Circuit architecture with biased randomization
AssigneeAmazon Technologies, Inc.
InventorsRandy Huang, Ron Diamant
Life of this patent
Estimating the term…
Abstract
Disclosed herein are techniques for classifying data with a data processing circuit. In one embodiment, the data processing circuit includes a probabilistic circuit configurable to generate a decision at a pre-determined probability, and an output generation circuit including an output node and configured to receive input data and a weight, and generate output data at the output node for approximating a product of the input data and the weight. The generation of the output data includes propagating the weight to the output node according a first decision of the probabilistic circuit. The probabilistic circuit is configured to generate the first decision at a probability determined based on the input data.
Claims17
A method comprising:
- receiving a fractional input and a propagation candidate at a probabilistic circuit, the probabilistic circuit including a probabilistic switching circuit and a propagation switch;
- forwarding the fractional input to the probabilistic switching circuit to cause the probabilistic switching circuit to set a comparison threshold value based on the fractional input and to generate a switch signal with a predetermined logical state at a probability based on the comparison threshold value;
- triggering the probabilistic switching circuit to generate the switch signal;
- providing the switch signal to the propagation switch;
- and
- propagating, using the propagation switch and based on a logical state of the switch signal, the propagation candidate to generate a classifier output.
An integrated circuit device comprising:
- a probabilistic switching circuit configured to:
- receive a fractional input;
- set a comparison threshold value based on the fractional input;
- generate a switch signal with a predetermined logical state at a probability based on the comparison threshold value;
- and
- output the switch signal;
- and
- a propagation switch coupled to the probabilistic switching circuit, wherein the propagation switch is configured to:
- receive the switch signal from the probabilistic switching circuit;
- receive a propagation candidate;
- and
- propagate, based on a logical state of the switch signal, the propagation candidate to generate a classifier output.
A non-transitory computer-readable medium comprising instructions that, when executed by a processor, cause the processor to perform operations comprising:
- receiving a fractional input and a propagation candidate at a probabilistic circuit, the probabilistic circuit including a probabilistic switching circuit and a propagation switch;
- forwarding the fractional input to the probabilistic switching circuit to cause the probabilistic switching circuit to set a comparison threshold value based on the fractional input and to generate a switch signal with a predetermined logical state at a probability based on the comparison threshold value;
- triggering the probabilistic switching circuit to generate the switch signal;
- providing the switch signal to the propagation switch;
- and
- propagating, using the propagation switch and based on a logical state of the switch signal, the propagation candidate to generate a classifier output.
Dependencies are inferred from the claim text.