| − | [[人工神经网络]]在语音合成<ref>Zhizheng Wu, Oliver Watts, and Simon King. Merlin: An open source neural network speech synthesis system. In SSW, pages 202–207, 2016.</ref>、图像识别<ref name=":2">Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097–1105, 2012.</ref><ref>Edgar Xi, Selina Bing, and Yang Jin. Capsule network performance on complex data. arXiv preprint arXiv:1712.03480, 2017.</ref>和翻译<ref>I Sutskever, O Vinyals, and QV Le. Sequence to sequence learning with neural networks. Advances in NIPS, 2014.</ref>等各个领域都表现出了先进的性能。[[深度学习网络]](DNN)的主要原理是将[[深度学习]]技术<ref>Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. Deep learning. nature, 521(7553):436–444, 2015.</ref>引入[[人工神经网络]],以及将GPU用于高速计算<ref>Rajat Raina, Anand Madhavan, and Andrew Y Ng. Large-scale deep unsupervised learning using graphics processors. In Proceedings of the 26th annual international conference on machine learning, pages 873–880. ACM, 2009.</ref>。然而,[[人工神经网络]]底层机制还存在很多未知。例如,基本的[[机器学习]]理论表明,拥有大量参数的模型往往容易记住数据集中的所有信息,导致泛化能力差,特别是在未正则化的模型中<ref>Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals. Understanding deep learning requires rethinking generalization. arXiv preprint arXiv:1611.03530, 2016.</ref>。然而在实践中,即使没有显式正则化的DNN也具有良好的泛化性能<ref>Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester, and Nati Srebro. Exploring generalization in deep learning. In Advances in Neural Information Processing Systems, pages 5947–5956, 2017.</ref>。虽然众所周知,尽管[[人工神经网络]]可以逼近任何函数<ref>Kurt Hornik, Maxwell Stinchcombe, and Halbert White. Multilayer feedforward networks are universal approximators. Neural networks, 2(5):359–366, 1989.</ref>,但它们得出的函数是如何超越训练数据进行泛化的,仍缺乏清晰的理论解释。 | + | [[人工神经网络]]在语音合成<ref>Zhizheng Wu, Oliver Watts, and Simon King. Merlin: An open source neural network speech synthesis system. In SSW, pages 202–207, 2016.</ref>、图像识别<ref name=":2">Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097–1105, 2012.</ref><ref>Edgar Xi, Selina Bing, and Yang Jin. Capsule network performance on complex data. arXiv preprint arXiv:1712.03480, 2017.</ref>和翻译<ref>I Sutskever, O Vinyals, and QV Le. Sequence to sequence learning with neural networks. Advances in NIPS, 2014.</ref>等各个领域都表现出了先进的性能。然而,[[人工神经网络]]底层机制还存在很多未知。例如,基本的[[机器学习]]理论表明,拥有大量参数的模型往往容易记住数据集中的所有信息,导致泛化能力差,特别是在未正则化的模型中<ref>Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals. Understanding deep learning requires rethinking generalization. arXiv preprint arXiv:1611.03530, 2016.</ref>。[[深度学习网络]](DNN)的主要原理是将[[深度学习]]技术<ref>Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. Deep learning. nature, 521(7553):436–444, 2015.</ref>引入[[人工神经网络]],以及将GPU用于高速计算<ref>Rajat Raina, Anand Madhavan, and Andrew Y Ng. Large-scale deep unsupervised learning using graphics processors. In Proceedings of the 26th annual international conference on machine learning, pages 873–880. ACM, 2009.</ref>。在实践中,研究者发现即使没有显式正则化的DNN也具有良好的泛化性能<ref>Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester, and Nati Srebro. Exploring generalization in deep learning. In Advances in Neural Information Processing Systems, pages 5947–5956, 2017.</ref>。虽然众所周知,尽管[[人工神经网络]]可以逼近任何函数<ref>Kurt Hornik, Maxwell Stinchcombe, and Halbert White. Multilayer feedforward networks are universal approximators. Neural networks, 2(5):359–366, 1989.</ref>,但它们得出的函数是如何超越训练数据进行泛化的,仍缺乏清晰的理论解释。 |
