Approximate Projection Expression of Nonlinear Artificial Intelligent Systems Based on Matrix Operator Polynomial Approximations

• Item type: SIG Technical Reports(1)
• 公開日: 2016-08-29
• タイトル: Approximate Projection Expression of Nonlinear Artificial Intelligent Systems Based on Matrix Operator Polynomial Approximations
• タイトル / 言語: en
• タイトル: Approximate Projection Expression of Nonlinear Artificial Intelligent Systems Based on Matrix Operator Polynomial Approximations
• 言語: eng
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: The School of Pharmaceutical sciences, Ohu University
• 著者所属: Tokyo Institute of Technology
• 著者所属(英): en
• 著者所属(英): The School of Pharmaceutical sciences, Ohu University
• 著者所属(英): en
• 著者所属(英): Tokyo Institute of Technology
• 著者名: Yuichi, Kida; Takuro, Kida
• 著者名(英): Yuichi, Kida; Takuro, Kida
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Firstly about an extended filter bank where input and output signal are matrix operators, we introduce a theory developed by Kida that shows the equivalence relation established between the optimum operator signal approximation which minimizes all the upper limit measures of error at the same time and the operator signal approximation based on the concept of pseudo inverse matrix which minimizes square average norm of the error. Secondly, based on a new concept of Kullback Leibler divergence extended to operator signals, we present a new scanning type approximation of operator signals that guarantees similar optimum performance in the above approximation. Thirdly, about a nonlinear operator in an artificial intelligence system represented by deep learning, we prove that there is an operator matrix polynomial approximation that the upper limit of error is approximately smaller than a given positive number epsilon. Finally, we prove that the above operator matrix polynomial approximation of the nonlinear operator in the artificial intelligence system is reduced to a linear combination of the input operator and the output operator. As a consequence, under some number of trials, we show that there is a possibility of controlling and guiding those artificial intelligence nonlinear operator systems to undesirable direction. And, in order to prevent bad use of words in an artificial intelligence chat system, we point out the necessity of introducing "the prior check and censorship" of "words to use" in these artificial intelligence chat systems.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Firstly about an extended filter bank where input and output signal are matrix operators, we introduce a theory developed by Kida that shows the equivalence relation established between the optimum operator signal approximation which minimizes all the upper limit measures of error at the same time and the operator signal approximation based on the concept of pseudo inverse matrix which minimizes square average norm of the error. Secondly, based on a new concept of Kullback Leibler divergence extended to operator signals, we present a new scanning type approximation of operator signals that guarantees similar optimum performance in the above approximation. Thirdly, about a nonlinear operator in an artificial intelligence system represented by deep learning, we prove that there is an operator matrix polynomial approximation that the upper limit of error is approximately smaller than a given positive number epsilon. Finally, we prove that the above operator matrix polynomial approximation of the nonlinear operator in the artificial intelligence system is reduced to a linear combination of the input operator and the output operator. As a consequence, under some number of trials, we show that there is a possibility of controlling and guiding those artificial intelligence nonlinear operator systems to undesirable direction. And, in order to prevent bad use of words in an artificial intelligence chat system, we point out the necessity of introducing "the prior check and censorship" of "words to use" in these artificial intelligence chat systems.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA11131797
• 書誌情報: 研究報告コンピュータビジョンとイメージメディア（CVIM）; 巻 2016-CVIM-203, 号 9, p. 1-6, 発行日 2016-08-29
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8701
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会