This work introduces minimum accumulative degeneracy, a variant of the degenerate primer design problem, which is particularly useful when a large number of sequences are to be covered by a set of restricted number of primers. A primer set, which is designed on a minimum accumulative degeneracy basis, especially helps to reduce nonspecific PCR amplification of undesired DNA fragments, as fewer ...

Two major classes of optimization techniques are the deterministic gradient methods and stochastic annealing methods. Gradient descent algorithms are greedy algorithms, which are subject to a fundamental limitation of being easily trapped in local minima of the cost function. Hopfield networks usually converge to a local minimum of energy function. Because of its deterministic input-output rela...

We introduce a method for the efficient design of a Boltzmann machine (or a Hopfield net) that computes an arbitrary given Boolean function f . This method is based on an efficient simulation of acyclic circuits with threshold gates by Boltzmann machines. As a consequence we can show that various concrete Boolean functions f that are relevant for classification problems can be computed by scala...

We introduce a method for the efficient design of a Boltzmann machine (or a Hopfield net) that computes an arbitrary given Boolean function f . This method is based on an efficient simulation of acyclic circuits with threshold gates by Boltzmann machines. As a consequence we can show that various concrete Boolean functions f that are relevant for classification problems can be computed by scala...

We introduce a method for the efficient design of a Boltzmann machine (or a Hopfield net) that computes an arbitrary given Boolean function / . TÈis method is based on an efficient simulation of acyclic circuits with threshold gates by Boltzmann machines. As a consequence u¡e can show that various concrete Boolean functions f tha| are relevant for classification problems can be computed by scal...

This note rectifies a logical gap in the derivation of the asynchronous Boltzmann machine learning algorithm.

We present a connectionist approach for solving Tangram puzzles. Tangram is an ancient Chinese puzzle where the object is to decompose a given figure into seven basic geometric figures. One connectionist approach models Tangram pieces and their possible placements and orientations as connectionist neuron units which receive excitatory connections from input units defining the puzzle and lateral...

Modelling the real world complexity of music is a challenge for machine learning. We address the task of modeling melodic sequences from the same music genre. We perform a comparative analysis of two probabilistic models; a Dirichlet Variable Length Markov Model (Dirichlet-VMM) and a Time Convolutional Restricted Boltzmann Machine (TC-RBM). We show that the TC-RBM learns descriptive music featu...