B.-T. Zhang. An incremental learning algorithm that optimizes network size and sample size in one trial. Proceedings of the IEEE International Conference on Neural Networks (ICNN'94), pages 215--220, 1994.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....method like pruning. However, instead of removing connections, it first restricts the growth of their weights by giving them a tendency to decay to zero, that is, the connection would disappear unless reinforced [20] Selective Learning with Flexible Neural Architectures (SELF) was introduced by [47]. It works on both the data and the network structure. Starting with a small training set and a small feed forward network, the training set is increased incrementally after training. If training does not converge, hidden units are then added to the network to increase its capacity. In biological ....

B.-T. Zhang. An incremental learning algorithm that optimizes network size and sample size in one trial. Proceedings of the IEEE International Conference on Neural Networks (ICNN'94), pages 215--220, 1994.

....In the diagram, empty circles represent input hidden output units while a black dot refers to a connection between units. 3.1.1 Simple Hidden Units There are two main categories. The first category is based on the multi layer perceptron (MLP) like the dynamic node creation network [3] and [39, 49, 66, 86, 91, 104, 106]. The hidden unit transfer function in a MLP is of the form: g(x) OE(a T x ) where OE is usually the sigmoidal function OE(z) 1= 1 e Gammaz ) The other category is based on the radial basis function network (RBFN) like the Gaussian potential function network (GPFN) 57] the ....

....units to learn. This is commonly used in many algorithms, such as PPL type algorithms [28, 43, 82, 83, 98] 7 A function space approach to analyzing the learning algorithm of RAN is developed in [46] cascade correlation architecture and its variants [18, 59, 58, 91, 104, 105] and methods in [86, 106]. Experimentally, this strategy allows the network to learn faster. Moreover, the hidden units, acting as feature detectors, are never cannibalized once built. They are available from that time on for producing outputs or more complex features. However, because the parameters of the hidden units ....

B.T. Zhang. An incremental learning algorithm that optimizes network size and sample size in one trial. In Proceedings of the IEEE International Conference on Neural Networks, volume 1, pages 215--220, Orlando, Florida, USA, June 1994.

....a taxonomy of the constructive algorithms surveyed in this paper. Details of individual categories will be discussed in the following sections, which are named after their representative algorithms. A. Dynamic Node Creation Constructive algorithms in this category [36] 64] 77] 80] 84] [88] are variants of the dynamic node creation (DNC) network proposed by Ash [84] Here, the state transition mapping is single valued. Sigmoid hidden units are added one at a time, and are always added to the same hidden layer. The whole network must be re trained completely after each hidden unit ....

B.T. Zhang, "An incremental learning algorithm that optimizes network size and sample size in one trial," in Proceedings of the IEEE International Conference on Neural Networks, Orlando, Florida, USA, June 1994, vol. 1, pp. 215--220.

....are dealing with active learning in which the set of training data can be provided only one after the another and also uses the intermediate learned results for deciding on the next best sample. Recently, a lot of work on these lines are being carried out, some of them being the papers by Zhang[16] and Jutten[3] However, most of them, though being incremental in the nature of addition of training data or increase in the number of hidden units etc. almost always involves re learning or re training with the addition of information or units. In this paper, the concept of truly incremental ....

Zhang,B. T. \An incremental learning algorithm that optimizes network size and sample size in one trial", Proc. of ICNN'94(Orlando, Florida), pp.215-220, (June 28 - July 2, 1994) .

No context found.

B. Zhang, "An incremental learning algorithm that optimizes network size and sample size in one trial," in Proc. IEEE Int. Conf. Neural Netw., 1994, pp. 215--220.

No context found.

Zhang, B. T. (1994). An incremental learning algorithm that optimizes network size and sample size in one trial. Proceedings of International Conference on Neural Networks (pp. 215--220). Orlando, USA.

No context found.

Zhang, B. T. (1994). An incremental learning algorithm that optimizes network size and sample size in one trial. Proceedings of International Conference on Neural Networks (pp. 215-220). Orlando, USA.

No context found.

Zhang, B. T. (1994). An incremental learning algorithm that optimizes network size and sample size in one trial. Proceedings of International Conference on Neural Networks

No context found.

Zhang, B. T. (1994). An incremental learning algorithm that optimizes network size and sample size in one trial. Proceedings of International Conference on Neural Networks

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