Anomaly detection is an important problem that has been well-studied within diverse
research areas and application domains. The aim of this survey is two-fold, firstly we present …

Abstract The recent Attend-Infer-Repeat (AIR) framework marks a milestone in structured
probabilistic modeling, as it tackles the challenging problem of unsupervised scene …

This paper proposes a new classification model called logistic circuits. On MNIST and
Fashion datasets, our learning algorithm outperforms neural networks that have an order of …

The productivity rate of a manufacturing process is limited by the speed of any measurement
processes at the quality control stage. Fast and effective in-line measurements are required …

We give conditions under which convolutional neural networks (CNNs) define valid sum-
product networks (SPNs). One subclass, called convolutional SPNs (CSPNs), can be …

In recent years, the weight binarized neural network (BNN) technology has made great
progress. However, neural networks with binarized inputs and binarized weights suffer from …

For many online customers, clothing image recognition is used mainly in computer vision for
fashion applications. Recognition of the clothing image and identification of their style and …

In this chapter, general aspects about optical in-process surface topography measurement
will be discussed, including clear definitions of terms related to types of measurement. The …

Probabilistic sentential decision diagrams are logic circuits where the inputs of disjunctive
gates are annotated by probability values. They allow for a compact representation of joint …

Variational autoencoders (VAEs) have received considerable attention, since they allow us
to learn expressive neural density estimators effectively and efficiently. However, learning …