| | [[信息瓶颈]](information bottleneck)是一种被提出来解释DNN泛化能力的理论框架<ref>Naftali Tishby, Fernando C Pereira, and William Bialek. The information bottleneck method. arXiv preprint physics/0004057, 2000.</ref>。它认为DNN在压缩输入数据与预测输出之间寻找最佳平衡。通过分析网络在[[信息平面]](information plane)上的行为——即输入数据与每层网络之间的[[互信息]],研究者尝试揭示网络的学习机制<ref>Ravid Shwartz-Ziv and Naftali Tishby. Opening the black box of deep neural networks via information. arXiv preprint arXiv:1703.00810, 2017.</ref>。虽然寻找[[信息瓶颈]]是一个可行的方法,但更大的网络仍然受到信息估计问题的困扰<ref>Kristoffer Wickstrøm, Sigurd Løkse, Michael Kampffmeyer, Shujian Yu, Jose Principe, and Robert Jenssen. Information plane analysis of deep neural networks via matrix-based renyi’s entropy and tensor kernels.arXiv preprint arXiv:1909.11396, 2019.</ref>,并且某些网络拓扑和激活函数的预测或偏差存在错误<ref>Andrew M Saxe, Yamini Bansal, Joel Dapello, Madhu Advani, Artemy Kolchinsky, Brendan D Tracey, and David DCox. On the information bottleneck theory of deep learning. Journal of Statistical Mechanics: Theory and Experiment, 2019(12):124020, 2019.</ref>。更根本的是,[[信息瓶颈]]方法的数学公式是数据依赖的,也就是说,它的互信息得分随着输入分布的变化而变化。然而,从定义上讲,泛化能力是不同数据集(输入频率不同,甚至是未知且尚未定义的未来数据集)性能的函数。因此,为了理解泛化能力,有必要关注DNN在具有不同属性的不同数据集上的不变性<ref>Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals. Understanding deep learning requires rethinking generalization. arXiv preprint arXiv:1611.03530, 2016.</ref>。 | | [[信息瓶颈]](information bottleneck)是一种被提出来解释DNN泛化能力的理论框架<ref>Naftali Tishby, Fernando C Pereira, and William Bialek. The information bottleneck method. arXiv preprint physics/0004057, 2000.</ref>。它认为DNN在压缩输入数据与预测输出之间寻找最佳平衡。通过分析网络在[[信息平面]](information plane)上的行为——即输入数据与每层网络之间的[[互信息]],研究者尝试揭示网络的学习机制<ref>Ravid Shwartz-Ziv and Naftali Tishby. Opening the black box of deep neural networks via information. arXiv preprint arXiv:1703.00810, 2017.</ref>。虽然寻找[[信息瓶颈]]是一个可行的方法,但更大的网络仍然受到信息估计问题的困扰<ref>Kristoffer Wickstrøm, Sigurd Løkse, Michael Kampffmeyer, Shujian Yu, Jose Principe, and Robert Jenssen. Information plane analysis of deep neural networks via matrix-based renyi’s entropy and tensor kernels.arXiv preprint arXiv:1909.11396, 2019.</ref>,并且某些网络拓扑和激活函数的预测或偏差存在错误<ref>Andrew M Saxe, Yamini Bansal, Joel Dapello, Madhu Advani, Artemy Kolchinsky, Brendan D Tracey, and David DCox. On the information bottleneck theory of deep learning. Journal of Statistical Mechanics: Theory and Experiment, 2019(12):124020, 2019.</ref>。更根本的是,[[信息瓶颈]]方法的数学公式是数据依赖的,也就是说,它的互信息得分随着输入分布的变化而变化。然而,从定义上讲,泛化能力是不同数据集(输入频率不同,甚至是未知且尚未定义的未来数据集)性能的函数。因此,为了理解泛化能力,有必要关注DNN在具有不同属性的不同数据集上的不变性<ref>Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals. Understanding deep learning requires rethinking generalization. arXiv preprint arXiv:1611.03530, 2016.</ref>。 |