N. Intrator
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
N. Intrator has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Leon N. Cooper
Department of Physics, Brown University, Providence, RI 02912;
3 shared publications - Daniel Remondini
Department of Physics and Astronomy (DIFA), University of Bologna, Bologna, Italy
2 shared publications - Gastone C. Castellani
Physics Department, DIMORFIPA, CIG, Bologna University, Bologna 40137, Italy
2 shared publications H Shouval
2 shared publicationsH. Shouval
2 shared publicationsBrian S. Blais
1 shared publication
Latest Publications
- 1 July 2003
- Published by MIT Press in Neural Computation
- Vol. 15 (7) , 1621-1640
The Effect of Noise on a Class of Energy-Based Learning Rules
We study the selectivity properties of neurons based on BCM and kurtosis energy functions in a general case of noisy high-dimensional input space. The proposed approach, which is used for characterization of the stable states, can be generalized to a whole class of energy functions. We characterize the critical noise levels beyond which the selectivity is destroyed. We also perform a quantitative analysis of such transitions, which shows interesting dependency on data set size. We observe that the robustness to noise of the BCM neuron (Bienenstock, Cooper, & Munro, 1982; Intrator & Cooper, 1992) increases as a function of dimensionality. We explicitly compute the separability limit of BCM and kurtosis learning rules in the case of a bimodal input distribution. Numerical simulations show a stronger robustness of the BCM rule for practical data set size when compared with kurtosis.
- 1 July 2003
- Published by MIT Press in Neural Computation
- Vol. 15 (7) , 1621-1640
The Effect of Noise on a Class of Energy-Based Learning Rules
We study the selectivity properties of neurons based on BCM and kurtosis energy functions in a general case of noisy high-dimensional input space. The proposed approach, which is used for characterization of the stable states, can be generalized to a whole class of energy functions. We characterize the critical noise levels beyond which the selectivity is destroyed. We also perform a quantitative analysis of such transitions, which shows interesting dependency on data set size. We observe that the robustness to noise of the BCM neuron (Bienenstock, Cooper, & Munro, 1982; Intrator & Cooper, 1992) increases as a function of dimensionality. We explicitly compute the separability limit of BCM and kurtosis learning rules in the case of a bimodal input distribution. Numerical simulations show a stronger robustness of the BCM rule for practical data set size when compared with kurtosis.
- 30 June 2002
- Published by Elsevier in Neurocomputing
- Vol. 44-46, 591-595
Optimal spontaneous activity in neural network modeling
- 30 June 2002
- Published by Elsevier in Neurocomputing
- Vol. 44-46, 591-595
Optimal spontaneous activity in neural network modeling
- 1 May 1999
- Vol. 10 (2) , 111-21
Solutions of the BCM learning rule in a network of lateral interacting nonlinear neurons.
We introduce a new method for obtaining the fixed points for neurons that follow the BCM learning rule. The new formalism, which is based on the objective function formulation, permits analysis of a laterally connected network of nonlinear neurons and allows explicit calculation of the fixed points under various network conditions. We show that the stable fixed points, in terms of the postsynaptic activity, are not altered by the lateral connectivity or nonlinearity. We show that the lateral connectivity alters the probability of attaining different states in a network of interacting neurons. We further show the exact alteration in presynaptic weights as a result of the neuronal nonlinearity.
- 1 May 1999
- Vol. 10 (2) , 111-21
Solutions of the BCM learning rule in a network of lateral interacting nonlinear neurons.
We introduce a new method for obtaining the fixed points for neurons that follow the BCM learning rule. The new formalism, which is based on the objective function formulation, permits analysis of a laterally connected network of nonlinear neurons and allows explicit calculation of the fixed points under various network conditions. We show that the stable fixed points, in terms of the postsynaptic activity, are not altered by the lateral connectivity or nonlinearity. We show that the lateral connectivity alters the probability of attaining different states in a network of interacting neurons. We further show the exact alteration in presynaptic weights as a result of the neuronal nonlinearity.
- 1 May 1999
- Published by Taylor & Francis in Network: Computation in Neural Systems
- Vol. 10 (2) , 111-121
Solutions of the BCM learning rule in a network of lateral interacting nonlinear neurons
- 1 May 1999
- Published by Taylor & Francis in Network: Computation in Neural Systems
- Vol. 10 (2) , 111-121
Solutions of the BCM learning rule in a network of lateral interacting nonlinear neurons
- Open Access
- 1 October 1998
- Published by MIT Press in Neural Computation
- Vol. 10 (7) , 1797-1813
Receptive Field Formation in Natural Scene Environments: Comparison of Single-Cell Learning Rules
We study several statistically and biologically motivated learning rules using the same visual environment: one made up of natural scenes and the same single-cell neuronal architecture. This allows us to concentrate on the feature extraction and neuronal coding properties of these rules. Included in these rules are kurtosis and skewness maximization, the quadratic form of the Bienenstock-Cooper-Munro (BCM) learning rule, and single-cell independent component analysis. Using a structure removal method, we demonstrate that receptive fields developed using these rules depend on a small portion of the distribution. We find that the quadratic form of the BCM rule behaves in a manner similar to a kurtosis maximization rule when the distribution contains kurtotic directions, although the BCM modification equations are computationally simpler.
- 1 October 1998
- Published by MIT Press in Neural Computation
- Vol. 10 (7) , 1797-1813
Open AccessReceptive Field Formation in Natural Scene Environments: Comparison of Single-Cell Learning Rules
We study several statistically and biologically motivated learning rules using the same visual environment: one made up of natural scenes and the same single-cell neuronal architecture. This allows us to concentrate on the feature extraction and neuronal coding properties of these rules. Included in these rules are kurtosis and skewness maximization, the quadratic form of the Bienenstock-Cooper-Munro (BCM) learning rule, and single-cell independent component analysis. Using a structure removal method, we demonstrate that receptive fields developed using these rules depend on a small portion of the distribution. We find that the quadratic form of the BCM rule behaves in a manner similar to a kurtosis maximization rule when the distribution contains kurtotic directions, although the BCM modification equations are computationally simpler.
- 10 December 1997
- Published by Defense Technical Information Center (DTIC)
Receptive Field Formation in Natural Scene Environments: Comparison of Single Cell Learning Rules
We study several statistically and biologically motivated learning rules using the same visual environment, one made up of natural scenes, and the same single cell neuronal architecture. This allows us to concentrate on the feature extraction and neuronal coding properties of these rules. Included in these rules are kurtosis and skewness maximization, the quadratic form of the BCM learning rule, and single cell ICA. Using a structure removal method, we demonstrate that receptive fields developed using these rules depend on a small portion of the distribution. We find that the quadratic form of the BCM rule behaves in a manner similar to a kurtosis maximization rule when the distribution contains kurtotic directions, although the BCM modification equations are computationally simpler.
- 10 December 1997
- Published by Defense Technical Information Center (DTIC)
Receptive Field Formation in Natural Scene Environments: Comparison of Single Cell Learning Rules
We study several statistically and biologically motivated learning rules using the same visual environment, one made up of natural scenes, and the same single cell neuronal architecture. This allows us to concentrate on the feature extraction and neuronal coding properties of these rules. Included in these rules are kurtosis and skewness maximization, the quadratic form of the BCM learning rule, and single cell ICA. Using a structure removal method, we demonstrate that receptive fields developed using these rules depend on a small portion of the distribution. We find that the quadratic form of the BCM rule behaves in a manner similar to a kurtosis maximization rule when the distribution contains kurtotic directions, although the BCM modification equations are computationally simpler.