Stochastic Logic Circuits for Fast Probability Sampling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional approaches to solving stochastic problems are inefficient due to their reliance on deterministic computers, which require high-precision floating-point arithmetic and significant processing resources, leading to unnecessary time and resource consumption.
Innovation Solution
The development of stochastic digital circuits that generate samples according to a probability distribution, allowing for the efficient solution of stochastic problems by producing uncertain, probabilistic outputs based on conditional probability distributions, enabling parallel operation and reducing the need for precise calculations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional deterministic computers are used to solve stochastic problems with high-precision floating-point arithmetic, then measurement precision is improved, but productivity deteriorates due to substantial processing resources and time consumption
Solution Approach 1:
The patent replaces conventional deterministic mechanical computing systems with a stochastic computing system that uses probabilistic logic elements. Instead of using deterministic floating-point arithmetic to compute probabilities, the system uses stochastic logic circuits that naturally produce probabilistic outputs through random processes, substituting a fundamentally different computational paradigm that is inherently more efficient for stochastic problems
Solution Approach 2:
The patent changes the fundamental parameter of computation from deterministic precision-based calculation to stochastic probability-based sampling. By transforming the problem from requiring high-precision floating-point arithmetic to requiring probabilistic sample generation, the system achieves comparable accuracy with significantly reduced computational resources and time
2Reliability
If conventional deterministic computers are used to solve stochastic problems, then reliability is improved through precise calculation, but device complexity increases due to substantial processing resources required
Solution Approach 1:
The patent replaces complex deterministic computing hardware with simpler stochastic logic elements that inherently produce reliable probabilistic results. The substitution eliminates the need for complex floating-point arithmetic units, large memory systems, and extensive processing resources while maintaining solution reliability through the natural probabilistic behavior of the stochastic logic system
Solution Approach 2:
The patent employs numerous simple, low-cost stochastic logic elements that can be easily fabricated and replaced. Instead of using a few complex deterministic processing units, the system uses many simple probabilistic elements whose collective behavior produces reliable results, trading individual component complexity for system-level reliability
Data Source
AI summary
Circuits that solve stochastic problems and techniques for operating them. These natively stochastic circuits may produce samples from probability distributions of interest for particular stochastic problems, and may be combined together in any suitable way to yield potential solutions to stochastic problems. In some implementations, the stochastic circuits may generate samples from conditional probability distributions conditioned on input data provided to the stochastic circuits. The circuits may be constructed from multiple interconnected stochastic subcircuits such that a circuit may produce a sample from a joint probability distribution, or from a marginal distribution of a joint distribution. These circuits may be used to implement stochastic sampling algorithms to solve stochastic processes, and may include stochastic subcircuits that operate concurrently.