23 June 2023
Kwabena Boahen
Departments of Bioengineering, Electrical Engineering and Computer Science
Stanford University
Artificial intelligence now advances by performing twice as many floating-point multiplications every two months, but the semiconductor industry tiles twice as many multipliers on a chip every two years. Moreover, the returns from tiling these multipliers ever more densely now diminish because signals must travel relatively farther and farther. Although travel can be shortened by stacking multipliers tiled in two dimensions in the third dimension, such a solution acutely reduces the available surface area for dissipating heat. We can transcend this thermal constraint 3D chips face by moving away from learning with synapses to learning with dendrites. Synaptocentric learning weights synaptic inputs precisely, whereas dendrocentric learning orders synaptic inputs meticulously along a short stretch of dendrite. With the help of a computational model of a dendrite and a conceptual model of a ferroelectric device that emulates it, I will illustrate how dendrocentric learning artificial intelligence — or synthetic intelligence for short — could run not with megawatts in the cloud but rather with watts on a smartphone.