A Subtler Silicon Cell for Neural Networks
Sunny Bains · Science · 1997
Neural nets traditionally consist of so-called sigmoidal neurons, circuits that add up incoming signals until they reach a fixed threshold and then fire themselves. But a University of Pennsylvania research has now developed so-called bifurcation neurons, which switch between different modes of operation depending on subtler factors, including the interaction between many incoming signals and the neuron9s recent history. This work could yield neural nets with more complex behavior than has been seen in networks to date, such as the ability to see, recognize, and even react to the world in real time.