麻省理工大学出版社
期刊
会议
图书
作者:Shun-ichi Amari , Tomoko Ozeki , Ryo Karakida ...
来源:[J].Neural Computation(IF 1.76), 2018, Vol.30 (1), pp.1-33麻省理工大学出版社
摘要:The dynamics of supervised learning play a main role in deep learning, which takes place in the parameter space of a multilayer perceptron (MLP). We review the history of supervised stochastic gradient learning, focusing on its singular structure and natural gradient. The paramet...
作者:Cengiz Pehlevan , Anirvan M. Sengupta , Dmitri B. Chklovskii
来源:[J].Neural Computation(IF 1.76), 2018, Vol.30 (1), pp.84-124麻省理工大学出版社
摘要:Modeling self-organization of neural networks for unsupervised learning using Hebbian and anti-Hebbian plasticity has a long history in neuroscience. Yet derivations of single-layer networks with such local learning rules from principled optimization objectives became possible on...
作者:Sizhen Du , Guojie Song , Lei Han ...
来源:[J].Neural Computation(IF 1.76), 2018, Vol.30 (1), pp.271-291麻省理工大学出版社
摘要:Accurate causal inference among time series helps to better understand the interactive scheme behind the temporal variables. For time series analysis, an unavoidable issue is the existence of time lag among different temporal variables. That is, past evidence would take some time...
作者:Mohammadjavad Faraji , Kerstin Preuschoff , Wulfram Gerstner
来源:[J].Neural Computation(IF 1.76), 2018, Vol.30 (1), pp.34-83麻省理工大学出版社
摘要:Surprise describes a range of phenomena from unexpected events to behavioral responses. We propose a novel measure of surprise and use it for surprise-driven learning. Our surprise measure takes into account data likelihood as well as the degree of commitment to a belief via the ...
作者:Kunling Geng , Dae C. Shin , Dong Song ...
来源:[J].Neural Computation(IF 1.76), 2018, Vol.30 (1), pp.149-183麻省理工大学出版社
摘要:This letter examines the results of input-output (nonparametric) modeling based on the analysis of data generated by a mechanism-based (parametric) model of CA3-CA1 neuronal connections in the hippocampus. The motivation is to obtain biological insight into the interpretation of ...
作者:Jacob Østergaard , Mark A. Kramer , Uri T. Eden
来源:[J].Neural Computation(IF 1.76), 2018, Vol.30 (1), pp.125-148麻省理工大学出版社
摘要:To understand neural activity, two broad categories of models exist: statistical and dynamical. While statistical models possess rigorous methods for parameter estimation and goodness-of-fit assessment, dynamical models provide mechanistic insight. In general, these two categorie...
作者:Osamu Hoshino , Meihong Zheng , Kazuo Watanabe
来源:[J].Neural Computation(IF 1.76), 2018, Vol.30 (1), pp.184-215麻省理工大学出版社
摘要:Learning of sensory cues is believed to rely on synchronous pre- and postsynaptic neuronal firing. Evidence is mounting that such synchronicity is not merely caused by properties of the underlying neuronal network but could also depend on the integrity of gap junctions that conne...
作者:Minkyu Choi , Jun Tani
来源:[J].Neural Computation(IF 1.76), 2018, Vol.30 (1), pp.237-270麻省理工大学出版社
摘要:This letter proposes a novel predictive coding type neural network model, the predictive multiple spatiotemporal scales recurrent neural network (P-MSTRNN). The P-MSTRNN learns to predict visually perceived human whole-body cyclic movement patterns by exploiting multiscale spatio...
作者:Rasmus Troelsgaard , Lars Kai Hansen
来源:[J].Neural Computation(IF 1.76), 2018, Vol.30 (1), pp.216-236麻省理工大学出版社
摘要:Model-based classification of sequence data using a set of hidden Markov models is a well-known technique. The involved score function, which is often based on the class-conditional likelihood, can, however, be computationally demanding, especially for long data sequences. Inspir...
作者:Rachel Churner
来源:[J].October, 2017, pp.108-111麻省理工大学出版社
摘要:Rachel Churner introduces essays by Annette Michelson and Rosalind Krauss on Soviet cinema, reprinted in conjunction with the centennial of the October revolution. Published in the early 1970s, these essays provide a glimpse into how the founders of October thought about the...

我们正在为您处理中,这可能需要一些时间,请稍等。

资源合作:cnki.scholar@cnki.net, +86-10-82896619   意见反馈:scholar@cnki.net

×