• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Learning of a sparse code by a constrained optimization

Research Project

Project/Area Number 19700219
Research Category

Grant-in-Aid for Young Scientists (B)

Allocation TypeSingle-year Grants
Research Field Sensitivity informatics/Soft computing
Research InstitutionKyoto University (2008-2009)
Nara Institute of Science and Technology (2007)

Principal Investigator

SHIN-ICHI Maeda  Kyoto University, 情報学研究科, 助教 (20379530)

Project Period (FY) 2007 – 2009
Project Status Completed (Fiscal Year 2009)
Budget Amount *help
¥2,600,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥300,000)
Fiscal Year 2009: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2008: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2007: ¥1,300,000 (Direct Cost: ¥1,300,000)
Keywords階層ニューラルネットワーク / Contrastive Divergence Learning / 制約付き最適化 / EMアルゴリズム / スパースコーディング / 階層型モデル / 特徴抽出 / contrastive divergence / ニューラルネットワーク / ボルツマンマシン / autoencoder / pretraining / 自由エネルギー最小化 / companding function
Research Abstract

Hinton et al. (2006) showed that the performance of hierarchical neural networks couldbe greatly improved by an innovation of the learning algorithm and training with a largeamount of data. In this research project, I aim to clear up the causes which enable anefficient learning. As the results, I've succeeded to clearly show the reason why thelearning by EM algorithm freezes in some cases, generalize contrastive divergencelearning which was used in the training of the hierarchical neural networks and newlyderive the convergence condition of the algorithm. We also successfully demonstrated thatan efficient coding of natural images can be obtained by the learning based on aconstrained optimization.

Report

(4 results)
  • 2009 Annual Research Report   Final Research Report ( PDF )
  • 2008 Annual Research Report
  • 2007 Annual Research Report
  • Research Products

    (20 results)

All 2010 2009 2008 2007 Other

All Journal Article (3 results) (of which Peer Reviewed: 3 results) Presentation (16 results) Remarks (1 results)

  • [Journal Article] Sparse Bayesian Learning of Filters for Efficient Image Expansion2010

    • Author(s)
      A. Kanemura, S. Maeda, S. Ishii.
    • Journal Title

      IEEE Transactions on image processing 19(6)

      Pages: 1480-1490

    • NAID

      120002381088

    • Related Report
      2009 Final Research Report
    • Peer Reviewed
  • [Journal Article] Learning a multidimensional companding function for lossy source coding2009

    • Author(s)
      S. Maeda, S. Ishii.
    • Journal Title

      Neural Networks 22(7)

      Pages: 998-1010

    • Related Report
      2009 Final Research Report
    • Peer Reviewed
  • [Journal Article] Learning a multidimensional companding function for lossy source coding2009

    • Author(s)
      S.Maeda, S.Ishii
    • Journal Title

      Neural Networks 22(7)

      Pages: 998-1010

    • Related Report
      2009 Annual Research Report
    • Peer Reviewed
  • [Presentation] オンライン適応自然勾配法による囲碁の盤面評価の学習2010

    • Author(s)
      富澤弘貴, 前田新一, 石井信
    • Organizer
      電子情報通信学会NC研究会
    • Place of Presentation
      玉川
    • Year and Date
      2010-03-11
    • Related Report
      2009 Final Research Report
  • [Presentation] オンライン適応自然勾配法による囲碁の盤面評価の学習2010

    • Author(s)
      富澤弘貴, 前田新一, 石井信
    • Organizer
      電子情報通信学会 NC研究会
    • Place of Presentation
      玉川大学
    • Year and Date
      2010-03-11
    • Related Report
      2009 Annual Research Report
  • [Presentation] Learning of Go board state evaluation function by artificial neural network2009

    • Author(s)
      H. Tomizawa, S. Maeda, S. Ishii
    • Organizer
      International Conference on Neural Information Processing
    • Place of Presentation
      バンコク
    • Year and Date
      2009-12-03
    • Related Report
      2009 Final Research Report
  • [Presentation] Learning of Go board state evaluation function by artificial neural network2009

    • Author(s)
      H.Tomizawa, S.Maeda, S.Ishii
    • Organizer
      International Conference on Neural Information Processing
    • Place of Presentation
      タイ,バンコク
    • Year and Date
      2009-12-03
    • Related Report
      2009 Annual Research Report
  • [Presentation] Detailed Balance Learningによるマルコフ連鎖の学習2009

