Personal information

Activities

Collapse all

Works (15)

A tutorial on the art of dynamic programming for some issues concerning Bellman’s principle of optimality

ICT Express
2023-12 | Journal article
DOI: 10.1016/j.icte.2023.07.001
Contributors: Eiji Mizutani; Stuart Dreyfus
Source: check_circle
Crossref

A note on a single-shift days-off scheduling problem with sequence-dependent labor costs

Journal of Scheduling
2023-06 | Journal article
DOI: 10.1007/s10951-022-00749-3
Contributors: Eiji Mizutani; Kevin Alexander Sánchez Galeano
Source: check_circle
Crossref

A Proof on Equivalence of Stagewise Newton and Dreyfus's Successive Approximation Procedures

IEEE Transactions on Automatic Control
2020-06 | Journal article
DOI: 10.1109/TAC.2019.2944921
Contributors: Eiji Mizutani
Source: check_circle
Crossref

A Note on Liao’s Recurrent Neural-Network Learning for Discrete Multi-stage Optimal Control Problems

Neural Processing Letters
2019-12-29 | Journal article
DOI: 10.1007/s11063-019-09986-8
Contributors: Eiji Mizutani
Source: check_circle
Crossref

Totally model-free actor-critic recurrent neural-network reinforcement learning in non-Markovian domains

Annals of Operations Research
2017-11 | Journal article
DOI: 10.1007/s10479-016-2366-2
Part of ISSN: 0254-5330
Part of ISSN: 1572-9338
Contributors: Eiji Mizutani; Stuart Dreyfus
Source: Self-asserted source
Eiji Mizutani

On Pantoja's problem allegedly showing a distinction between differential dynamic programming and stagewise Newton methods

International Journal of Control
2015-09-02 | Journal article
DOI: 10.1080/00207179.2015.1013063
Part of ISSN: 0020-7179
Part of ISSN: 1366-5820
Contributors: E. Mizutani
Source: Self-asserted source
Eiji Mizutani

On improving trust-region variable projection algorithms for separable nonlinear least squares learning

The 2011 International Joint Conference on Neural Networks
2011-07 | Conference paper
DOI: 10.1109/ijcnn.2011.6033249
Contributors: Eiji Mizutani; James Demmel
Source: Self-asserted source
Eiji Mizutani

An analysis on negative curvature induced by singularity in multi-layer neural-network learning

Advances in Neural Information Processing Systems 23 (NIPS 2010)
2010-12 | Conference paper
Contributors: Eiji Mizutani; James Demmel
Source: Self-asserted source
Eiji Mizutani

Stage-lookahead dynamic programming algorithms for stochastic problems with time-lagged control dynamics

2009 IEEE International Conference on Industrial Engineering and Engineering Management
2009-12 | Conference paper
DOI: 10.1109/ieem.2009.5373354
Contributors: Eiji Mizutani; Stuart Dreyfus
Source: Self-asserted source
Eiji Mizutani

Second-order stagewise backpropagation for Hessian-matrix analyses and investigation of negative curvature

Neural Networks
2008-03 | Journal article
DOI: 10.1016/j.neunet.2007.12.038
Part of ISSN: 0893-6080
Contributors: Eiji Mizutani; Stuart E. Dreyfus
Source: Self-asserted source
Eiji Mizutani

Iterative Scaled Trust-Region Learning in Krylov Subspaces via Pearlmutter's Implicit Sparse Hessian-Vector Multiply

Advances in Neural Information Processing Systems 16 (NIPS 2003)
2003-12 | Conference paper
Contributors: Eiji Mizutani; James W. Demmel
Source: Self-asserted source
Eiji Mizutani

On structure-exploiting trust-region regularized nonlinear least squares algorithms for neural-network learning

Neural Networks
2003-06 | Journal article
DOI: 10.1016/s0893-6080(03)00085-6
Part of ISSN: 0893-6080
Contributors: Eiji Mizutani; James W. Demmel
Source: Self-asserted source
Eiji Mizutani

Multi-illuminant color reproduction for electronic cameras via CANFIS neuro-fuzzy modular network device characterization

IEEE Transactions on Neural Networks
2002-07 | Journal article
DOI: 10.1109/tnn.2002.1021900
Part of ISSN: 1045-9227
Contributors: E. Mizutani; K. Nishio
Source: Self-asserted source
Eiji Mizutani

On derivation of MLP backpropagation from the Kelley-Bryson optimal-control gradient formula and its application

Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium
2000 | Conference paper
DOI: 10.1109/ijcnn.2000.857892
Contributors: E. Mizutani; S.E. Dreyfus; K. Nishio
Source: Self-asserted source
Eiji Mizutani

On Iterative Krylov-Dogleg Trust-Region Steps for Solving Neural Networks Nonlinear Least Squares Problems

Advances in Neural Information Processing Systems 13 (NIPS 2000)
2000-12 | Conference paper
Contributors: Eiji Mizutani; James Demmel
Source: Self-asserted source
Eiji Mizutani
How many people are using ORCID?