D.E. Rumelhart, G.E. Hinton, and J.L. McClelland. Learning internal representations. In D.E. Rumelhart and J.L. McClelland, editors, Parallel Distributed Processing, pages 318--362, Cambridge, Massachusetts, 1986. MIT Press.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....0.1 85.3 Sigma 7.4 0.08 Training Time Training Time (secs) t test Dataset LP PQM p Wine 14.3 Sigma 1.2 5.2 Sigma 1.5 0:00001 Iris 5.8 Sigma 0.7 0.4 Sigma 0. 1 0:00001 Glass 231.2 Sigma 25.2 12.4 Sigma 25.1 0:00001 Image s 610.5 Sigma 107.0 96.9 Sigma 13.1 0:00001 algorithm [20], one successful stopping criteria is to reserve part of the training set as a tuning set, and to stop the algorithm when the accuracy on the tuning set decreases [14, p. 41 42] We plan to investigate in the future the use of such tuning sets to halt the algorithm. The training times for the ....

D.E. Rumelhart, G.E. Hinton, and J.L. McClelland. Learning internal representations. In D.E. Rumelhart and J.L. McClelland, editors, Parallel Distributed Processing, pages 318--362, Cambridge, Massachusetts, 1986. MIT Press.

.... separation is a natural extension of linear separation which, for a long time, has been known to be equivalent to the polynomial time solution of a single linear program [9, 13, 26, 5] Linear separation is also equivalent to separation by Rosenblatt s perceptron or linear threshold unit (LTU) [24, 25, 11] (see Figure 2) However most problems are not linearly separable. For example the simple Minsky Papert exclusive or classical problem [20] is not linearly separable, but is bilinearly separable. It can be solved by a neural network with 2 layers of linear threshold units [25, 18] see Figure 3) ....

....unit (LTU) 24, 25, 11] see Figure 2) However most problems are not linearly separable. For example the simple Minsky Papert exclusive or classical problem [20] is not linearly separable, but is bilinearly separable. It can be solved by a neural network with 2 layers of linear threshold units [25, 18](see Figure 3) Other methods of separation by more than one plane, for example multisurface methods (MSM) of pattern separation, have also been proposed [14, 5, 6] and extensively used for medical diagnosis [29, 17, 5] MSM which has been shown to be equivalent to a feed forward neural network ....

[Article contains additional citation context not shown here]

D.E. Rumelhart, G.E. Hinton, and J.L. McClelland. Learning internal representations. In D.E. Rumelhart and J.L. McClelland, editors, Parallel Distributed Processing, pages 318--362, Cambridge, Massachusetts, 1986. MIT Press.

....avoid this problem, heuristics are applied to prune decisions from the tree [29, 22] In this paper, optimization techniques are used to minimize the error of the entire decision tree. Our global approach is analogous to the widely used back propagation algorithm for constructing neural networks [31]. For a neural network, one specifies an initial structure, the number of units, and their interconnections. An error function which measures the error of the neural network is then constructed. The decisions in a multivariate decision tree are the same as linear threshold units in a neural ....

D.E. Rumelhart, G.E. Hinton, and R.J. Williams. Learning internal representations. In D.E. Rumelhart and J.L. McClelland, editors, Parallel Distributed Processing, pages 318--362, Cambridge, Massachusetts, 1986. MIT Press.

No context found.

D. E. Rumelhart, G. E. Hinton, and J. L. McClelland, Learning Internal Representations, in Parallel Distributed Processing, D. E. Rumelhart and J. L. McClelland (Eds.), Vol. I, M.I.T. Press, Cambridge, Massachusetts 1969, pp. 318-362.

No context found.

D. Rumelhart, G.E. Hinton and R. J. Williams. Learning internal representation, in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, 1, Foundations, MIT Press, Cambridge, MA, 1986.

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