Search

Your search keyword '"Amari, S.-i."' showing total 593 results
Start Over Author "Amari, S.-i."

Refine your results

more »

more »

more »

more »
593 results on '"Amari, S.-i."'

1. Spontaneous Motion on Two-dimensional Continuous Attractors

Author

Fung, C. C. Alan and Amari, S. -I.

Subjects
Condensed Matter - Disordered Systems and Neural Networks
Abstract

Attractor models are simplified models used to describe the dynamics of firing rate profiles of a pool of neurons. The firing rate profile, or the neuronal activity, is thought to carry information. Continuous attractor neural networks (CANNs) describe the neural processing of continuous information such as object position, object orientation and direction of object motion. Recently, it was found that, in one-dimensional CANNs, short-term synaptic depression can destabilize bump-shaped neuronal attractor activity profiles. In this paper, we study two-dimensional CANNs with short-term synaptic depression and with spike frequency adaptation. We found that the dynamics of CANNs with short-term synaptic depression and CANNs with spike frequency adaptation are qualitatively similar. We also found that in both kinds of CANNs the perturbative approach can be used to predict phase diagrams, dynamical variables and speed of spontaneous motion., Comment: 58 pages, 11 figures

Published
2015
Full Text
View/download PDF

3. Interpolating between optimal transport and MMD using Sinkhorn divergences

Author

Feydy, J, Séjourné, T, Vialard, F-X, Amari, S-I, Trouvé, A, and Peyré, G

Subjects
stat.TH, math.ST
Abstract

Comparing probability distributions is a fundamental problem in data sciences. Simple norms and divergences such as the total variation and the relative entropy only compare densities in a point-wise manner and fail to capture the geometric nature of the problem. In sharp contrast, Maximum Mean Discrepancies (MMD) and Optimal Transport distances (OT) are two classes of distances between measures that take into account the geometry of the underlying space and metrize the convergence in law. This paper studies the Sinkhorn divergences, a family of geometric divergences that interpolates between MMD and OT. Relying on a new notion of geometric entropy, we provide theoretical guarantees for these divergences: positivity, convexity and metrization of the convergence in law. On the practical side, we detail a numerical scheme that enables the large scale application of these divergences for machine learning: on the GPU, gradients of the Sinkhorn loss can be computed for batches of a million samples.

Published
2018

9. A general framework for symbol and rule extraction in neural networks

Author

Amari, S.-I., Apolloni, C., Orovas, C., Taylor, J., Fellenz, W., Gielen, C.C.A.M., Westerdijk, M.J.D., Amari, S.-I., Apolloni, C., Orovas, C., Taylor, J., Fellenz, W., Gielen, C.C.A.M., and Westerdijk, M.J.D.

Abstract

IJCNN 2000, Item does not contain fulltext

Published
2000

21. Using ancillary statistics in on-line learning algorithms

Author

Amari, S I, Xu, L, Chan, L W, King, I, Leung, K S, Zhu, Huaiyu, Rohwer, Richard, Amari, S I, Xu, L, Chan, L W, King, I, Leung, K S, Zhu, Huaiyu, and Rohwer, Richard

Abstract

Neural networks are usually curved statistical models. They do not have finite dimensional sufficient statistics, so on-line learning on the model itself inevitably loses information. In this paper we propose a new scheme for training curved models, inspired by the ideas of ancillary statistics and adaptive critics. At each point estimate an auxiliary flat model (exponential family) is built to locally accommodate both the usual statistic (tangent to the model) and an ancillary statistic (normal to the model). The auxiliary model plays a role in determining credit assignment analogous to that played by an adaptive critic in solving temporal problems. The method is illustrated with the Cauchy model and the algorithm is proved to be asymptotically efficient.

Published
1996

23. Information content of neural networks with self-control and variable activity.

Author

Bolle´, D., Amari, S. I., Dominguez Carreta, D. R. C., and Massolo, G.

Subjects
*ARTIFICIAL neural networks, *LOCAL fields (Algebra), *COMPUTER architecture
Abstract

A self-control mechanism for the dynamics of neural networks with variable activity is discussed using a recursive scheme for the time evolution of the local field. It is based upon the introduction of a self-adapting time-dependent threshold as a function of both the neural and pattern activity in the network. This mechanism leads to an improvement of the information content of the network as well as an increase of the storage capacity and the basins of attraction. Different architectures are considered and the results are compared with numerical simulations. [ABSTRACT FROM AUTHOR]

Published
2001

49. Power system fault prediction using artificial neural networks

Author

Amari, S. -I., Xu, L., Chan, L. -W., King, I., Leung, K. -S., Wong, K. C. P., Ryan, H. M., Tindle, J., Amari, S. -I., Xu, L., Chan, L. -W., King, I., Leung, K. -S., Wong, K. C. P., Ryan, H. M., and Tindle, J.

Abstract

The medium term goal of the research reported in this paper was the development of a major in-house suite of strategic computer aided network simulation and decision support tools to improve the management of power systems. This paper describes a preliminary research investigation to access the feasibility of using an Artificial Intelligence (AI) method to predict and detect faults at an early stage in power systems. To achieve this goal, an AI based detector has been developed to monitor and predict faults at an early stage on particular sections of power systems. The detector only requires external measurements taken from the input and output nodes of the power system. The AI detection system is capable of rapidly predicting a malfunction within the system . Simulation will normally take place using equivalent circuit representation. Artificial Neural Networks (ANNs) are used to construct a hierarchical feed-forward structure which is the most important component in the fault detector. Simulation of a transmission line (2-port  circuit ) has already been carried out and preliminary results using this system are promising. This approach provided satisfactory results with accuracy of 95% or higher.

50. Power system fault prediction using artificial neural networks

Author

Amari, S. -I., Xu, L., Chan, L. -W., King, I., Leung, K. -S., Wong, K. C. P., Ryan, H. M., Tindle, J., Amari, S. -I., Xu, L., Chan, L. -W., King, I., Leung, K. -S., Wong, K. C. P., Ryan, H. M., and Tindle, J.

Abstract

The medium term goal of the research reported in this paper was the development of a major in-house suite of strategic computer aided network simulation and decision support tools to improve the management of power systems. This paper describes a preliminary research investigation to access the feasibility of using an Artificial Intelligence (AI) method to predict and detect faults at an early stage in power systems. To achieve this goal, an AI based detector has been developed to monitor and predict faults at an early stage on particular sections of power systems. The detector only requires external measurements taken from the input and output nodes of the power system. The AI detection system is capable of rapidly predicting a malfunction within the system . Simulation will normally take place using equivalent circuit representation. Artificial Neural Networks (ANNs) are used to construct a hierarchical feed-forward structure which is the most important component in the fault detector. Simulation of a transmission line (2-port  circuit ) has already been carried out and preliminary results using this system are promising. This approach provided satisfactory results with accuracy of 95% or higher.

Catalog

Books, media, physical & digital resources
See catalog results