E.B. Baum. Towards practical 'neural' computation for combinatorial optimization problems. In Denker, J., editor, Proceedings of the AIP Conference 151: Neural Networks for Computing, pages 53--58, Snowbird, UT, 1986. American Institute of Physics, New York, NY. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Using Bayesian networks for incorporating probabilistic a priori .. - Myllymäki (1994) (Correct)
....for incorporating probabilistic a priori information into a neural network architecture, which can then be trained further with existing learning algorithms. I. Introduction Neural network models have been suggested as a massively parallel platform for solving (NP )hard problems approximatively [10, 2]. Especially suitable for this task seems to be the Boltzmann machine neural network architecture [8, 9] as this model is based on a stochastic energy minimization process similar to the famous Gibbs sampling method [14] So far, the Boltzmann machine network structure corresponding to a ....
Baum, E.B., Towards practical 'neural' computation for combinatorial optimization problems. Pp. 53--58 in Proceedings of the AIP Conference 151: Neural Networks for Computing (Snowbird, UT, 1986.
Applying Iterated Local Search to the Permutation Flow Shop Problem - Stützle (1998) (1 citation) (Correct)
....the global optimum. Yet, the strength of this bias may be crucial for the performance of the ILS 3 algorithm. 2.2 Iterated local search applications Like in many metaheuristic algorithms, the first application of an ILS algorithm has been proposed for the TSP. A first application is reported in [2], yet the obtained results were not very convincing due to a poor choice for Modify and LocalSearch. A major improvement in the development of ILS algorithms came from the Large Step Markov Chain (LSMC) algorithm for the TSP proposed by Martin, Otto, and Felten [23] The term Large Step Markov ....
E.B. Baum. Towards Practical 'Neural' Computation for Combinatorial Optimization Problems. In Neural Networks for Computing, AIP Conference Proceedings, pages 53--64, 1986.
Using Bayesian networks for incorporating probabilistic a priori .. - Myllymäki (1994) (Correct)
....for incorporating probabilistic a priori information into a neural network architecture, which can then be trained further with existing learning algorithms. I. Introduction Neural network models have been suggested as a massively parallel platform for solving (NP )hard problems approximatively [10, 2]. Especially suitable for this task seems to be the Boltzmann machine neural network architecture [8, 9] as this model is based on a stochastic energy minimization process similar to the famous Gibbs sampling method [14] So far, the Boltzmann machine network structure corresponding to a ....
Baum, E.B., Towards practical 'neural' computation for combinatorial optimization problems. Pp. 53--58 in Proceedings of the AIP Conference 151: Neural Networks for Computing (Snowbird, UT, 1986), edited by J.Denker. American Institute of Physics, New York, NY, 1986.
Massively Parallel Probabilistic Reasoning with Boltzmann Machines - Myllymäki (1999) (Correct)
.... of neural models, see e.g. the classic collections [1 4] These models can perform certain computational tasks extremely fast when run on customized parallel hardware, and hence they have been suggested as a computationally efficient tool for solving NP hard optimization problems approximatively [5,6]. Especially suitable for this type of tasks are stochastic neural network architectures, as these models are based on a stochastic updating process which converges to a state maximizing an objective function determined by the variable states of the binary nodes of the network, and by the ....
E.B. Baum. Towards practical 'neural' computation for combinatorial optimization problems. In Denker, J., editor, Proceedings of the AIP Conference 151: Neural Networks for Computing, pages 53--58, Snowbird, UT, 1986. American Institute of Physics, New York, NY.
Applied Intelligence, 11, 31--44 (1999) - Massively Parallel Probabilistic (Correct)
No context found.
E.B. Baum. Towards practical 'neural' computation for combinatorial optimization problems. In Denker, J., editor, Proceedings of the AIP Conference 151: Neural Networks for Computing, pages 53--58, Snowbird, UT, 1986. American Institute of Physics, New York, NY.
Massively Parallel Probabilistic Reasoning with Boltzmann Machines - MyllymÄki (1999) (Correct)
No context found.
E.B. Baum. Towards practical 'neural' computation for combinatorial optimization problems. In Denker, J., editor, Proceedings of the AIP Conference 151: Neural Networks for Computing, pages 53--58, Snowbird, UT, 1986. American Institute of Physics, New York, NY.
.00 15.00 20.00 25.00 30.00 35.00 40.00 45.00 50.00 55.00.. - Ave Distance (Correct)
No context found.
E. B. Baum, "Towards Practical `Neural' Computation for Combinatorial Optimization Problems", in J. Denker, ed., Neural Networks for Computing, American Institute of Physics, 1986.
Heuristic Solution of the Multisource Weber Problem as .. - Hansen, Mladenovic.. (1996) (Correct)
No context found.
Baum, E.B. 1986. Toward practical 'neural' computation for combinatorial optimization problems. In J. Denker (Eds.), Neural networks for computing, American Institute of Physics.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC