Hava T. Siegelmann

Support Vector Clustering Asa Ben-Hur (2008)

Biowulf Technologies, David Horn, Hava T. Siegelmann, Vladimir Vapnik, Nello Critianini, John Shawe-taylor, ...

We present a novel clustering method using the approach of support vector machines. Data points are mapped by means of a Gaussian kernel to a high dimensional feature space, where we search for the...

Support Vector Clustering Asa Ben-Hur (2008)

Biowulf Technologies, David Horn, Hava T. Siegelmann, Vladimir Vapnik, Nello Critianini, John Shawe-taylor, ...

We present a novel clustering method using the approach of support vector machines. Data points are mapped by means of a Gaussian kernel to a high dimensional feature space, where we search for the...

Posttranscriptional regulation of BK channel splice variant stability by miR-9 underlies neuroadaptation to alcohol (2008)

Pietrzykowski, Andrzej Z., Friesen, Ryan M., Martin, Gilles E., Puig, Sylvie I., Nowak, Cheryl L., Wynne, Patricia M., ...

Tolerance represents a critical component of addiction. The large-conductance calcium- and voltage-activated potassium channel (BK) is a well-established alcohol target, and an important element in...

INFORMATION CODING AND NEURAL COMPUTING (2008)

J. Pedro Neto, Hava T. Siegelmann, J. Félix Costa

Abstract. In [2,5] it is showed that programming languages can be translated into recurrent neural nets. Implementation of programming languages in neural nets turns to be not only theoretical...

Adaptive Multi-modal Sensors (2008)

Kyle I. Harrington, Hava T. Siegelmann

Abstract. Compressing real-time input through bandwidth constrained connections has been studied within robotics, wireless sensor networks, and image processing. When there are bandwidth constraints...

Adaptive Multi- Modal Sensors (2008)

Kyle I. Harrington, Hava T. Siegelmann

Real world applications of robotics and artificial intelligence sometimes require input from unknown environments (Pederson, 2001). For such cases an internal representation of the environment must...

Support Vector Clustering Asa Ben-Hur (2008)

Biowulf Technologies, David Horn, Hava T. Siegelmann, Vladimir Vapnik, Nello Critianini, John Shawe-taylor, ...

We present a novel clustering method using the approach of support vector machines. Data points are mapped by means of a Gaussian kernel to a high dimensional feature space, where we search for the...

On a Learnability Question Associated to Neural Networks with Continuous Activations (Extended Abstract) z (2008)

Bhaskar Dasgupta Y, Hava T. Siegelmann, Eduardo Sontag

This paper deals with learnability of concept classes de ned by neural networks, showing the hardness of PAC-learning (in the complexity, not merely information-theoretic sense) for networks with a...

Overcoming selective ensemble averaging: unsupervised identi"cation of event-related brain potentials (2007)

Daniel H. Lange, Hava T. Siegelmann, Hillel Pratt, Gideon F. Inbar

We present a novel approach to the problem of Event Related Potential (ERP) identification, based on a competitive Artificial Neural Net (ANN) structure. Our approach dismisses the need for stimulus-...

Turing Universality of Neural Nets (Revisited) (2007)

J. Pedro Neto, Hava T. Siegelmann, J. Félix Costa

. We show how to use recursive function theory to prove Turing universality of finite analog recurrent neural nets, with a piecewise linear sigmoid function as activation function. We emphasize the...

Computational Power of Neural Networks: A Kolmogorov Complexity Characterization (2007)

José L. Balcázar, Ricard Gavaldà, Hava T. Siegelmann

The computational power of neural networks depends on properties of the real numbers used as weights. We focus on networks restricted to compute in polynomial time, operating on boolean inputs....

Computational Power of Neural Networks: A Kolmogorov Complexity Characterization (2007)

Jos'e Balc'azar, Hava T. Siegelmann

The computational power of recurrent neural networks is shown to depend ultimately on the amount of information encoded in the constants (weights) of the network. The information is characterized by...

On the Computational Power of Faulty and Asynchronous Neural Networks (2007)

Hava T. Siegelmann

This paper deals with finite size recurrent neural networks which consist of general (possibly with cycles) interconnections of evolving processors. Each neuron may assume real activation value. We...

Concise Papers_____________________________ Multiprocessor Document Allocation: A Genetic Algorithm Approach (2007)

Ophir Frieder, Senior Member, Hava T. Siegelmann

Abstract—We formally define the Multiprocessor Document Allocation Problem (MDAP) and prove it to be computationally intractable (NP Complete). Once it is shown that MDAP is NP Complete, we...

Verifying Properties of Neural Networks (2007)

Pedro Rodrigues, J. Félix Costa, Hava T. Siegelmann

Abstract. In the beginning of nineties, Hava Siegelmann proposed a new computational model, the Artificial Recurrent Neural Network (ARNN), and proved that it could perform hypercomputation. She also...

Journal of Machine Learning Research 2 (2001) 125-137 Submitted 3/04; Published 12/01 Support Vector Clustering (2007)

Biowulf Technologies, David Horn, Hava T. Siegelmann, Vladimir Vapnik, Nello Critianini, ...

