This paper is theoretical. We present sufficient and ''almost'' necessary conditions for learning compatibility coefficients in relaxation labeling whose satisfaction will guarantee each desired sample...
详细信息
ISBN:
(纸本)0818679204
This paper is theoretical. We present sufficient and ''almost'' necessary conditions for learning compatibility coefficients in relaxation labeling whose satisfaction will guarantee each desired sample labeling to become consistent and each ambiguous or erroneous input sample labeling to Be attracted to the corresponding desired sample labeling. The derived learning conditions are parallel and local information based. In fact, they are organized as linear inequalities in unit wise and thus the perceptron like algorithms can be used to solve them efficiently with finite convergence.
Backpropagation (BP) learning algorithm is the most widely supervised learning technique which is extensively applied in the training of multi-layer feed-forward neural networks. Many modifications that have been prop...
详细信息
ISBN:
(纸本)9781424435494
Backpropagation (BP) learning algorithm is the most widely supervised learning technique which is extensively applied in the training of multi-layer feed-forward neural networks. Many modifications that have been proposed to improve the performance of BP have focused on solving the "flat spot" problem to increase the convergence rate. However, their performance is limited due to the error overshooting problem. In [20], a novel approach called BP with Two-Phase Magnified Gradient Function (2P-MGFPROP) was introduced to overcome the error overshooting problem and hence speed up the convergence rate of MGFPROP. In this paper, this approach is further enhanced by proposing to divide the learning process into multiple phases, and different fast learning algorithms are assigned in different phases to improve the convergence rate in different adaptive problems. Through the performance investigation, it is found that the convergence rate can be increased up to two times, compared with existing fast learning algorithms.
This paper mainly introduces machine learning algorithms in the field of artificial intelligence. First, it describes the classification of such algorithms and their main application scenarios. Then the paper introduc...
详细信息
This paper mainly introduces machine learning algorithms in the field of artificial intelligence. First, it describes the classification of such algorithms and their main application scenarios. Then the paper introduces the principles behind those algorithms and presents the author's views. Finally, the development trend of machine learning algorithms is envisioned.
In this paper, we investigate and systematically evaluate two machine learning algorithms for analog fault detection and isolation: (1) Restricted Coloumb Energy (RCE) Neural Network, and (2) learning Vector Quantizat...
详细信息
ISBN:
(纸本)0780347781
In this paper, we investigate and systematically evaluate two machine learning algorithms for analog fault detection and isolation: (1) Restricted Coloumb Energy (RCE) Neural Network, and (2) learning Vector Quantization (LVQ). The RCE and LVQ models excel at recognition and classification types of problems. In order to evaluate the efficacy of the two learning algorithms, we have developed a software tool, termed Virtual Test-Bench (VTB), which generates diagnostic information for analog circuits represented by SPICE descriptions. The RCE and LVQ models render themselves more naturally to on-line monitoring, where measurement data from various sensors is continuously available. The effectiveness of RCE and LVQ is demonstrated on illustrative example circuits.
Reinforcement learning (RL) is a learning technique that learns an optimal policy in case of knowing almost nothing about the dynamics of the environment under consideration. When RL is combined with function approxim...
详细信息
ISBN:
(纸本)9781424409907
Reinforcement learning (RL) is a learning technique that learns an optimal policy in case of knowing almost nothing about the dynamics of the environment under consideration. When RL is combined with function approximation schemes, the learning performance is greatly influenced by RL algorithms and learning parameters. This paper proposes a new on-line multiple learning and aggregating architecture, "Aggregated Multiple Reinforcement learning System (AMRLS)". Instead of searching for the optimal learning parameters or featurization schemes, AMRLS attempts to aggregate the outcomes of different learners to produce a better policy. This architecture is tested on the mountain car problem with the aggregation of several related tiling and learning parameters. Experimental results show that AMRLS can improve the learning performance over the use of a single RL algorithm.
Cryptographic chips have been widely used in the field of digital security. With the continuous development of side-channel attacks, the security of cryptographic chips has attracted more and more attention. This pape...
