Network information criterion-determining the number of hidden units for an artificial neural network model N Murata, S Yoshizawa, S Amari IEEE transactions on neural networks 5 (6), 865-872, 1994 | 822 | 1994 |

An approach to blind source separation based on temporal structure of speech signals N Murata, S Ikeda, A Ziehe Neurocomputing 41 (1-4), 1-24, 2001 | 646 | 2001 |

Asymptotic statistical theory of overtraining and cross-validation S Amari, N Murata, KR Muller, M Finke, HH Yang IEEE Transactions on Neural Networks 8 (5), 985-996, 1997 | 409 | 1997 |

A method of ICA in time-frequency domain S Ikeda, N Murata in Proc. ICA, 1999 | 241 | 1999 |

Information geometry of U-Boost and Bregman divergence N Murata, T Takenouchi, T Kanamori, S Eguchi Neural Computation 16 (7), 1437-1481, 2004 | 210 | 2004 |

Statistical theory of learning curves under entropic loss criterion SI Amari, N Murata Neural Computation 5 (1), 140-153, 1993 | 197 | 1993 |

Neural network with unbounded activation functions is universal approximator S Sonoda, N Murata Applied and Computational Harmonic Analysis 43 (2), 233-268, 2017 | 168 | 2017 |

Asymptotically optimal choice of ε-loss for support vector machines AJ Smola, N Murata, B Schölkopf, KR Müller International Conference on Artificial Neural Networks, 105-110, 1998 | 168 | 1998 |

An on-line algorithm for blind source separation on speech signals N Murata, S Ikeda Proc. NOLTA98 3, 923-926, 1998 | 167 | 1998 |

Adaptive on-line learning in changing environments N Murata, KR Müller, A Ziehe, S Amari Advances in neural information processing systems, 599-605, 1997 | 105 | 1997 |

Statistical theory of overtraining-Is cross-validation asymptotically effective? S Amari, N Murata, KR Müller, M Finke, HH Yang Advances in neural information processing systems, 176-182, 1996 | 104 | 1996 |

The EM algorithm and related statistical models M Watanabe, K Yamaguchi CRC Press, 2003 | 102 | 2003 |

A statistical study of on-line learning N Murata Online Learning and Neural Networks. Cambridge University Press, Cambridge …, 1998 | 102 | 1998 |

A robust approach to independent component analysis of signals with high-level noise measurements J Cao, N Murata, S Amari, A Cichocki, T Takeda IEEE Transactions on Neural Networks 14 (3), 631-645, 2003 | 94 | 2003 |

On-line learning in changing environments with applications in supervised and unsupervised learning N Murata, M Kawanabe, A Ziehe, KR Müller, S Amari Neural Networks 15 (4-6), 743-760, 2002 | 71 | 2002 |

Independent component analysis for unaveraged single-trial MEG data decomposition and single-dipole source localization J Cao, N Murata, S Amari, A Cichocki, T Takeda Neurocomputing 49 (1-4), 255-277, 2002 | 60 | 2002 |

An integral representation of functions using three-layered networks and their approximation bounds N Murata Neural Networks 9 (6), 947-956, 1996 | 60 | 1996 |

A method of blind separation on temporal structure of signals S Ikeda, N Murata ICONIP 98, 737-742, 1998 | 58 | 1998 |

An approach to blind source separation of speech signals S Ikeda, N Murata International Conference on Artificial Neural Networks, 761-766, 1998 | 58 | 1998 |

Learning curves, model selection and complexity of neural networks N Murata, S Yoshizawa, S Amari Advances in neural information processing systems, 607-614, 1993 | 58 | 1993 |