The paper presents a new algorithm to build a feedforward neural network with a single hidden layer. The algorithm starts with 1 hidden unit and the new hidden units are added to the network only if they improve the classification accuracy of the network on the cross-validation samples. The initialization of the weights and bias is done using Nguyen-Widrow method and the network is trained with...

Restricted Boltzmann machines were developed using binary stochastic hidden units. These can be generalized by replacing each binary unit by an infinite number of copies that all have the same weights but have progressively more negative biases. The learning and inference rules for these “Stepped Sigmoid Units” are unchanged. They can be approximated efficiently by noisy, rectified linear units...

CA 125 is an antigenic determinant expressed by greater than 80% of nonmucinous epithelial ovarian carcinomas. An immunoradiometric assay has been developed using a murine monoclonal antibody (OC125) to quantitate CA 125 in human serum. This immunoradiometric assay was optimized for specificity, sensitivity, and performance characteristics. Using a simultaneous immunoradiometric assay, the mean...

CA 125 is an antigenic determinant expressed by greater than 80% of nonmucinous epithelial ovarian carcinomas. An immunoradiometric assay has been developed using a murine mono clonal antibody (OC125) to quantitate CA 125 in human serum. This immunoradiometric assay was optimized for specificity, sensitivity, and performance characteristics. Using a simultane ous immunoradiometric assay, the me...

In a We use statistical mechanics to study generalization in large committee machines. For an architecture with nonoverlapping receptive fields a replica calculation yields the generalization error in the limit of a large number of hidden units. For continuous weights the generalization error falls off asymptotically inversely proportional to Q, the number of training examples per weight. For b...

Maloney and Ahumada [9] have proposed a network learning algorithm that allows the visual system to compensate for irregularities in the positions of its photoreceptors. Weights in the network are adjusted by a process tending to make the internal image representation translationinvariant. We report on the behavior of this translation-invariance algorithm calibrating a visual system that has lo...

We introduce DropConnect, a generalization of Dropout (Hinton et al., 2012), for regularizing large fully-connected layers within neural networks. When training with Dropout, a randomly selected subset of activations are set to zero within each layer. DropConnect instead sets a randomly selected subset of weights within the network to zero. Each unit thus receives input from a random subset of ...

Corpus-based speech synthesis performance depends on the skill to model and represent appropriately all the characteristics of the speech units that serve as a basis for concatenation. Although there is usually general agreement in the set of essential features (fundamental frequency, duration, power and phonetic context), it is still an open question the proper way of modelling them and consid...