详细信息
Cryptographic chips have been widely used in the field of digital security. With the continuous development of side-channel attacks, the security of cryptographic chips has attracted more and more attention. This paper mainly reviews the most distinguishing template attacks in current side-channel attacks, introduces the basic steps of template attack implementation, analyzes and discusses the existing template attacks, and finally focuses on the research progress of template attacks, especially the current the research status of template attacks based on machine learning and deep learning algorithms lays the foundation for further research.
Construction tasks involve various activities composed of one or more body motions. It is essential to understand the dynamically changing behavior and state of construction workers to manage construction workers effe...
详细信息
ISBN:
(纸本)9780784482438
Construction tasks involve various activities composed of one or more body motions. It is essential to understand the dynamically changing behavior and state of construction workers to manage construction workers effectively with regards to their safety and productivity. While several research efforts have shown promising results in activity recognition, further research is still necessary to identify the best locations of motion sensors on a worker's body by analyzing the recognition results for improving the performance and reducing the implementation cost. This study proposes a simulation-based evaluation of multiple motion sensors attached to workers performing typical construction tasks. A set of 17 inertial measurement unit (IMU) sensors is utilized to collect motion sensor data from an entire body. Multiple machine learning algorithms are utilized to classify the motions of the workers by simulating several scenarios with different combinations and features of the sensors. Through the simulations, each IMU sensor placed in different locations of a body is tested to evaluate its recognition accuracy toward the worker's different activity types. Then, the effectiveness of sensor locations is measured regarding activity recognition performance to determine relative advantage of each location. Based on the results, the required number of sensors can be reduced maintaining the recognition performance. The findings of this study can contribute to the practical implementation of activity recognition using simple motion sensors to enhance the safety and productivity of individual workers.
Can learning algorithms find a Nash equilibrium? This is a natural question for several reasons. learning algorithms resemble the behavior of players in many naturally arising games, and thus results on the convergenc...
详细信息
ISBN:
(纸本)9783642161698
Can learning algorithms find a Nash equilibrium? This is a natural question for several reasons. learning algorithms resemble the behavior of players in many naturally arising games, and thus results on the convergence or non-convergence properties of such dynamics may inform our understanding of the applicability of Nash equilibria as a plausible solution concept in some settings. A second reason for asking this question is in the hope of being able to prove an impossibility result, not dependent on complexity assumptions, for computing Nash equilibria via a restricted class of reasonable algorithms. In this work, we begin to answer this question by considering the dynamics of the standard multiplicative weights update learning algorithms (which are known to converge to a Nash equilibrium for zero-sum games). We revisit a 3 x 3 game defined by Shapley [10] in the 1950s in order to establish that fictitious play does not converge in general games. For this simple game, we show via a potential function argument that in a variety of settings the multiplicative updates algorithm impressively fails to find the unique Nash equilibrium, in that the cumulative distributions of players produced by learning dynamics actually drift away from the equilibrium.
An absorbing learning automaton which is based on the use of a stochastic estimator is introduced. According to the proposed stochastic estimator scheme, the estimates of the reward probabilities are computed stochast...
详细信息
ISBN:
(纸本)0769511651
An absorbing learning automaton which is based on the use of a stochastic estimator is introduced. According to the proposed stochastic estimator scheme, the estimates of the reward probabilities are computed stochastically. Actions that have not been selected many times have the opportunity to be estimated as optimal, to increase their choice probabilities, and consequently, to be selected. In this way, the automaton's accuracy is significantly improved. This proposed automaton is proven to be absolutely expedient in all stationary environments, while the simulation results demonstrate that the proposed scheme achieves a significantly higher performance in comparison with the deterministic estimator based schemes.
Expert based learning algorithms have been used by robots to choose satisfying reactions to human movements. These algorithms often demonstrate random performance that tries to hit a balance between adaptiveness and c...
详细信息
ISBN:
(纸本)9781509059928
Expert based learning algorithms have been used by robots to choose satisfying reactions to human movements. These algorithms often demonstrate random performance that tries to hit a balance between adaptiveness and consistency that matches human's preferences intuitively. This paper provides a rigorous way to quantify the adaptiveness and consistency of the expert based learning algorithms in the context of human robot interaction. It is discovered that a Markov chain model can be used to allow the analysis of both adaptiveness and consistency for several popular expert based learning algorithms. Success of the method has been seen in both simulation and experimental work.
暂无评论