Theory and learning protocols for the material tempotron model
نویسندگان
چکیده
PRL/v96/i3/e030201 [8] Baldassi C, Braunstein A, Brunel N and Zecchina R 2007 Proceedings of the National Academy of Sciences 104 11079–11084 ISSN 0027-8424, 1091-6490 PMID: 17581884 URL http://www.pnas.org/ content/104/26/11079 [9] Baldassi C 2009 Journal of Statistical Physics 136 ISSN 0022-4715 (Print) 1572-9613 (Online) URL http://www.springerlink.com/content/r07772l167526045/ [10] Mézard, M 1989 Journal of Physics A: Mathematical and General 22 2181–2190 ISSN 0305-4470, 1361-6447 [11] Braunstein A, Kayhan F, Montorsi G and Zecchina R 2007 Encoding for the blackwell channel with reinforced belief propagation IEEE International Symposium on Information Theory (ISIT07) pp 1891– 1895 [12] Bailly-Bechet M, Borgs C, Braunstein A, Chayes J, Dagkessamanskaia A, François J and Zecchina R 2010 Proceedings of the National Academy of Sciences 108 882–887 ISSN 0027-8424 URL http: //www.pnas.org/content/108/2/882.short [13] Mézard M, Parisi G and Zecchina R 2002 Science 297 812 – 815 ISSN 10959203 26 [14] Braunstein A, Mézard M and Zecchina R 2005 Random Structures and Algorithms 27 201–226 [15] Monasson R and Zecchina R 1996 Physical Review Letters 76 2205–2205 URL http://link.aps.org/ doi/10.1103/PhysRevLett.76.2205.3 [16] Cocco S, Monasson R and Zecchina R 1996 Physical Review E 54 717–736 URL http://link.aps. org/doi/10.1103/PhysRevE.54.717
منابع مشابه
A Gradient Learning Rule for the Tempotron
We introduce a new supervised learning rule for the tempotron task: the binary classification of input spike trains by an integrate-and-fire neuron that encodes its decision by firing or not firing. The rule is based on the gradient of a cost function, is found to have enhanced performance, and does not rely on a specific reset mechanism in the integrate-and-fire neuron.
متن کاملSpike-Timing Error Backpropagation in Theta Neuron Networks
The main contribution of this letter is the derivation of a steepest gradient descent learning rule for a multilayer network of theta neurons, a one-dimensional nonlinear neuron model. Central to our model is the assumption that the intrinsic neuron dynamics are sufficient to achieve consistent time coding, with no need to involve the precise shape of postsynaptic currents; this assumption depa...
متن کاملTempotron-Like Learning with ReSuMe
The tempotron is a model of supervised learning that allows a spiking neuron to discriminate between different categories of spike trains, by firing or not as function of the category. We show that tempotron learning is quasi-equivalent to an application for a specific problem of a previously proposed, more general and biologically plausible, supervised learning rule (ReSuMe). Moreover, we show...
متن کاملApplication of Learning Theories in Clinical Education
Introduction: The purpose of education is learning. Several theories have been raised about learning, which have tried to explain how learning occurs. They help teachers to choose teaching methods, prepare learning environment and determine students' activities. Given the importance of learning theories in education, this study aimed to review application of learning theories in nursing educati...
متن کاملA geometrical treatment of Tempotron-like problems
In the Tempotron learning problem a neuron receives time varying inputs and for a set of such input sequences (S set) the neuron must be sub-threshold for all times while for some other sequences (S+ set) the neuron must be super threshold for at least one time. Here we present a graphical treatment of a slight reformulation of the tempotron problem. We show that the problem’s general form is e...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2013