We present a novel clustering method using the approach of support vector machines. Data points are mapped by means of a Gaussian kernel to a high dimensional feature space, where we search for the...

Support Vector Clustering Asa Ben-Hur (2007)

Biowulf Technologies, David Horn, Hava T. Siegelmann, Vladimir Vapnik, Nello Critianini, John Shawe-taylor, ...

We present a novel clustering method using the approach of support vector machines. Data points are mapped by means of a Gaussian kernel to a high dimensional feature space, where we search for the...

Symbolic processing in neural networks (2003)

Neto,João Pedro, Siegelmann,Hava T., Costa,J.Félix

In this paper we show that programming languages can be translated into recurrent (analog, rational weighted) neural nets. Implementation of programming languages in neural nets turns to be not only...

Symbolic processing in neural networks (2003)

João Pedro Neto, Hava T. Siegelmann, J. Félix Costa

Abstract. In this paper we show that programming languages can be translated into recurrent (analog, rational weighted) neural nets. Implementation of programming languages in neural nets turns to be...

A theory of complexity for continuous time systems (2002)

Asa Ben-hur, Hava T. Siegelmann

We present a model of computation with ordinary differential equations (ODEs) which converge to attractors that are interpreted as the output of a computation. We introduce a measure of complexity...

Probabilistic analysis of the phase space flow for linear programming (2001)

Ben-Hur, Asa, Feinberg, Joshua, Fishman, Shmuel, Siegelmann, Hava T.

The phase space flow of a dynamical system leading to the solution of Linear Programming (LP) problems is explored as an example of complexity analysis in an analog computation framework. An ensemble...

Probabilistic analysis of a differential equation for linear programming (2001)

Ben-Hur, Asa, Feinberg, Joshua, Fishman, Shmuel, Siegelmann, Hava T.

In this paper we address the complexity of solving linear programming problems with a set of differential equations that converge to a fixed point that represents the optimal solution. Assuming a...

Support vector clustering (2001)

Asa Ben-hur, David Horn, Hava T. Siegelmann, Vladimir Vapnik

We present a novel clustering method using the approach of support vector machines. Data points are mapped by means of a Gaussian kernel to a high dimensional feature space, where we search for the...

A support vector method for clustering (2001)

Asa Ben-hur, David Horn, Hava T. Siegelmann, Vladimir Vapnik

We present a novel method for clustering using the support vector machine approach. Data points are mapped to a high dimensional feature space, where support vectors are used to define a sphere...

Symbolic Processing in Neural Networks (2001)

Joao Pedro Neto, Hava T. Siegelmann, J. Felix Costa

. In this paper we show that programming languages can be translated on recurrent (analog, rational weighted) neural nets. Implementation of programming languages in neural nets turns to be not only...

A support vector method for clustering (2001)

Asa Ben-hur, Hava T. Siegelmann, David Horn, Vladimir Vapnik

We present a novel method for clustering using the support vector machine approach. Data points are mapped to a high dimensional feature space, where support vectors are used to define a sphere...

Discontinuities in Recurrent Neural Networks (1998)

Ricard Gavalda, Hava T. Siegelmann

This paper studies the computational power of various discontinuous real computational models that are based on the classical analog recurrent neural network (ARNN). This ARNN consists of finite...

Turing Universality of Neural Nets (revisited (1997)

J. Pedro Neto, Hava T. Siegelmann, J. Félix Costa

Abstract. We show how to use recursive function theory to prove Turing universality of finite analog recurrent neural nets, with a piecewise linear sigmoid function as activation function. We...

Analog Computation with Dynamical Systems (1997)

Hava T. Siegelmann, Shmuel Fishman

This paper presents a theory that enables to interpret natural processes as special purpose analog computers. Since physical systems are naturally described in continuous time, a definition of...

Computational capabilities of recurrent NARX neural networks (1997)

Hava T. Siegelmann, Bill G. Horne, C. Lee Giles

Recently, fully connected recurrent neural networks have been proven to be computationally rich --- at least as powerful as Turing machines. This work focuses on another network which is popular in...

Computational Capabilities of Recurrent NARX Neural Networks (1995)

Siegelmann, Hava T., Horne, Bill G., Giles, C. Lee

Recently, fully connected recurrent neural networks have been proven to be computationally rich --- at least as powerful as Turing machines. This work focuses on another network which is popular in...

Computational Capabilities of Recurrent NARX Neural Networks (1995)

Siegelmann, Hava T., Horne, Bill G., Giles, C. Lee

Recently, fully connected recurrent neural networks have been proven to be computationally rich --- at least as powerful as Turing machines. This work focuses on another network which is popular in...

On the Complexity of Training Neural Networks with Continuous Activation Functions (1995)

Bhaskar Dasgupta, Hava T. Siegelmann, Eduardo Sontag

We deal with computational issues of loading a fixed-architecture neural network with a set of positive and negative examples. This is the first result on the hardness of loading a simple 3-node...

