9. 9
PDP (並列分散処理)
[McClelland+ 86]
多数の (暗黙の) 制約を満たしながら認識や行動を遂行
するための計算モデル
知覚、運動制御、記憶検索の過程を自然に記述可能
e.g. 物体認識、リーチング、連想記憶
明示的な規則の定式化ではなく、あたかもルールに
従って動くような結合の獲得を目標とする
17/09/04 WBA若手の会 第29回勉強会
J. L. McClellandD. Rumelhart G. E. Hinton
33. 33
現代的コネクショニズム
現代的なニューラルネットの目標は、異なるモダリ
ティ間の相互変換を実現することであり、その内部に
高次構造を見出すことである
17/09/04 WBA若手の会 第29回勉強会
Aytar, Y., Vondrick, C., & Torralba, A. (2017). See, Hear, and Read: Deep Aligned Representations. arXiv preprint arXiv:1706.00932.
Finn, C., Goodfellow, I., & Levine, S. (2016). Unsupervised learning for physical interaction through video prediction. In Advances in
Neural Information Processing Systems (pp. 64-72).
画像
音声 言語
分類 状況
音素・形態素
感情価・覚醒度
時系列データ過去・将来
方策位置
高次構造
51. 51
参考文献
[辻井 12] 辻井潤一, 『合理主義と経験主義のはざまで―内的な処理の計算モデル―』, 人工知能学会誌, Vol. 27, No.
3, 2012
[Dreyfus & Dreyfus 87] H. L. Dreyfus and S. E. Dreyfus, 『純粋人工知能批判』, アスキー出版局, 1987,椋田直
子訳
[黒崎 90] 黒崎政男, 『ミネルヴァのふくろうは世紀末を飛ぶ テクノロジーと哲学の現在』, 弘文堂, 1990
[Brown+ 93] Brown, P. F., Pietra, V. J. D., Pietra, S. A. D., & Mercer, R. L. (1993). The mathematics of
statistical machine translation: Parameter estimation. Computational linguistics, 19(2), 263-311.
[Sung & Poggio 98] Sung, K. K., & Poggio, T. (1998). Example-based learning for view-based human face
detection. IEEE Transactions on pattern analysis and machine intelligence, 20(1), 39-51.
[Fei-Fei 04] L. Fei-Fei, R. Fergus and P. Perona. Learning generative visual models from few training
examples: an incremental Bayesian approach tested on 101 object categories. IEEE. CVPR 2004, Workshop
on Generative-Model Based Vision. 2004
[Deng+ 09] Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009, June). Imagenet: A large-
scale hierarchical image database. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE
Conference on (pp. 248-255). IEEE.
[Lin+ 16] Lin, H. W., Tegmark, M., & Rolnick, D. (2016). Why does deep and cheap learning work so well?.
Journal of Statistical Physics, 1-25.
[Banko & Brill 01] Banko, M., & Brill, E. (2001, July). Scaling to very very large corpora for natural
language disambiguation. In Proceedings of the 39th annual meeting on association for computational
linguistics (pp. 26-33). Association for Computational Linguistics.
[Zhou+ 17] Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., & Torralba, A. (2017). Places: A 10 million image
database for scene recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence.
[Sun+ 17] Sun, C., Shrivastava, A., Singh, S., & Gupta, A. (2017). Revisiting unreasonable effectiveness of
data in deep learning era. arXiv preprint arXiv:1707.02968.
17/09/04 WBA若手の会 第29回勉強会
52. 52
参考文献
[Collobert+ 08] Collobert, R., & Weston, J. (2008, July). A unified architecture for natural language
processing: Deep neural networks with multitask learning. In Proceedings of the 25th international
conference on Machine learning (pp. 160-167). ACM.
[Yosinski+ 14] Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep
neural networks?. In Advances in neural information processing systems (pp. 3320-3328).
[LeCun 86] Y. LeCun: Learning Processes in an Asymmetric Threshold Network, in Bienenstock, E. and
Fogelman-Soulié, F. and Weisbuch, G. (Eds), Disordered systems and biological organization, 233-240,
Springer-Verlag, Les Houches, France, 1986
[Cybenko 89] Cybenko., G. (1989) "Approximations by superpositions of sigmoidal functions", Mathematics
of Control, Signals, and Systems, 2 (4), 303-314
[Vapnik 98] Vapnik, V. N., & Vapnik, V. (1998). Statistical learning theory (Vol. 1). New York: Wiley.
[Bartlett 02] Bartlett, P. L., & Mendelson, S. (2002). Rademacher and Gaussian complexities: Risk bounds
and structural results. Journal of Machine Learning Research, 3(Nov), 463-482.
[Krueger+ 17] Krueger, D., Ballas, N., Jastrzebski, S., Arpit, D., Kanwal, M. S., Maharaj, T., ... & Courville, A.
(2017). Deep Nets Don't Learn via Memorization.
[Hoffer+ 17] Hoffer, E., Hubara, I., & Soudry, D. (2017). Train longer, generalize better: closing the
generalization gap in large batch training of neural networks. arXiv preprint arXiv:1705.08741.
[Kuzborskij & Lampert 17] Kuzborskij, I., & Lampert, C. (2017). Data-Dependent Stability of Stochastic
Gradient Descent. arXiv preprint arXiv:1703.01678.
[Wu+ 17] Lei Wu, Zhanxing Zhu and Weinan E. Towards Understanding Generalization of Deep Learning:
Perspective of Loss Landscapes. ICML 2017 Workshop.
[安西 88]安西祐一郎. (1988). 認識の情報科学への計算論的アプローチ (< 連載>「AI における論争」[第 4 回]). 人
工知能学会誌, 3(3), 248-256.
[Karpathy+ 14] Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., & Fei-Fei, L. (2014). Large-
scale video classification with convolutional neural networks. In Proceedings of the IEEE conference on
Computer Vision and Pattern Recognition (pp. 1725-1732).
17/09/04 WBA若手の会 第29回勉強会