How Deep Learning Software Works
Neural networks learn by example to make judgement-based decisions
Deep learning software trains on a set of labeled images that represent a part’s known features, anomalies, and classes—much like a human inspector would be trained. A supervised training period teaches the system to recognize explicit defects. For defects that come in multiple forms, the system trains itself in unsupervised mode to learn the normal appearance of an object, including its significant but tolerable variations.
Based on these representative images, the software creates its reference model. It is an iterative process of constant improvement, during which parameters can be adjusted and the outcome validated until the model works as desired. During runtime, software extracts data from a new set of images, and its neural networks localize parts, extract anomalies, and classify them.
For more information on Cognex products: