D. Barber and P. Sollich. Online learning from finite training sets. In D. Saad, editor, On-Line Learning in Neural Networks, pages 279--302. Cambridge U.P., 1998.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....during training is technically a much harder problem and has received much attention recently. Most of the work has focussed on simple or linear learning rules [5, 6, 7] or different kinds of approximations, such as Fokker Planck approaches [8, 9, 10, 11] and Gaussian local field distributions [12]. Exact work on non linear learning rules has drawn heavily on techniques from the spin glass and disordered systems community (for an early overview of these techniques see e.g. 13] The generating functional technique was Supervised Learning with Restricted Training Sets 2 used to study the ....

D. Barber and P. Sollich. Online learning from finite training sets. In D. Saad, editor, On-Line Learning in Neural Networks, pages 279--302. Cambridge U.P., 1998.

....during training is technically a much harder problem and has received much attention recently. Most of the work has focussed on simple or linear learning rules [5, 6, 7] or di#erent kinds of approximations, such as Fokker Planck approaches [8, 9, 10, 11] and Gaussian local field distributions [12]. Exact work on non linear learning rules has drawn heavily on techniques from the spin glass and disordered systems community (for an early overview of these techniques see e.g. 13] The generating functional technique was Supervised Learning with Restricted Training Sets 2 used to study the ....

D. Barber and P. Sollich. Online learning from finite training sets. In D. Saad, editor, On-Line Learning in Neural Networks, pages 279--302. Cambridge U.P., 1998.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC