Comparison of Typically Trained Neural Net (Left and Centre) Vs. Heuristically Trained (IMAGE)

University of Toronto Faculty of Applied Science & Engineering

Comparison of Typically Trained Neural Net (Left and Centre) Vs. Heuristically Trained

Caption

This figure compares a traditionally trained algorithm to Aarabi and Guo's heuristically trained neural net. The left and centre columns show an aggressive and conservative image-recognition algorithm trained to recognized human hair, compared to the more precise heuristically trained algorithm at right.

Credit

Courtesy: IEEE Trans NN & LS

Usage Restrictions

None

License

Licensed content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.