Generalization in fully-connected neural networks for time series forecasting

Journal of Computational Science - Tập 36 - Trang 101020 - 2019
Anastasia Borovykh1, Cornelis W. Oosterlee1, Sander M. Bohté1
1CWI Amsterdam, The Netherlands

Tóm tắt

Từ khóa


Tài liệu tham khảo

Achille, 2018, Emergence of invariance and disentanglement in deep representations, J. Mach. Learn. Res., 19, 1

Agarwal, 2013, The generalization ability of online algorithms for dependent data, IEEE Trans. Inform. Theory, 59, 573, 10.1109/TIT.2012.2212414

Auffinger, 2013, Random matrices and complexity of spin glasses, Commun. Pure Appl. Math., 66, 165, 10.1002/cpa.21422

Becker, 2018

Bernier, 2000, A quantitative study of fault tolerance, noise immunity, and generalization ability of MLPs, Neural Comput., 12, 2941, 10.1162/089976600300014782

Bishop, 2007

Bray, 2007, Statistics of critical points of Gaussian fields on large-dimensional spaces, Phys. Rev. Lett., 98, 150201, 10.1103/PhysRevLett.98.150201

Chaudhari, 2018, Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks, 1

Choromanska, 2015, 192

Cont, 2001

Dauphin, 2014, Identifying and attacking the saddle point problem in high-dimensional non-convex optimization, Advances in Neural Information Processing Systems, 2933

Dinh, 2017

Dziugaite, 2017

Fyodorov, 2007, Replica symmetry breaking condition exposed by random matrix calculation of landscape complexity, J. Stat. Phys., 129, 1081, 10.1007/s10955-007-9386-x

Geirhos, 2018, Generalisation in humans and deep neural networks, Advances in Neural Information Processing Systems, 7549

Hochreiter, 1997, Flat minima, Neural Comput., 9, 1, 10.1162/neco.1997.9.1.1

Jastrzkebski, 2017

Kuznetsov, 2014, Generalization bounds for time series prediction with non-stationary processes, 260

Kuznetsov, 2017, Generalization bounds for non-stationary mixing processes, Mach. Learn., 106, 93, 10.1007/s10994-016-5588-2

Kuznetsov, 2018

Li, 2018

Mandt, 2017

Martens, 2010, Deep learning via Hessian-free optimization, ICML, vol. 27, 735

McDonald, 2017, Nonparametric risk bounds for time-series forecasting, J. Mach. Learn. Res., 18, 1

Novak, 2018

Park, 2019

Pennington, 2017, Geometry of neural network loss surfaces via random matrix theory, International Conference on Machine Learning, 2798

Reed, 1992, Regularization using jittered training data, 147

Seong, 2018

Shwartz-Ziv, 2017

Smith, 2017

Smith, 2018

Sokolić, 2017, Robust large margin deep neural networks, IEEE Trans. Signal Process., 65, 4265, 10.1109/TSP.2017.2708039

Srivastava, 2014, 1929

Tishby, 2015, Deep learning and the information bottleneck principle, 1

Zhang, 2016

Zhang, 1998, Forecasting with artificial neural networks: the state of the art, Int. J. Forecast., 14, 35, 10.1016/S0169-2070(97)00044-7

Zhou, 2018