    • Author(s)
      前田新一, 青木佑紀, 石井信
    • Organizer
      日本神経回路学会第19回全国大会
    • Place of Presentation
      仙台
    • Year and Date
      2009-09-25
    • Related Report
      2009 Final Research Report
  • [Presentation] Detailed Balance Learningによるマルコフ連鎖の学習2009

    • Author(s)
      前田新一, 青木佑紀, 石井信
    • Organizer
      日本神経回路学会 第19回全国大会
    • Place of Presentation
      東北大学
    • Year and Date
      2009-09-25
    • Related Report
      2009 Annual Research Report
  • [Presentation] ニューラルネットワークによる囲碁の盤面評価の学習2009

    • Author(s)
      富澤弘貴, 前田新一, 石井信
    • Organizer
      日本神経回路学会第19回全国大会
    • Place of Presentation
      仙台
    • Year and Date
      2009-09-24
    • Related Report
      2009 Final Research Report
  • [Presentation] 平均場近似を用いたHelmholtz Machineの学習2009

    • Author(s)
      青木佑紀, 前田新一, 石井信
    • Organizer
      電子情報通信学会NC研究会
    • Place of Presentation
      玉川
    • Year and Date
      2009-03-11
    • Related Report
      2009 Final Research Report
  • [Presentation] 平均場近似を用いたHelmholtz Machineの学習2009

    • Author(s)
      青木佑紀, 前田新一, 石井信
    • Organizer
      電子情報通信学会NC研究会
    • Place of Presentation
      玉川大学
    • Year and Date
      2009-03-11
    • Related Report
      2008 Annual Research Report
  • [Presentation] スパースベイズ学習による画像拡大フィルタの獲得2008

    • Author(s)
      兼村厚範, 前田新一, 石井信
    • Organizer
      第23回信号処理シンポジウム
    • Place of Presentation
      金沢
    • Year and Date
      2008-11-13
    • Related Report
      2009 Final Research Report
  • [Presentation] 疎ベイズ解像度合成2008

    • Author(s)
      兼村厚範, 前田新一, 石井信
    • Organizer
      日本神経回路学会第18回全国大会
    • Place of Presentation
      つくば
    • Year and Date
      2008-09-25
    • Related Report
      2009 Final Research Report
  • [Presentation] Subspace selection for resolution synthesis2008

    • Author(s)
      A. Kanemura, S. Maeda, S. Ishii
    • Organizer
      部分空間法研究会2008
    • Place of Presentation
      軽井沢
    • Year and Date
      2008-07-28
    • Related Report
      2009 Final Research Report
  • [Presentation] Optimization of parametric companding function for an efficient coding2007

    • Author(s)
      Shin-ichi Maeda, Shin Ishii
    • Organizer
      IEEE International Symposium on Signal Processing and Information Technology
    • Place of Presentation
      エジプト カイロ
    • Year and Date
      2007-12-16
    • Related Report
      2007 Annual Research Report
  • [Presentation] Optimization of parametric companding function for an efficient coding2007

    • Author(s)
      S. Maeda, S. Ishii
    • Organizer
      International Conference on Neural Information Processing
    • Place of Presentation
      北九州
    • Year and Date
      2007-11-14
    • Related Report
      2009 Final Research Report
  • [Presentation] Convergence analysis of the EM algorithm and Joint minimization of free energy2007

    • Author(s)
      S. Maeda, S. Ishii
    • Organizer
      IEEE International Workshop on Machine Learning for Signal Processing
    • Place of Presentation
      テッサロニキ
    • Year and Date
      2007-08-28
    • Related Report
      2009 Final Research Report
  • [Presentation] Convergence analysis of the EM algorithm and joint minimization of free energy2007

    • Author(s)
      Shin-ichi Maeda, Shin Ishii
    • Organizer
      IEEE International Workshop on Machine Learning for Signal Processing
    • Place of Presentation
      ギリシャ テッサロニキ
    • Year and Date
      2007-08-28
    • Related Report
      2007 Annual Research Report
  • [Remarks]

    • URL

      http://hawaii.sys.i.kyoto-u.ac.jp/~ichi/publication.htm

    • Related Report
      2009 Final Research Report

URL: 

Published: 2007-04-01   Modified: 2016-04-21  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi