This is cool and I understand the RAM emulation with gated attention but how does the CPU emulation wor? You add layers that are then trained to predict outputs while interpreting RISC instructions?
This is cool and I understand the RAM emulation with gated attention but how does the CPU emulation wor? You add layers that are then trained to predict outputs while interpreting RISC instructions?
I think they describe the CPU using the weights? I mean in some sense a CPU can be viewed as just a function, right?
At each cycle, a cpu is a simple function from the previous state to the next state.