter, Bomberger, Cunningham, Fay, Gove, Ivey, Mehanian, Ross, Rubin, Streilein) have contributed to this effort, which is now located at Alphatech, Inc. Customers for BU/CNS neural network technologies have attributed their selection of ART over alternative systems to the model's defining design principles. In listing the advantages of its THOT technology, for example, American Heuristics Corporation (AHC) cites several characteristic computational capabilities of this family of neural models, including fast on-line (one-pass) learning, “vigilant” detection of novel patterns, retention of rare patterns, improvement with experience, “weights [which] are understandable in real world terms,” and scalability (www.heuristics.com). Design principles derived from scientific analyses and design constraints imposed by targeted applications have jointly guided the development of many variants of the basic networks, including fuzzy ARTMAP [9], ART-EMAP [10], ARTMAP-IC [11],
Citations
More filters
TL;DR: The results from a project aimed at creating an MRIO account that represents all countries at a detailed sectoral level, allows continuous updating, provides information on data reliability, contains table sheets expressed in basic prices as well as all margins and taxes, and contains a historical time series are described.
Abstract: There are a number of initiatives aimed at compiling large-scale global multi-region input–output (MRIO) tables complemented with non-monetary information such as on resource flows and environmental burdens. Depending on purpose or application, MRIO construction and usage has been hampered by a lack of geographical and sectoral detail; at the time of writing, the most advanced initiatives opt for a breakdown into at most 129 regions and 120 sectors. Not all existing global MRIO frameworks feature continuous time series, margins and tax sheets, and information on reliability and uncertainty. Despite these potential limitations, constructing a large MRIO requires significant manual labour and many years of time. This paper describes the results from a project aimed at creating an MRIO account that represents all countries at a detailed sectoral level, allows continuous updating, provides information on data reliability, contains table sheets expressed in basic prices as well as all margins and taxes, and co...
1,071 citations
01 Jan 2007
TL;DR: This chapter complements other chapters of this book in reviewing user models and user modeling approaches applied in adaptive Web systems by focusing on the overlay approach to user model representation and the uncertainty-based approach touser modeling.
Abstract: One distinctive feature of any adaptive system is the user model that represents essential information about each user This chapter complements other chapters of this book in reviewing user models and user modeling approaches applied in adaptive Web systems The presentation is structured along three dimensions: what is being modeled, how it is modeled, and how the models are maintained After a broad overview of the nature of the information presented in these various user models, the chapter focuses on two groups of approaches to user model representation and maintenance: the overlay approach to user model representation and the uncertainty-based approach to user modeling
869 citations
03 Dec 2012
TL;DR: This paper presents a system for human physical Activity Recognition using smartphone inertial sensors and proposes a novel hardware-friendly approach for multiclass classification that adapts the standard Support Vector Machine and exploits fixed-point arithmetic for computational cost reduction.
Abstract: Activity-Based Computing [1] aims to capture the state of the user and its environment by exploiting heterogeneous sensors in order to provide adaptation to exogenous computing resources. When these sensors are attached to the subject's body, they permit continuous monitoring of numerous physiological signals. This has appealing use in healthcare applications, e.g. the exploitation of Ambient Intelligence (AmI) in daily activity monitoring for elderly people. In this paper, we present a system for human physical Activity Recognition (AR) using smartphone inertial sensors. As these mobile phones are limited in terms of energy and computing power, we propose a novel hardware-friendly approach for multiclass classification. This method adapts the standard Support Vector Machine (SVM) and exploits fixed-point arithmetic for computational cost reduction. A comparison with the traditional SVM shows a significant improvement in terms of computational costs while maintaining similar accuracy, which can contribute to develop more sustainable systems for AmI.
802 citations
TL;DR: A simple and effective sample size prediction algorithm that conducts weighted fitting of learning curves and outperformed an un-weighted algorithm described in previous literature can help researchers determine annotation sample size for supervised machine learning.
Abstract: Supervised learning methods need annotated data in order to generate efficient models. Annotated data, however, is a relatively scarce resource and can be expensive to obtain. For both passive and active learning methods, there is a need to estimate the size of the annotated sample required to reach a performance target. We designed and implemented a method that fits an inverse power law model to points of a given learning curve created using a small annotated training set. Fitting is carried out using nonlinear weighted least squares optimization. The fitted model is then used to predict the classifier's performance and confidence interval for larger sample sizes. For evaluation, the nonlinear weighted curve fitting method was applied to a set of learning curves generated using clinical text and waveform classification tasks with active and passive sampling methods, and predictions were validated using standard goodness of fit measures. As control we used an un-weighted fitting method. A total of 568 models were fitted and the model predictions were compared with the observed performances. Depending on the data set and sampling method, it took between 80 to 560 annotated samples to achieve mean average and root mean squared error below 0.01. Results also show that our weighted fitting method outperformed the baseline un-weighted method (p < 0.05). This paper describes a simple and effective sample size prediction algorithm that conducts weighted fitting of learning curves. The algorithm outperformed an un-weighted algorithm described in previous literature. It can help researchers determine annotation sample size for supervised machine learning.
382 citations
TL;DR: A review on the most recent progress of mechanisms, training modes and control strategies for lower limb rehabilitation robots from year 2001 to 2014 is presented.
