ANN Processor Cluster Safety Mechanisms for Error Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Artificial neural networks (ANNs) face challenges in ensuring functional safety, particularly in critical applications like autonomous vehicles, due to their complexity and susceptibility to random errors and adversarial strategies, which existing solutions do not fully address.
Innovation Solution
The development of a neural network processor that incorporates multiple safety mechanisms, including redundancy by design, spatial mapping, self-tuning procedures, and error detection mechanisms, to provide system-level safety and immunity against failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple safety mechanisms are incorporated into the ANN processor, then reliability is improved, but device complexity increases
Solution Approach 1:
The processor is divided into multiple clusters, each independently capable of processing tensor data. This segmentation allows safety mechanisms to be applied at the cluster level rather than requiring system-wide complexity, isolating failures to individual clusters while maintaining overall system functionality.
Solution Approach 2:
The patent implements redundant copying of computational logic within and between clusters. Each cluster contains duplicate computational pathways that can be activated for error detection and correction, providing reliability through copying without requiring complete system redundancy.
2Reliability
If error detection mechanisms are added to the neural network processor, then reliability is improved, but manufacturing complexity increases
Solution Approach 1:
Error detection functionality is merged directly into the existing computational clusters rather than being implemented as separate external components. The safety mechanisms share computational resources and infrastructure with the primary processing functions, reducing overall manufacturing complexity while maintaining detection capabilities.
3Reliability
If redundancy by design is implemented in the processor, then immunity to failures is improved, but device complexity increases
Solution Approach 1:
Redundancy is implemented locally within each cluster rather than uniformly across the entire processor. Each cluster independently possesses error detection and correction capabilities through localized redundant pathways, providing failure immunity without requiring complex system-wide redundancy management.
Data Source
AI summary
Novel and useful system and methods of several functional safety mechanisms for use in an artificial neural network (ANN) processor. The mechanisms can be deployed individually or in combination to provide a desired level of safety in neural networks. Multiple strategies are applied involving redundancy by design, redundancy through spatial mapping as well as self-tuning procedures that modify static (weights) and monitor dynamic (activations) behavior. The various mechanisms of the present invention address ANN system level safety in situ, as a system level strategy that is tightly coupled with the processor architecture. The NN processor incorporates several functional safety concepts which reduce its risk of failure that occurs during operation from going unnoticed. The mechanisms function to detect and promptly flag and report the occurrence of an error with some mechanisms capable of correction as well. The safety mechanisms cover data stream fault detection, software defined redundant allocation, cluster interlayer safety, cluster intralayer safety, layer control unit (LCU) instruction addressing, weights storage safety, and neural network intermediate results storage safety.