On the complexity of training neural networks with continuous activation functions (1995)

Bhaskar Dasgupta, Eduardo Sontag, Hava T. Siegelmann

We deal with computational issues of loading a fixed-architecture neural network with a set of positive and negative examples. This is the first result on the hardness of loading a simple 3-node...

and (1995)

Jeremy Schiff, Hava T. Siegelmann

Abstract. We show how to associate a computation to certain 2 degree of freedom hamiltonian systems, and use this to discuss the level of complexity of certain problems in the dynamics of these...

On the Computational Power of Neural Nets (1995)

Hava T. Siegelmann, Eduardo D. Sontag

This paper deals with finite size networks which consist of interconnections of synchronously evolving processors. Each processor updates its state by applying a “sigmoidal ” function to a linear...

Analog Computation Via Neural Networks (1994)

Hava T. Siegelmann, Eduardo D. Sontag

We pursue a particular approach to analog computation, based on dynamical systems of the type used in neural networks research. Our systems have a fixed structure, invariant in time, corresponding to...

On the Intractability of Loading Neural Networks (1994)

Bhaskar Dasgupta, Hava T. Siegelmann, Eduardo D. Sontag

Introduction Neural networks have been proposed as a tool for machine learning. In this role, a network is trained to recognize complex associations between inputs and outputs that were presented...

Analog Computation Via Neural Networks (1994)

Hava T. Siegelmann, Eduardo D. Sontag

We pursue a particular approach to analog computation, based on dynamical systems of the type used in neural networks research. Our systems have a fixed structure, invariant in time, corresponding to...

On a Learnability Question Associated to Neural Networks with Continuous Activations (1994)

Bhaskar Dasgupta, Hava T. Siegelmann, Eduardo Sontag

) z Bhaskar DasGupta y Department of Computer Science University of Minnesota Minneapolis, MN 55455-0159 dasgupta@cs.umn.edu Hava T. Siegelmann Department of Computer Science Bar-Ilan University...

Analog computation via neural networks (1994)

Hava T. Siegelmann, Eduardo D. Sontag

We pursue a particular approach to analog computation, based on dynamical systems of the type used in neural networks research. Our systems have a fixed structure, invariant in time, corresponding to...

On the Complexity of Training Neural Networks with Continuous Activation Functions (1993)

Bhaskar Dasgupta, Hava T. Siegelmann, Eduardo D. Sonntag

We deal with computational issues of loading a fixed-architecture neural network with a set of positive and negative examples. This is the first result on the hardness of loading networks which do...

Neural Networks with Real Weights: Analog Computational Complexity (1992)

Hava T. Siegelmann, Hava T. Siegelmann, Eduardo D. Sontag, Eduardo D. Sontag

We pursue a particular approach to analog computation, based on dynamical systems of the type used in neural networks research. Our systems have a fixed structure, invariant in time, corresponding to...

Integrating implicit answers with object-oriented queries (1991)

Hava T. Siegelmann

Queries in object-oriented datab;Lqcs are formulated against a class and retrieve instnnccls of the class sat,is-fying a certain predicate on the att,riblltes of the class. The presence of a class...

On The Computational Power Of Neural Nets (1991)

Hava T. Siegelmann, Eduardo D. Sontag

This paper deals with finite size networks which consist of interconnections of synchronously evolving processors. Each processor updates its state by applying a "sigmoidal" function to a...

Turing Computability With Neural Nets (1991)

Hava T. Siegelmann, Eduardo D. Sontag

. This paper shows the existence of a finite neural network, made up of sigmoidal neurons, which simulates a universal Turing machine. It is composed of less than 10 5 synchronously evolving...

On The Computational Power Of Neural Nets (1991)

Hava T. Siegelmann, Eduardo D. Sontag

This paper deals with the simulation of Turing machines by neural networks. Such networks are made up of interconnections of synchronously evolving processors, each of which updates its state...

On The Computational Power Of Neural Nets (1991)

Hava T. Siegelmann, Eduardo D. Sontag

This paper deals with finite size networks which consist of interconnections of synchronously evolving processors. Each processor updates its state by applying a "sigmoidal" function to a...

Turing Computability with Neural Nets (1991)

Hava T. Siegelmann, Eduardo D. Sontag

Abstract. This paper shows the existence of a finite neural network, made up of sigmoidal neurons, which simulates a universal Turing machine. It is composed of less than 10 5 synchronously evolving...

accepted on the recommendation of (1975)

Fabian Roth, Prof Dr, Rodney J. Douglas, Prof Dr, Hava T. Siegelmann

I want to thank Rodney Douglas, my thesis advisor and inspirational source very much for his great support. His guidance was very gentle and he was very careful not to disturb my own intuition and...

Transcriptional Responses to Estrogen and Progesterone in Mammary Gland Identify Networks Regulating p53 Activity

Lu, Shaolei, Becker, Klaus A., Hagen, Mary J., Yan, Haoheng, Roberts, Amy L., Mathews, Lesley A., ...

Estrogen and progestins are essential for mammary growth and differentiation but also enhance the activity of the p53 tumor suppressor protein in the mammary epithelium. However, the pathways by...