A Winner-Take-All Circuit with Controllable Soft Max Property

I describe a silicon network consisting of a group of excitatory neurons and a global inhibitory neuron. The output of the inhibitory neuron is normalized with respect to the input strengths. This output models the normalization property of the wideeld directionselective cells in the y visual system. This normalizing property is also useful in any system where we wish the output signal to code only the strength of the inputs, and not be dependent on the number of inputs. The circuitry in each neuron is equivalent to that in Lazzaro's winner-take-all (WTA) circuit with one additional transistor and a voltage reference. Just as in Lazzaro's circuit, the outputs of the excitatory neurons code the neuron with the largest input. The di erence here is that multiple winners can be chosen. By varying the voltage reference of the neuron, the network can transition between a soft-max behavior and a hard WTA behavior. I show results from a fabricated chip of 20 neurons in a 1.2 m CMOS technology.