![]() ![]() Well, you can use a bitgrid (which is an array of 4 input/4 output bit lookup tables, clocked like the colors of a chess board) to implement the game of life. Now consider creating real, physical wafer-scale hardware that computes this way usingĪ whole-wafer "Conway chip". That fall to 0 weights can simply "die" and be reborn as something else in a circuit being The Neural Net can adapt because weighted logic "cells" Each "neuron" is a combinatorial logic "cell" that computes a weightedįunction of its inputs and bias. ![]() Now consider what happens when we try to architecture a Neural Network on thisĬellular FPGA. What are the new Conway's rules for such a simulation? But this FPGA can grow and adapt dynamically The cells have "memory" as they continue to assert their output bit at every clock tick.Ĭells can be born, live, die, or change their lookup table value based on the rules. Assume that the clock signal is not universal but that many clocksĮxist that control a subset of the cells (clock domains). Indeed,īy ganging together multiple cells any combinatorial logic function could be implemented.Ī second generalization is to create "clock domains" so each cell only computes when a A cell could compute an XOR, AND, OR, NOT, 0, 1, etc. Thus a cell could output compute any possibleĬombination of 2 bits. Would be an exact simulation of Conway's game.Ī generalization of the game would be that each cell can accept 2 input bits and wouldĬompute a bit output bit using a lookup table. Clearly one canĬreate a game of life simulation where each 2-bit table either computes a 0 or a 1. Now assume that each cell can be implemented as a 2-bit lookup table. ![]() It has already been shown that Conway's game of life is Turing complete. The gates change based on a universal "clock", i.e. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |