Digital processing has the advantage of versatility – the utter ubiquity of computer technology is a testament to that. But digital logic has to use lots of bits to represent large ranges of values; perhaps some applications – spam filtering, for instance, or pattern analysis – would run better and faster on a system that allowed for analogue values “in the raw”, so to speak?
Lyric’s innovation is to use analogue signals instead of digital ones, to allow probabilities to be encoded directly as voltages. Their probability gates represent zero probability as 0 V, and certainty as VDD. But unlike digital logic, for which these are the only options, Lyric’s technology allows probabilities between 0 and 1 to use voltages between 0 and VDD. Each probabilistic bit (“pbit”) stores not an exact value, but rather, the probability that the value is 1. The technology allows a resolution of about 8 bits; that is, they can discriminate between about 28 = 256 different values (different probabilities) between 0 and VDD.
By creating circuits that can operate directly on probabilities, much of the extra complexity of digital circuits can be eliminated. Probabilistic processors can perform useful computations with just a handful of pbits, with a drastic reduction in the number of transistors and circuit complexity as a result.
This could so easily be an excerpt from a Rudy Rucker story… or a Neal Stephenson novel, for that matter.
There have been analog computers before, and there are certainly some in operation now, for signal processing and other applications. And yes, every so often, someone proposes using them for some application or another.
The trouble is that so far, analog computers have often been more complex than the digital computer that they would replace, both in theory of construction and implementation. Bits are simple: on or off, 0 or 1. This makes it easier to make integrated circuits with very large numbers of decision gates with high degrees of reliability and repeatability, like microprocessors.
If one p-bit takes one of 256 states, then its state can be represented by 8 digital bits, and you can use a general-purpose digital processor to represent that, building a state machine ( i.e. writing software) to present the effects of what each of those states represents, and what state it should transition to, given its inputs. This becomes an easy exercise, rather than the much more difficult design and construction of specialized analog hardware for a particular task.
I do wish them the best, but so far, no one has been able to come up with an idea which can compete with digital solid-state.