#### Filter Results:

#### Publication Year

2004

2016

#### Publication Type

#### Co-author

#### Key Phrase

#### Publication Venue

Learn More

Two neural networks that are trained on their mutual output synchronize to an identical time dependant weight vector. This novel phenomenon can be used for creation of a secure cryptographic secret-key using a public channel. Several models for this cryptographic system have been suggested, and have been tested for their security under different… (More)

- Andreas Ruttor
- 2006

Neural networks can synchronize by learning from each other. For that purpose they receive common inputs and exchange their outputs. Adjusting discrete weights according to a suitable learning rule then leads to full synchronization in a finite number of steps. It is also possible to train additional neural networks by using the inputs and outputs generated… (More)

We present a novel approach to inference in conditionally Gaussian continuous time stochastic processes, where the latent process is a Markovian jump process. We first consider the case of jump-diffusion processes, where the drift of a linear stochastic differential equation can jump at arbitrary time points. We derive partial differential equations for… (More)

MOTIVATION
Stress response in cells is often mediated by quick activation of transcription factors (TFs). Given the difficulty in experimentally assaying TF activities, several statistical approaches have been proposed to infer them from microarray time courses. However, these approaches often rely on prior assumptions which rule out the rapid responses… (More)

Neural cryptography is based on synchronization of tree parity machines by mutual learning. We extend previous key-exchange protocols by replacing random inputs with queries depending on the current state of the neural networks. The probability of a successful attack is calculated for different model parameters using numerical simulations. The results show… (More)

We introduce a nonparametric approach for estimating drift functions in systems of stochastic differential equations from sparse observations of the state vector. Using a Gaussian process prior over the drift as a function of the state vector, we develop an approximate EM algorithm to deal with the unobserved, latent dynamics between observations. The… (More)

We consider the problem of Bayesian inference for continuous-time multi-stable stochastic systems which can change both their diffusion and drift parameters at discrete times. We propose exact inference and sampling methodologies for two specific cases where the discontinuous dynamics is given by a Poisson process and a two-state Markovian switch. We test… (More)

We present an approximate inference approach to parameter estimation in a spatio-temporal stochastic process of the reaction-diffusion type. The continuous space limit of an inference method for Markov jump processes leads to an approximation which is related to a spatial Gaus-sian process. An efficient solution in feature space using a Fourier basis is… (More)

We study a model of a stochastic process with unobserved parameters which suddenly change at random times. The possible parameter values are assumed to be from a finite but unknown set. Using a Chinese restaurant process prior over parameters we develop an efficient MCMC procedure for Bayesian inference. We demonstrate the significance of our approach with… (More)

Neural cryptography Two partners A and B want to exchange a secret message over a public channel. A encrypts the message to protect the content against an opponent E listening to the communication. But B usually needs A's key for decryption. If a secure channel for the key is not available, A and B must use a key exchange protocol to generate a common key.… (More)