DNNs as Layers of Cooperating Classifiers

Distribution as a Set of Cooperating Aspects

This paper describes work done in the Aspect-oriented Programming (AOP) community, whose goal is to simplify development of programs by enabling the application of the principle of separation of concerns where this was previously not possible. The AOP community has performed work relating to a number of aspects of particular significance to the eld of distributed computing: coordination, replic...

Network Evolution for DNNs

Interpolants as Classifiers

We show how interpolants can be viewed as classifiers in supervised machine learning and the advantages this view provides. First, we are able to use off-the-shelf classification techniques, in particular support vector machines, for computing interpolants. Second, since classification algorithms are predictive, the interpolants computed via classification have a good chance of being generalize...

Improving accuracy of Winograd convolution for DNNs

Modern deep neural networks (DNNs) spend a large amount of their execution time computing convolutions. Winograd's minimal algorithm for small convolutions can greatly reduce the number of arithmetic operations. However, a large reduction in floating point (FP) operations in these algorithms can result in significantly reduced FP accuracy of the result. In this paper we propose several methods ...

Decision trees as possibilistic classifiers

This paper addresses the classification problem with imperfect data. More precisely, it extends standard decision trees to handle uncertainty in both building and classification procedures. Uncertainty here is represented by means of possibility distributions. The first part investigates the issue of building decision trees from data with uncertain class values by developing a non-specificity b...