Graphs denote useful dependencies among objects ubiquitously. This paper introduces new and simple bijections to the integer grid to enable the succinct, canonical and efficient representations of labeled graphs;where...
详细信息
ISBN:
(纸本)9781479938407
Graphs denote useful dependencies among objects ubiquitously. This paper introduces new and simple bijections to the integer grid to enable the succinct, canonical and efficient representations of labeled graphs;whereas previous work has focused on regularities in structure such as triangularity, separability, planarity, symmetry and sparsity. By succinct we imply that space is information-theoretically optimal, by canonical we imply that generation of instances is unique, and by efficient we imply that coding and decoding take polynomial time. Our results have direct implications to handle labeled graphs by using single numbers efficiently, which is significant to enable the canonical graph encodings in learning and optimization algorithms. Our bijections are the first known in the literature.
Enabling accurate and low-cost classification of a range of motion activities is of significant importance for wireless health through body worn inertial sensors and smartphones, due to the need by healthcare and fitn...
详细信息
ISBN:
(纸本)9781479935130
Enabling accurate and low-cost classification of a range of motion activities is of significant importance for wireless health through body worn inertial sensors and smartphones, due to the need by healthcare and fitness professonals to monitor exercises for quality and compliance. This paper proposes a novel contextual multi-armed bandits approach for large-scale activity classification. The proposed method is able to address the unique challenges arising from scaling, lack of training data and adaptation by melding context augmentation and continuous online learning into traditional activity classification. We rigorously characterize the performance of the proposed learning algorithm and prove that the learning regret (i.e. reward loss) is sublinear in time, thereby ensuring fast convergence to the optimal reward as well as providing short-term performance guarantees. Our experiments show that the proposed algorithm outperforms existing algorithms in terms of both providing higher classification accuracy as well as lower energy consumption.
This paper studies a property of neural network architecture for non-linear modeling. This method was proposed in our previous work and has three improvements;1) the design of a sigmoidal function with localized deriv...
详细信息
ISBN:
(纸本)4907764227
This paper studies a property of neural network architecture for non-linear modeling. This method was proposed in our previous work and has three improvements;1) the design of a sigmoidal function with localized derivative, 2) a deterministic scheme for weight initialization, and 3) an updating rule for weight parameters. We discuss its robustness against noise based on simulation results.
Two principles of neurocomputational design are implemented into an autonomous real-world device, such as a helicopter. The helicopter has a motivational component towards emitting motor responses in a manner similar ...
详细信息
In this paper, we analyze an existing Quantum Perceptron in terms of its generalization performance and introduce alternative strategies to avoid classification errors, the Circuit Threshold Operator (CTO) and Neuron ...
详细信息
ISBN:
(纸本)9781728169262
In this paper, we analyze an existing Quantum Perceptron in terms of its generalization performance and introduce alternative strategies to avoid classification errors, the Circuit Threshold Operator (CTO) and Neuron Threshold Variation (NTV). The adjust of the CTO and NTV parameters increases the probability of the neuron to tolerate differences between input and stored weights allowing some noise level to be acceptable. Experiments were conducted in IBM quantum simulator, showing that our proposals are effective when compared to the original fixed parameter. A hybrid classical-quantum training was executed, using Genetic algorithm to train the parameters of the model classically and running our model in a quantum simulator. Our solution achieves 78.57% and 76.43% of accuracy on a noisy dataset, while the original neuron approach does not exceed 53.57%.
In general, there is small perturbation between a pattern obtained by a certain acquisition way and the corresponding actual pattern in real word. Such small perturbation may cause disadvantage to several performance ...
详细信息
ISBN:
(纸本)9780769533827
In general, there is small perturbation between a pattern obtained by a certain acquisition way and the corresponding actual pattern in real word. Such small perturbation may cause disadvantage to several performance of a fuzzy neural network. Thus, a new concept is established in the paper that the robustness of a feed-forward fuzzy associative memory to perturbations of training pattern pair. Then for a Max-product-based fuzzy associative memory (Max-Product FAM), the investigation reveal that such robustness of the memory is good when the fuzzy Hebbian learning algorithm is used, however is poor when another learning algorithm is employed. Finally, an experiment is given to testify the theoretical conclusion and illustrate practical application of Max-product FAM.
Functional verification is the bottleneck in delivering today's highly integrated electronic systems and chips. We should notice the simulation times and computation resource challenge in the automatic pseudo-rand...
详细信息
ISBN:
(纸本)0780387368
Functional verification is the bottleneck in delivering today's highly integrated electronic systems and chips. We should notice the simulation times and computation resource challenge in the automatic pseudo-random test generation and a novel solution named Priority Directed test Generation (PDG) is proposed in this paper. With PDG, a test vector which hasn't been simulated is granted a priority attribute. The priority indicates the possibility of detecting new bugs by simulating this vector. We show how to apply Artificial Neural Networks (ANNs) learning algorithm to the PDG problem. Several experiments are given to exhibit how to achieve better result in this PDG method.
One of the fundamental problems in wireless sensor networks is providing area coverage to fulfill a certain task. This problem in directional sensor networks is more challenging because of limited sensing angle of dir...
详细信息
ISBN:
(纸本)9781509034352
One of the fundamental problems in wireless sensor networks is providing area coverage to fulfill a certain task. This problem in directional sensor networks is more challenging because of limited sensing angle of directional sensors. This paper addresses the problem of deployment and orientation of a specific number of directional sensor nodes in order to maximize the area coverage. First, we present an optimization model for this problem. Then, we propose a distributed payoff based learning algorithm in which each sensor tries to maximize its own coverage relative to the coverage of its neighbors by relocating toward uncovered positions and selecting an appropriate working direction. Simulation results demonstrate the performance of proposed algorithm.
The Fuzzy Cognitive Map (FCM) has emerged as a convenient and powerful soft modeling tool since its proposal. During the last nearly 30 years, Fuzzy Cognitive Maps have gained considerable research interests and have ...
详细信息
ISBN:
(纸本)9783319220536;9783319220529
The Fuzzy Cognitive Map (FCM) has emerged as a convenient and powerful soft modeling tool since its proposal. During the last nearly 30 years, Fuzzy Cognitive Maps have gained considerable research interests and have been applied to many areas. The advantageous modeling characteristics of FCMs encourage us to investigate the FCM structure, attempting to broaden the FCM functionality and applicability in real world. In this paper, the main representation and inference characteristics of conventional Fuzzy Cognitive Maps are investigated, and also the current state of the extensions of FCMs, learning algorithms for FCMs is introduced and summarized briefly.
The purpose of this paper is to provide a path for designing a tool for decision support to ensure the effectiveness of Quality Management System (QMS). For this, we propose a Fuzzy-Neural Networks (FNN) approach for ...
详细信息
ISBN:
(纸本)9781467307840
The purpose of this paper is to provide a path for designing a tool for decision support to ensure the effectiveness of Quality Management System (QMS). For this, we propose a Fuzzy-Neural Networks (FNN) approach for improving the efficiency of such system. The aim of this approach is to classify the objectives for a real-world case study which presents a major problem for controlling the quality levels of its production lines. This approach provided a significant improvement when the testing data are various or complex.
暂无评论