The Experts below are selected from a list of 3123 Experts worldwide ranked by ideXlab platform

Jose C Principe - One of the best experts on this subject based on the ideXlab platform.

  • An Analysis of the Value of Information When Exploring Stochastic, Discrete Multi-Armed Bandits
    Entropy, 2018
    Co-Authors: Isaac J. Sledge, Jose C Principe
    Abstract:

    In this paper, we propose an information-theoretic exploration strategy for stochastic, discrete multi-armed bandits that achieves optimal regret. Our strategy is based on the value of information criterion. This criterion measures the trade-off between policy information and obtainable rewards. High amounts of policy information are associated with exploration-dominant searches of the space and yield high rewards. Low amounts of policy information favor the exploitation of existing knowledge. Information, in this criterion, is quantified by a parameter that can be varied during search. We demonstrate that a simulated-annealing-like update of this parameter, with a sufficiently fast Cooling Schedule, leads to a regret that is logarithmic with respect to the number of arm pulls.

  • Using the Value of Information to Explore Stochastic, Discrete Multi-Armed Bandits
    arXiv:1710.02869 [cs stat], 2017
    Co-Authors: Isaac J. Sledge, Jose C Principe
    Abstract:

    In this paper, we propose an information-theoretic exploration strategy for stochastic, discrete multi-armed bandits that achieves optimal regret. Our strategy is based on the value of information criterion. This criterion measures the trade-off between policy information and obtainable rewards. High amounts of policy information are associated with exploration-dominant searches of the space and yield high rewards. Low amounts of policy information favor the exploitation of existing knowledge. Information, in this criterion, is quantified by a parameter that can be varied during search. We demonstrate that a simulated-annealing-like update of this parameter, with a sufficiently fast Cooling Schedule, leads to an optimal regret that is logarithmic with respect to the number of episodes.

Herbert H. Tsang - One of the best experts on this subject based on the ideXlab platform.

  • CEC - Examination of Annealing Schedules for RNA Design
    2020 IEEE Congress on Evolutionary Computation (CEC), 2020
    Co-Authors: Ryan Mcbride, Herbert H. Tsang
    Abstract:

    Computational Intelligence is frequently applied to solve RNA design problems, to construct RNA sequences that fold into biochemically useful structures and alignments. RNA Design’s NP-Hardness means that heuristic solutions, such as Evolutionary algorithms’ Simulated Annealing, are commonly used to more effectively search for RNA sequences that fold into the target structure. Examples of Simulated Annealing in RNA Design include SIMARD, the ERD approach, and RNAPredict, all which aim to return RNA Sequences as close as possible to the target structure. However, such methods only use a single simulated annealing Cooling Schedule even though literature covers many Schedules with varied convergence and performances guarantees. Since existing RNA Design Cooling Schedule surveys only cover at most four RNA design problems over two simulated annealing variants, we investigate the performance of four major simulated annealing Schedules with ten variants on twenty-nine RNA design sequences. Relevant findings include a) the insensitivity of geometric Schedule parameters, b) that logarithmic Cooling Schedules can solve RNA Design problems not solved by other Schedules, c) suggestions for adjusting geometric Schedule stopping conditions, and d) identifying common issues in popular adaptive and non-adaptive Schedules for RNA Design.

  • CEC - Examining the annealing Schedules for RNA design algorithm
    2016 IEEE Congress on Evolutionary Computation (CEC), 2016
    Co-Authors: Halid Emre Erhan, Sinem Sav, Stas Kalashnikov, Herbert H. Tsang
    Abstract:

    RNA structures are important for many biological processes in the cell. One important function of RNA are as catalytic elements. Ribozymes are RNA sequences that fold to form active structures that catalyze important chemical reactions. The folded structure for these RNA are very important; only specific conformations maintain these active structures, so it is very important for RNA to fold in a specific way. The RNA design problem describes the prediction of an RNA sequence that will fold into a given RNA structure. Solving this problem allows researchers to design RNA; they can decide on what folded secondary structure is required to accomplish a task, and the algorithm will give them a primary sequence to assemble. However, there are far too many possible primary sequence combinations to test sequentially to see if they would fold into the structure. Therefore we must employ heuristics algorithms to attempt to solve this problem. This paper introduces SIMARD, an evolutionary algorithm that uses an optimization technique called simulated annealing to solve the RNA design problem. We analyzes three different Cooling Schedules for the annealing process: 1) An adaptive Cooling Schedule, 2) a geometric Cooling Schedule, and 3) a geometric Cooling Schedule with warm up. Our results show that an adaptive annealing Schedule may not be more effective at minimizing the Hamming distance between the target structure and our folded sequence's structure when compared with geometric Schedules. The results also show that warming up in a geometric Cooling Schedule may be useful for optimizing SIMARD.

Nen-fu Huang - One of the best experts on this subject based on the ideXlab platform.

