reynolds@park.bu.edu (John Reynolds) (05/15/91)
The following note appeared in Volume 7, Issue 15 of Neuron-Digest: >I am looking for articles on the application of ART in supervised > ========== >learning situations. Can anyone help? >Thanks. >Kok Wee Gan >Department of Information Systems and Computer Science >National University of Singapore >bitnet address: gankw@nusdiscs.bitnet >[[Editor's Note: Perhaps someone from Boston U. could answer in a future >Digest? I thought ART was, strictly speaking, unsupervised only. -PM]] Gail Carpenter, Stephen Grossberg and I have recently introduced a supervised ART system, called ARTMAP, that autonomously learns to classify arbitrarily many, arbitrarily ordered vectors into recognition categories based on predictive success. Tested on a benchmark machine learning database in both on-line and off-line simulations, the ARTMAP system learns orders of magnitude more quickly, efficiently, and accurately than alternative algorithms. It achieves these properties by using an internal controller that conjointly maximizes predictive generalization and minimizes predictive error by linking predictive success to category size on a trial-by-trial basis, using only local operations. It was presented last week at the Wang Institute Conference on Neural Networks for Vision and Image Processing, and it will also appear at the upcoming IJCNN meeting (Lecture, Friday, July 12, Session 2, 9:10 - 9:30AM). It will be discussed in an upcoming issue of Neural Networks (Neural Networks, 4, in press), and it is now available as Technical Report CAS/CNS-TR-91-001. Write to the following address: Boston University Center for Adaptive Systems and Cognitive and Neural Systems Department 111 Cummington Street, Rm. 244 Boston, MA 02215 or contact Cindy Suchta (cindy@park.bu.edu) to request a copy of the technical report. -John Reynolds