文献一覧: 09128085 (ISSN) - Ceek.jp Altmetrics

3 0 0 0 OA 深層脳内情報処理から学ぶもの : 機能脳科学の観点から

著者: 苫米地英人 Hideto Tomabechi
雑誌: 人工知能学会誌 = Journal of Japanese Society for Artificial Intelligence (ISSN:09128085)
巻号頁・発行日: vol.16, no.2, pp.267-277, 2001-03-01

2021-03-07 00:05:50
2 + 0 Twitter
1 + 1 Wikipedia

http://id.nii.ac.jp/1004/00005195/

3 0 0 0 国文学の研究教育における機械学習応用(<特集>機械学習の科学研究への応用)

著者: 福田智子竹田正幸
出版者: 社団法人人工知能学会
雑誌: 人工知能学会誌 (ISSN:09128085)
巻号頁・発行日: vol.24, no.6, pp.780-787, 2009-11-01

2020-11-29 22:58:48
3 + 1 Twitter

https://ci.nii.ac.jp/naid/110007467971

3 0 0 0 深層脳内情報処理から学ぶもの : 機能脳科学の観点から

著者: 苫米地英人
出版者: 社団法人人工知能学会
雑誌: 人工知能学会誌 (ISSN:09128085)
巻号頁・発行日: vol.16, no.2, pp.267-277, 2001-03-01

2020-02-18 22:52:48
3 + 0 Twitter

https://ci.nii.ac.jp/naid/110002808481

3 0 0 0 OA 小論文およびエッセイの自動評価採点における研究動向(<特集>テキストの自動評価)

著者: 石岡恒憲 Tsunenori Ishioka
雑誌: 人工知能学会誌 = Journal of Japanese Society for Artificial Intelligence (ISSN:09128085)
巻号頁・発行日: vol.23, no.1, pp.17-24, 2008-01-01

2019-09-23 16:05:51
3 + 0 Twitter

http://id.nii.ac.jp/1004/00006884/

3 0 0 0 OA 牌譜の解析による麻雀の分析(<特集>思考ゲーム)

著者: とつげき東北伊藤毅志 Tohoku Totsugeki Takeshi Ito
雑誌: 人工知能学会誌 = Journal of Japanese Society for Artificial Intelligence (ISSN:09128085)
巻号頁・発行日: vol.24, no.3, pp.355-360, 2009-05-01

2019-03-30 10:53:23
2 + 2 Twitter
1 + 1 Wikipedia

http://id.nii.ac.jp/1004/00007260/

3 0 0 0 OA 多様な目的に適した形態素解析システム用電子化辞書(<特集>日本語コーパス)

著者: 伝康晴 Yasuharu Den
雑誌: 人工知能学会誌 = Journal of Japanese Society for Artificial Intelligence (ISSN:09128085)
巻号頁・発行日: vol.24, no.5, pp.640-646, 2009-09-01

2018-11-29 17:58:07
3 + 1 Twitter

http://id.nii.ac.jp/1004/00007330/

3 0 0 0 OA HAIのための心理学実験と生体情報 : ユーザを知るということ(<特集>深化するHAI:ヒューマンエージェントインタラクション)

著者: 小松孝徳 Takanori Komatsu 信州大学ファイバーナノテク国際若手研究者育成拠点 International Young Researcher Empowerment Center Shinshu University
雑誌: 人工知能学会誌 = Journal of Japanese Society for Artificial Intelligence (ISSN:09128085)
巻号頁・発行日: vol.24, no.6, pp.833-839, 2009-11-01

2017-12-11 14:19:44
3 + 12 Twitter

http://id.nii.ac.jp/1004/00007382/

3 0 0 0 イグノーベル賞受賞研究SpeechJammer

著者: 栗原一貴塚田浩二
出版者: 社団法人人工知能学会
雑誌: 人工知能学会誌 (ISSN:09128085)
巻号頁・発行日: vol.28, no.2, pp.318-325, 2013-03-01

2016-09-23 10:54:55
3 + 1 Twitter

https://ci.nii.ac.jp/naid/110009594469

3 0 0 0 遺伝的アルゴリズムにおける世代交代モデルの提案と評価

著者: 佐藤浩小野功小林重信
出版者: 社団法人人工知能学会
雑誌: 人工知能学会誌 (ISSN:09128085)
巻号頁・発行日: vol.12, no.5, pp.734-744, 1997-09-01
被引用文献数: 211

When Genetic Algorithms (GAs) are applied to optimization problems, characteristic preserving in designing coding/crossover and diversity maintaining in designing generation alternation are important. Generation alternation models are independent of problems, while coding/crossover depends on problems. We discuss generation alternation models in this paper. Simple GA is one of the well-known generation alternation models, however it has two problems. One is early convergence in the first stage of search and the other is evolutionary stagnation in the last stage of it. Many improvements and new models have been presented to overcome the above problems. In this paper, we propose a new generation alternation model called minimal generation gap (MGG) which has all advantages of conventional models. As generation alternation models use only information of fitness, alternation of generations can be regarded as a transformation of fitness distributions. We propose a new method of assessing generation alternation models. We measure the ability of avoiding the early convergence and suppressing the evolutionary stagnation by the dynamics of the best value and variance of fitness distributions. From the results of some experiments, we found that MGG is the most desirable model which can avoid the early convergence and suppress the evolutionary stagnation. We also show the efficiency of MGG by applying it to benchmarks in different two domains: function optimization and traveling salesman problems. In the both domains, MGG showed higher performance than the other conventional models especially under small population size.

2016-07-10 00:53:53
3 + 1 Twitter

https://ci.nii.ac.jp/naid/110002806861

3 0 0 0 巡回セールスマン問題に対する交叉 : 枝組み立て交叉の提案と評価

著者: 永田裕一小林重信
出版者: 社団法人人工知能学会
雑誌: 人工知能学会誌 (ISSN:09128085)
巻号頁・発行日: vol.14, no.5, pp.848-859, 1999-09-01
被引用文献数: 21

In this paper, we propose a new crossover named Edge Assembly Crossover(EAX) for the Traveling Salesman Problern. EAX constructs intermediate individuals by assembling only edges of parents under the assignment relaxation that is one of TSP relaxations, and then modifies them into complete ones to satisfy the original constraint of TSP. EAX has two features. One is that EAX is excellent in chartacteristic preservation in view of preserving edges from parents to children. The other is that EAX can generate a wide variety of children from a pair of parents. We show by experiments that EAX generates new soltution candidates under a suitable trade-off between characteristic preservation and a variety of children, which brings better performance than other crossovers do. Finally, we show that EAX realizes global neighborhood search by comparing EAX with the traditional local search operators for TSP.