  • The shortest path computation in MOSPF protocol using an annealed Hopfield neural network with a new Cooling Schedule
    Information Sciences, 2000
    Co-Authors: Jzau-sheng Lin, Mingshou Liu, Nen-fu Huang
    Abstract:

    Abstract Many network services, such as video conferencing and video on demand, have popularly used the multimedia communications. The attached hosts/routers are required to transmit data as multicasting in most multimedia applications. In order to provide an efficient data routing, routers must provide multicast capability. In this paper, a new Cooling Schedule in Hopfield neural network with annealing strategy is proposed to calculate the shortest path (SP) tree for multicast open shortest path first (MOSPF) protocol. The SP tree in multicast is built on demand and is rooted at the source node. To facilitate the hardware implementation, the annealed Hopfield neural network could be a good candidate to deal with SP problems in packet switching computer networks. In addition, it is proved that the proposed new Cooling Schedule is more suitable in all range of fixed temperature than the other demonstrated Cooling Schedules in the experimental results.

  • The shortest path computation in MOSPF protocol using an annealed Hopfield neural network with a new Cooling Schedule
    Information Sciences, 2000
    Co-Authors: Jzau-sheng Lin, Mingshou Liu, Nen-fu Huang
    Abstract:

    [[abstract]]Many network services, such as video conferencing and video on demand, have popularly used the multimedia communications. The attached hosts/routers are required to transmit data as multicasting in most multimedia applications. In order to provide an efficient data routing, routers must provide multicast capability. In this paper, a new Cooling Schedule in Hopfield neural network with annealing strategy is proposed to calculate the shortest path (SP) tree for multicast open shortest path first (MOSPF) protocol. The SP tree in multicast is built on demand and is rooted at the source node. To facilitate the hardware implementation, the annealed Hopfield neural network could be a good candidate to deal with SP problems in packet switching computer networks. In addition, it is proved that the proposed new Cooling Schedule is more suitable in all range of fixed temperature than the other demonstrated Cooling Schedules in the experimental results.[[fileno]]2030210030057[[department]]資訊工程學

Aya Hagishima - One of the best experts on this subject based on the ideXlab platform.

  • State transition stochastic model for predicting off to on Cooling Schedule in dwellings as implemented using a multilayered artificial neural network
    Journal of Building Performance Simulation, 2012
    Co-Authors: Jun Tanimoto, Aya Hagishima
    Abstract:

    Our previous study (Tanimoto, J. and Hagishima, A. 2005. State transition probability for the Markov model dealing with on/off Cooling Schedule in dwellings. Energy and Buildings, 37, 181–187) proposed a set of state transition probabilities for the Markov chain dealing with the on/off Cooling Schedule in dwellings. The probability of turning on an air conditioner was defined in the form of a sigmoid function by the indoor globe temperature. Obviously, a real stochastic event of shifting from the off to on state is affected by not only indoor thermal quality parameters but also by other complex factors, such as the presence of family members, time of the day and whether it is a weekday or holiday. In this article, we report an alternate model, based on a multilayered artificial neural network (MANN), for predicting the off to on Cooling Schedule. We gathered field measurement data on family dwellings during the summer of 2008 by deploying hygrothermometers with recording functions to measure the room temp...

  • a stochastic model to predict off on Cooling Schedule in dwellings applied by multilayered neural network
    Journal of Environmental Engineering (transactions of Aij), 2009
    Co-Authors: Jun Tanimoto, Aya Hagishima
    Abstract:

    In our previous study (Tanimoto & Hagishima (2005), Energy and Buildings 37), a set of state transition probabilities for the Markov Chain dealing with on/ off Cooling Schedule in dwellings was proposed. Obtained probability of turning on an air conditioning system was defined in a form of Sigmoid-function by indoor globe temperature. Obviously, a real stochastic event of shifting from the off to on state cannot be affected by only indoor environmental parameters but also by other complex factors such as presence probability of family members, time, either weekday or holiday etc. In this paper, we report an alternative model based on the Multilayered Neural Network to predict off/ on Cooling Schedule. We gathered field measurement data on familial dwellings during summer 2008 by deploying handy type hygrothermal meters with self-recording functions to measure room air, globe and blow-off air temperature of an air conditioner. The assumed Multilayered Neural Network has 9 nodes in both input and hidden layers, and 1 single node in output layer implying either state shifting from off to on (1) or not (0). The information given to the input layer nodes consists of what time, whether weekday of holiday, presence probability of inhabitants and PPD (Predicted Percentage of Dissatisfied). PPD derived from the theory of PMV is applied as a representative parameter for the indoor environment instead of globe temperature, since it contains various influences. The field measurement data sets were divided into two parts: teaching data and data for validation. The model trained by the teaching data was confirmed to reproduce state transition characteristic of the validation period, which seems complex and is determined by various inhabitants' manners. The model performance to reproduce is observed much excellent than the previous model derived from the Markov Chain.

