Convolutional highways are deep networks based on multiple stacked convolutional layers for feature preprocessing. We introduce an evolutionary algorithm (EA) for optimization of the structure and hyperparameters of convolutional highways and demonstrate the potential of this optimization setting on the well-known MNIST data set. The (1+1)-EA employs Rechenberg’s mutation rate control and a nic...

Multiword expressions (MWEs) are lexical items that can be decomposed into multiple component words, but have properties that are unpredictable with respect to their component words. In this paper we propose the first deep learning models for token-level identification of MWEs. Specifically, we consider a layered feedforward network, a recurrent neural network, and convolutional neural networks...

In this paper, we construct new sequences of asymptotically good convolutional codes (AGCC). These sequences are obtained from sequences of transitive, self-orthogonal and self-dual algebraic geometry (AG) codes attaining the Tsfasman-Vladut-Zink bound. Furthermore, by applying the techniques of expanding, extending, puncturing, direct sum, the 〈u|u+ v〉 construction and the product code constru...

Lung nodule classification is a class imbalanced problem because nodules are found with much lower frequency than non-nodules. In the class imbalanced problem, conventional classifiers tend to be overwhelmed by the majority class and ignore the minority class. We therefore propose cascaded convolutional neural networks to cope with the class imbalanced problem. In the proposed approach, multi-s...

This study is an analysis of scene recognition in a pre-trained convolutional network, to evaluate the information the network uses to distinguish scene categories. We are particularly interested in how the network is related to various areas in the human brain that are involved in different modes of scene recognition. Results of several experiments suggest that the convolutional network relies...

We propose a convolutional encoder over the finite ring of integers modulo pk ,Zpk , where p is a prime number and k is any positive integer, to generate a space-time convolutional code (STCC). Under this structure, we prove three properties related to the generator matrix of the convolutional code that can be used to simplify the code search procedure for STCCs over Zpk . Some STCCs of large d...

Recently a new construction of run length limited block error control codes based on control matrices of linear block codes was proposed. In this paper a similar construction for obtaining trellis run length limited error control codes from convolutional codes is described. The main advantage of it, beyond its simplicity is that it does not require any additional redundancy except the one which...

In this paper, we propose a novel face alignment method using single deep network (SDN) on existing limited training data. Rather than using a max-pooling layer followed one convolutional layer in typical convolutional neural networks (CNN), SDN adopts a stack of 3 layer groups instead. Each group layer contains two convolutional layers and a maxpooling layer, which can extract the features hie...

We present a multi-modal Deep Neural Network (DNN) approach for bird song identification. The presented approach takes both audio samples and metadata as input. The audio is fed into a Convolutional Neural Network (CNN) using four convolutional layers. The additionally provided metadata is processed using fully connected layers. The flattened convolutional layers and the fully connected layer o...

The success of convolutional networks in learning problems involving planar signals such as images is due to their ability to exploit the translation symmetry of the data distribution through weight sharing. Many areas of science and egineering deal with signals with other symmetries, such as rotation invariant data on the sphere. Examples include climate and weather science, astrophysics, and ...