RESEARCH SUMMARY

We have implemented two machine-learning models of object recognition by human observers. Both models capture two hallmarks of human performance: (1) spatial frequency channels and (2) effects of font complexity. One model is a Convolutional Neural Network (ConvNet), and the other is a texture statistics model followed by a simple classifier. With appropriate training and hyper-parameters, both models account for spatial frequency channels and effects of letter complexity.

 

Moore Sloan Poster Research Project