  • State transition probability for the Markov Model dealing with on/off Cooling Schedule in dwellings
    Energy and Buildings, 2005
    Co-Authors: Jun Tanimoto, Aya Hagishima
    Abstract:

    We gathered field measurement data on five familial and three single dwellings during summer 2000 by deploying numerous handy type hygrothermal meters with self-recording functions to measure room air, globe and outdoor air temperatures. These measurements led to conclusions on the probability of turning on an air conditioning system versus indoor globe temperature and the ongoing probability of air conditioning versus outdoor temperature. This analysis was transformed into state transition probability functions, i.e. shifting from the off to on state and from the on to off state. Identifying these state transition probability functions is an important first step in applying the Markov Model to on/off state analysis for air conditioning systems, which is one of the significant approaches for dealing with the stochastic thermal load for HVAC system. The obtained state transition probability functions should help immeasurably in determining effective Schedules for air conditioning operation from inhabitant occupancy Schedules.

Jzau-sheng Lin - One of the best experts on this subject based on the ideXlab platform.

  • Fuzzy Artificial Bee Colony System with Cooling Schedule for the Segmentation of Medical Images by Using of Spatial Information
    Research Journal of Applied Sciences Engineering and Technology, 2013
    Co-Authors: Jzau-sheng Lin
    Abstract:

    In this study, segmentation of medical images using a fuzzy artificial bee colony algorithm with a Cooling Schedule is created. In this study, we embed ed fuzzy inference strategy into the artificial bee colony system to construct a segmentation system named Fuzzy Artificial Bee Colony System (FABCS). A conventional FCM algorithm did not utilize the spatial information in the image. We set a local circular area with a variable radius by using a Cooling Schedule for each bee to search suitable cluster centers with the FCM algorithm in an image. The cluster centers can be calculated by each bee with the membership states in the FABCS and then updated iteratively for all bees in order to find near-global solution in MR image segmentation. The proposed FABCS found the cluster centers with local spatial information in stead of global pixels' intensities. In the simulation and real medical-image segmentation results, the proposed FABCS network can reserve the segmentation performance.

  • Segmentation of multispectral MR images through an annealed rough neural network
    Neural Computing and Applications, 2011
    Co-Authors: Yi-ying Chang, Shen-chuan Tai, Jzau-sheng Lin
    Abstract:

    In this paper, multispectral image segmentation using a rough neural network based on an annealed strategy with a Cooling Schedule is created. The main purpose is to embed an annealed Cooling Schedule into the rough neural network to construct a segmentation system named annealed rough neural net (ARNN). The classification system is a paradigm for the implementation of annealed reasoning and rough systems in neural network architecture. Instead of all the information in the image are fed into the neural network, the upper- and lower-bound gray level, captured from a training vector in a multispectral image, were fed into a rough neuron in the ARNN. Therefore, only 2-channel images are selected as the training samples if an N-dimensional multispectral image was used. In the simulation results, the proposed network not only reduces the consuming time but also reserves the classification performance.

  • The shortest path computation in MOSPF protocol using an annealed Hopfield neural network with a new Cooling Schedule
    Information Sciences, 2000
    Co-Authors: Jzau-sheng Lin, Mingshou Liu, Nen-fu Huang
    Abstract:

    Abstract Many network services, such as video conferencing and video on demand, have popularly used the multimedia communications. The attached hosts/routers are required to transmit data as multicasting in most multimedia applications. In order to provide an efficient data routing, routers must provide multicast capability. In this paper, a new Cooling Schedule in Hopfield neural network with annealing strategy is proposed to calculate the shortest path (SP) tree for multicast open shortest path first (MOSPF) protocol. The SP tree in multicast is built on demand and is rooted at the source node. To facilitate the hardware implementation, the annealed Hopfield neural network could be a good candidate to deal with SP problems in packet switching computer networks. In addition, it is proved that the proposed new Cooling Schedule is more suitable in all range of fixed temperature than the other demonstrated Cooling Schedules in the experimental results.

  • The shortest path computation in MOSPF protocol using an annealed Hopfield neural network with a new Cooling Schedule
    Information Sciences, 2000
    Co-Authors: Jzau-sheng Lin, Mingshou Liu, Nen-fu Huang
    Abstract:

    [[abstract]]Many network services, such as video conferencing and video on demand, have popularly used the multimedia communications. The attached hosts/routers are required to transmit data as multicasting in most multimedia applications. In order to provide an efficient data routing, routers must provide multicast capability. In this paper, a new Cooling Schedule in Hopfield neural network with annealing strategy is proposed to calculate the shortest path (SP) tree for multicast open shortest path first (MOSPF) protocol. The SP tree in multicast is built on demand and is rooted at the source node. To facilitate the hardware implementation, the annealed Hopfield neural network could be a good candidate to deal with SP problems in packet switching computer networks. In addition, it is proved that the proposed new Cooling Schedule is more suitable in all range of fixed temperature than the other demonstrated Cooling Schedules in the experimental results.[[fileno]]2030210030057[[department]]資訊工程學