Learn More
Interconnect power is dynamic power dissipation due to switching of interconnection capacitances. This paper describes the characterization of interconnect power in a state-of-the-art high-performance microprocessor designed for power efficiency. The analysis showed that interconnect power is over 50% of the dynamic power. Over 90% of the interconnect power(More)
This paper proposes a new pruning method based on merging neurons with similar functional behavior which is defined by the internal representations of each neuron for the entire training set. Classification of neurons by their functional behavior with respect to the input vectors provides a powerful tool for pruning neurons and connections, thus reducing(More)
A bs t rac t. We propose a new hyb rid genetic bac k pr opagati on training algorithm based on a unique functional mat chin g recombinati on method. T he method is used t o evolve pop ulations of neur al networks and provides versatility in network ar chitecture and activation functions. Net reorganization and reconstruction is carried out prior t o genet(More)
P opul at ion diversit y loss is a major obstacle in applying geneti c algorit hms to optimizat ion problems, which often results in population degenerati on and pr emature convergence. The diversity changes caused by t hree nat ur al-select ion strategies-comparing new offspring t o t he least-fit spec imen in t he populati on , to one of t he parents, and(More)
  • 1