Abstract: A computation system using a neural network model includes: processor cores; a computation allocation unit that determines a computation processor core; and an anomaly detection unit that detects an anomaly in the computation processor core. The computation allocation unit causes an anomaly detection processor core to execute an anomaly detection computation. When a difference between a first computation result of a basic computation and a second computation result of the anomaly detection computation satisfies an allowance condition, the anomaly detection unit determines that the computation processor core and the anomaly detection processor core are normal. When the difference does not satisfy the allowance condition, the anomaly detection unit determines that at least a part of the computation processor core and the anomaly detection processor core has anomaly.

Abstract: A multi-view imaging apparatus of an embodiment includes a plurality of imaging units each including an image sensor and a memory configured to store therein image data taken by the image sensor, the imaging units being daisy-chain connected to each other in order to send the image data, and also includes an interface unit connected to a lowermost imaging unit, the interface unit being configured to output pieces of image data taken by the plurality of imaging units to an outside. The imaging units each add own-stage data to data outputted from an upper-stage imaging unit, and output the resultant data to a lower-stage imaging unit.