Knowledge Builders

A simple workflow…

A Knowledge Builder (KB) is an application which lets you train the neurons using annotated data sets and verify that the training is appropriate and sufficient to deliver recognition with acceptable accuracy and throughput for your application. The outputs are knowledge files which can then be loaded on systems equipped with neurons to reproduce the same recognition. Regardless of the type of data to comprehend, the Knowledge Builder features diagnostics guiding you through the process of learning for the best throughput and accuracy.

Collect

Collect data coming from your sensors and visualize for annotation

Learn

Select examples, extract discriminating features and teach to the neurons.

Validate

Verify the recognition of new datasets

Apply

Export the knowledge of the neurons to the deployment platform

NeuroMem Knowledge Builder

  • Pattern learning and classification, agnostic to data type
  • Windows-based
  • Simulates a NeuroMem network or interface to NeuroStack and other compatible hardware
  • Import pattern vectors with their ground truth category (csv format)
  • Learn training sets and produce diagnostics (supervised and unsupervised)
  • Classify testing sets and produce diagnostics (rbf, knn, decision rules)
  • Survey the knowledge, save and restore
  • Read more
  • Interested in a trial version?

Image Knowledge Builder®

  • Image learning and recognition
  • Windows-based
  • Simulates a NeuroMem network or interface to NeuroStack and other compatible hardware
  • Supervised learning from user-annotations, Unsupervised learning
  • Search for objects or anomalies in new images
  • Produce meta data, maps of categories, models and confidence levels
  • Display, save and restore the knowegde built by the neurons
  • Read more
  • Interested in a trial version?

Image Knowledge Builder is a registered trademark of General Vision Inc.

gv