Although traditional financial factors, such as value, growth, and momentum, have become
common practice in the construction of smart beta indexes, the question whether …

We describe symmetries of feedforward networks in terms of their corresponding groups,
which naturally act on and partition weight space. This leads to an algorithm that generates …

We demonstrate that neural-network classi ers are able to signi cantly enhance lowlevel
segmentation of medical images. Minimum-error-rate or Bayesian a posteriori probabilities of …

Rapidly growing cities and human activities change the environment and are accompanied
by some drawbacks. Sustainable remedies are needed to protect the environment and the …

We study symmetries of feedforward networks in terms of their corresponding groups. We
nd that these groups naturally act on and partition weight space into disjunct domains. We …

We study symmetries of feedforward networks in terms of their corresponding groups and
find that these groups naturally act on and partition weight space. We specify an algorithm to …

Urban climatologists have moved smoothly towards urban geometry meso-scales as obstruction
between buildings, streets, and urban environment. Urban climatologists and designers …

The usage of location information of weight vectors can help to overcome deficiencies of
gradient‐based learning for neural networks. We study the non‐trivial structure of weight space, …

Derivative instruments are financial engineering tools. They are linked to underlying financial
instruments and are often better suited to manage exposure to risk. A number of tools exist …

Background Peripheral endothelial dysfunction (ED) quantified by the determination of flow-mediated
dilation (FMD%) of the brachial artery with the use of high-resolution ultrasound is …