Pulsed neural networks are networks of spiking neurons, which represent an entirely new class of artificial neurons. The paper presents an overview of pulsed neural networks, including the structure, function and available training mechanisms for networks of spiking neurons.

This paper highlights differences between this model,“first generation” threshold gates, and “second generation” sigmoid activation gates, and
examines current research into pulsed neural networks and the use of temporal information in neural processing.
Lastly, it summarizes individual research efforts toward the end of using pulsed neural networks to identify computer users by the cadence of their keystrokes.
Access the paper here.
By Daniel R. Kunkle & Chadd Merrigan
Computer Science Dept.
College of Computing and Information Sciences
Rochester Institute of Technology

Post to Twitter Post to Yahoo Buzz Post to Delicious Post to Digg Post to Facebook Post to Google Buzz Post to LinkedIn Post to Slashdot Post to StumbleUpon Post to Technorati