^Ciresan, D.; Giusti, A.; Gambardella, L.M.; Schmidhuber, J. (2013). “Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks”. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2013. Lecture Notes in Computer Science. 7908. pp. 411–418. doi:10.1007/978-3-642-40763-5_51.
ISBN978-3-642-38708-1.
PMID24579167
^Ciresan, D.; Meier, U.; Schmidhuber, J. (2012). “Multi-column deep neural networks for image classification”. 2012 IEEE Conference on Computer Vision and Pattern Recognition. pp. 3642–3649. arXiv:1202.2745. doi:10.1109/cvpr.2012.6248110.
ISBN978-1-4673-1228-8
^Billings, S. A. (2013). Nonlinear System Identification: NARMAX Methods in the Time, Frequency, and Spatio-Temporal Domains. Wiley.
ISBN978-1-119-94359-4
^
Goodfellow, Ian; Pouget-Abadie, Jean; Mirza, Mehdi; Xu, Bing; Warde-Farley, David; Ozair, Sherjil; Courville, Aaron; Bengio, Yoshua (2014). Generative Adversarial Networks(PDF). Proceedings of the International Conference on Neural Information Processing Systems (NIPS 2014). pp. 2672–2680. 2019年11月22日時点のオリジナルよりアーカイブ(PDF). 2025年6月20日閲覧.
^
Schmidhuber, Jürgen (1991). “A possibility for implementing curiosity and boredom in model-building neural controllers”. Proc. SAB'1991. MIT Press/Bradford Books. pp. 222–227.
^Schmidhuber, Jürgen (2020). “Generative Adversarial Networks are Special Cases of Artificial Curiosity (1990) and also Closely Related to Predictability Minimization (1991)” (英語). Neural Networks127: 58–66. arXiv:1906.04493. doi:10.1016/j.neunet.2020.04.008.
PMID32334341.
^
Karras, T.; Aila, T.; Laine, S.; Lehtinen, J. (26 February 2018). “Progressive Growing of GANs for Improved Quality, Stability, and Variation”. arXiv:1710.10196 [cs.NE].
^
Schlag, Imanol; Irie, Kazuki; Schmidhuber, Jürgen (2021). “Linear Transformers Are Secretly Fast Weight Programmers”. ICML 2021. Springer. pp. 9355–9366.
^Wolf, Thomas; Debut, Lysandre; Sanh, Victor; Chaumond, Julien; Delangue, Clement; Moi, Anthony; Cistac, Pierric; Rault, Tim et al. (2020). “Transformers: State-of-the-Art Natural Language Processing”. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. pp. 38–45. doi:10.18653/v1/2020.emnlp-demos.6
^Y. LeCun; B. Boser; J. S. Denker; D. Henderson; R. E. Howard; W. Hubbard; L. D. Jackel (1989). “Backpropagation applied to handwritten zip code recognition”. Neural Computation1 (4): 541-551.
^"A nonrecurrent network has no cycles. Nonrecurrent networks can be thought of as computing an input-output function." Jordan, M.I. (1986). Serial order: A parallel distributed processing approach. (Tech. Rep. No. 8604). San Diego: University of California, Institute for Cognitive Science.
^Akira Hirose, Shotaro Yoshida (2012). “Generalization Characteristics of Complex-valued Feedforward Neural Networks in Relation to Signal Coherence”. IEEE TNNLS23 (4): 541-551.
^The proposed U-Net based architecture allows to provide detailed per-pixel feedback to the generator while maintaining the global coherence of synthesized images
^starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes itPGGAN paper
^"making normalization a part of the model architecture and performing the normalization for each training mini-batch." Sergey Ioffe, et. al.. (2015)
^"The most obvious drawback of the learning procedure is that the error-surface may contain local minima so that gradient descent is not guaranteed to find a global minimum." p.536 of Rumelhart, et al. (1986). Learning representations by back-propagating errors. Nature.
^"Quantization works by reducing the precision of the numbers used to represent a model's parameters, which by default are 32-bit floating point numbers." Model optimization. TensorFlow.
^"Quantizing a network means converting it to use a reduced precision integer representation for the weights and/or activations." DYNAMIC QUANTIZATION. PyTorch.
^"Quantization performance gain comes in 2 part: instruction and cache." Quantize ONNX Models. ONNX Runtime.
^"Less memory usage: Smaller models use less RAM when they are run, which frees up memory for other parts of your application to use, and can translate to better performance and stability." Model optimization. TensorFlow.
^"Old hardware doesn’t have or has few instruction support for byte computation. And quantization has overhead (quantize and dequantize), so it is not rare to get worse performance on old devices." Quantize ONNX Models. ONNX Runtime.
^"Performance improvement depends on your model and hardware." Quantize ONNX Models. ONNX Runtime.
^"Static quantization quantizes the weights and activations of the model. ... It requires calibration with a representative dataset to determine optimal quantization parameters for activations." QUANTIZATION. PyTorch.
^"with dynamic quantization ... determine the scale factor for activations dynamically based on the data range observed at runtime." DYNAMIC QUANTIZATION. PyTorch.
^"The model parameters ... are converted ahead of time and stored in INT8 form." DYNAMIC QUANTIZATION. PyTorch.
^"Simulate the quantize and dequantize operations in training time." FAKEQUANTIZE. PyTorch. 2022-03-15閲覧.
^"There are 2 ways to represent quantized ONNX models: ... Tensor Oriented, aka Quantize and DeQuantize (QDQ)." Quantize ONNX Models. ONNX RUNTIME. 2022-03-15閲覧.
Copyright c San-eishobo Publishing Co.,Ltd.All Rights Reserved.
Copyright (C) 2026 (社)日本オペレーションズ・リサーチ学会 All rights reserved.
All text is available under the terms of the GNU Free Documentation License. この記事は、ウィキペディアのニューラルネットワーク (改訂履歴)、ニューラルネットワーク (曖昧さ回避) (改訂履歴)の記事を複製、再配布したものにあたり、GNU Free Documentation Licenseというライセンスの下で提供されています。
Weblio辞書に掲載されているウィキペディアの記事も、全てGNU Free Documentation Licenseの元に提供されております。