Abstract: Introduced here is an artificial intelligence system designed for machine learning. The system may be based on a neuromorphic computational model that learns spatial patterns in inputs using data structures called Sparse Distributed Representations (SDRs) to represent the inputs. Moreover, the system can generate signatures for these SDRs, and these signatures may be used to create definitions of classes or subclasses for classification purposes.

Abstract: Introduced here are integrated circuits (also referred to as “chips”) that can be implemented in a neural processing unit. At a high level, the goal of these chips is to provide higher performance for machine learning algorithms than conventional processing units would. To accomplish this, the neural processing unit can include multiple computing components, each of which is able to independently determine the overlap between encoded data provided as input and values stored in a memory.

Abstract: A single shared processing path is used as contexts are switched during processing. Each unique context is processed using a corresponding unique pipeline. If a pipeline that is executing under one context stalls, processing is switched in the shared processing path to another pipeline that is executing under second context. New pipelines are enabled for execution by borrowing a clock cycle from the currently executing pipeline. In some cases contexts are assigned various relative priority levels. In one case a context switching microprocessor is used in a communication engine portion of a system-on-a-chip communication system.