We consider the problem of learning Bayes Net structures for related tasks. We present a formalism for learning related Bayes Net structures that takes advantage of the similarity between tasks by biasing toward learning similar structures for each task. Heuristic search is used to find a high scoring set of structures (one for each task), where the score for a set of structures is computed in ...

We consider the problem of learning Bayes Net structures for related tasks. We present an algorithm for learning Bayes Net structures that takes advantage of the similarity between tasks by biasing learning toward similar structures for each task. Heuristic search is used to find a high scoring set of structures (one for each task), where the score for a set of structures is computed in a princ...

The Pathalyzer is a program for analyzing large-scale signal transduction networks. Reactions and their substrates and products are represented as transitions and places in a safe Petri net. The user can interactively specify goal states, such as activation of a particular protein in a particular cell site, and the system will automatically find and display a pathway that results in the goal st...

Article history: Received 14 September 2011 Received 20 September 2012 Accepted 4 December 2012 Available online 26 December 2012

Deep Convolutional Neural Networks (CNNs) are capable of learning unprecedentedly effective features from images. Some researchers have struggled to enhance the parameters’ efficiency using grouped convolution. However, the relation between the optimal number of convolutional groups and the recognition performance remains an open problem. In this paper, we propose a series of Basic Units (BUs) ...

Most learning algorithms assume that a data set is given initially. We address the common situation where data is not available initially, but can be obtained, at a cost. We focus on learning Bayesian belief networks (BNs) over discrete variables. As such BNs are models of probabilistic distributions, we consider the “generative” challenge of learning the parameters for a fixed structure, that ...

This paper proposes a method of defining and analysing robotic tasks using Petri Nets. Both the robot behaviors and environment are modelled using Generalized Stochastic Petri Nets (GSPNs). Each action is modelled separately and composed with others to provide a complete task execution. The use of Petri Nets allows the qualitative and quantitative analysis of the task execution.