350 citations
References
More filters
01 Jan 1987
2,530 citations
TL;DR: The fuzzy ARTMAP system is compared with Salzberg's NGE systems and with Simpson's FMMC system, and its performance in relation to benchmark backpropagation and generic algorithm systems.
Abstract: A neural network architecture is introduced for incremental supervised learning of recognition categories and multidimensional maps in response to arbitrary sequences of analog or binary input vectors, which may represent fuzzy or crisp sets of features. The architecture, called fuzzy ARTMAP, achieves a synthesis of fuzzy logic and adaptive resonance theory (ART) neural networks by exploiting a close formal similarity between the computations of fuzzy subsethood and ART category choice, resonance, and learning. Four classes of simulation illustrated fuzzy ARTMAP performance in relation to benchmark backpropagation and generic algorithm systems. These simulations include finding points inside versus outside a circle, learning to tell two spirals apart, incremental approximation of a piecewise-continuous function, and a letter recognition database. The fuzzy ARTMAP system is also compared with Salzberg's NGE systems and with Simpson's FMMC system. >
2,096 citations
"Knowledge-Based Intelligent Informa..." refers background or methods in this paper
...Selection of one particular ARTMAP algorithm is intended to facilitate ongoing technology transfer....
[...]
...The talk will describe a recent application that relies on distributed code representations to exploit the ARTMAP capacity for one-to-many learning, which has enabled the development of self-organizing expert systems for multi-level object grouping, information fusion, and discovery of hierarchical knowledge structures....
[...]
...The character of their code representations, distributed vs. winner-take-all, is, in fact, a primary factor differentiating various ARTMAP networks....
[...]
...A, ART 3, fuzzy ART, distributed ART) and supervised (ARTMAP, fuzzy ARTMAP, ARTEMAP, ARTMAP-IC, ARTMAP-FTR, distributed ARTMAP, default ARTMAP) systems....
[...]
...Design principles derived from scientific analyses and design constraints imposed by targeted applications have jointly guided the development of many variants of the basic networks, including fuzzy ARTMAP [9], ART-EMAP [10], ARTMAP-IC [11],...
[...]
10 Jan 1999
TL;DR: This paper proposes a new algorithm, called A-Close, using a closure mechanism to find frequent closed itemsets, and shows that this approach is very valuable for dense and/or correlated data that represent an important part of existing databases.
Abstract: In this paper, we address the problem of finding frequent itemsets in a database. Using the closed itemset lattice framework, we show that this problem can be reduced to the problem of finding frequent closed itemsets. Based on this statement, we can construct efficient data mining algorithms by limiting the search space to the closed itemset lattice rather than the subset lattice. Moreover, we show that the set of all frequent closed itemsets suffices to determine a reduced set of association rules, thus addressing another important data mining problem: limiting the number of rules produced without information loss. We propose a new algorithm, called A-Close, using a closure mechanism to find frequent closed itemsets. We realized experiments to compare our approach to the commonly used frequent itemset search approach. Those experiments showed that our approach is very valuable for dense and/or correlated data that represent an important part of existing databases.
1,513 citations
"Knowledge-Based Intelligent Informa..." refers background or methods in this paper
...Our previous research highlighted the benefits gained (i) by combining different kinds of inferences and/or (ii) by including incomplete deductions and/or (iii) by reducing the expressiveness of the knowledge subject to analysis [5, 11]....
[...]
...In particular, the knowledge acquisition, knowledge modelling, and knowledge validation/verification phases ([7], [12], [11], [16], [3]) were too demanding in the context of our resources constraints especially in the context of a multidisciplinary domain such as that of SME for which little formalized knowledge exists....
[...]
...As the EEG features may be irrelevant to the binary classification problems, for learning the hidden neurons we use a bottom up search strategy which selects features providing the best classification accuracy [11]....
[...]
...A, ART 3, fuzzy ART, distributed ART) and supervised (ARTMAP, fuzzy ARTMAP, ARTEMAP, ARTMAP-IC, ARTMAP-FTR, distributed ARTMAP, default ARTMAP) systems....
[...]
...Addison-Wesley, Boston (1983) [11] Kneale, W....
[...]
TL;DR: A new neural network architecture, called ARTMAP, that autonomously learns to classify arbitrarily many, arbitrarily ordered vectors into recognition categories based on predictive success, which is a type of self-organizing expert system that calibrates the selectivity of its hypotheses based upon predictive success.
1,042 citations
Proceedings Article•
IBM1
TL;DR: In this paper, the problem of integrating constraints that are Boolean expressions over the presence or absence of items into the association discovery algorithm was considered and three integrated algorithms for mining association rules with item constraints were presented.
Abstract: The problem of discovering association rules has received considerable research attention and several fast algorithms for mining association rules have been developed. In practice, users are often interested in a subset of association rules. For example, they may only want rules that contain a specific item or rules that contain children of a specific item in a hierarchy. While such constraints can be applied as a post-processing step, integrating them into the mining algorithm can dramatically reduce the execution time. We consider the problem of integrating constraints that are Boolean expressions over the presence or absence of items into the association discovery algorithm. We present three integrated algorithms for mining association rules with item constraints and discuss their tradeoffs.
866 citations