Shenshen Gu

Learn More
In this paper, the K-Winners-Take-All (KWTA) problem is formulated equivalently to a linear program. A recurrent neural network for KWTA is then proposed for solving the linear programming problem. The KWTA network is globally convergent to the optimal solution of the KWTA problem. Simulation results are further presented to show the effectiveness and(More)
We propose a new algorithm based on a chaotic neural network to solve the attributed relational graph matching problem, which is an NP-hard problem of prominent importance in pattern recognition research. From some detailed analyses, we reach the conclusion that, unlike the conventional Hopfield neural networks for the attributed relational graph matching(More)
  • Shenshen Gu
  • 2010
In the field of signal processing, many problems can be formulated as optimization problems. And most of these optimization problem can be further described in a formal form, that is binary quadratic programming problem(BQP). However, solving the BQP is proved to be NP-hard. Due to this reason, many novel algorithms have been proposed in order to improve(More)
In this paper, we proposed a recurrent neural network to compute the distance between a point to an ellipsoid in n spatial dimensions. So far, the problem used to be solved by traditional mathematical algorithms, which is either too slow in computing time or too one-sided in applications. Our proposed neural network, which makes use of a cost gradient(More)
K-Winner-take-all (kWTA) is an operation that identifies the k largest inputs from multiple input signals. It has important applications in machine learning, statistics filtering and sorting, etc. As the number of inputs becomes large and the selection process should be operated in real time, parallel algorithms are desirable. For these reasons, many neural(More)