The research advances concerning the typical architectures of convolutional neural
networks (CNNs) as well as their optimizations are analyzed and elaborated in detail in this …

The success of machine learning algorithms generally depends on data representation, and
we hypothesize that this is because different representations can entangle and hide more or …

Automated melanoma recognition in dermoscopy images is a very challenging task due to
the low contrast of skin lesions, the huge intraclass variation of melanomas, the high degree …

Very deep convolutional networks with hundreds of layers have led to significant reductions
in error on competitive benchmarks. Although the unmatched expressiveness of the many …

Kwang Gi Kim https://doi. org/10.4258/hir. 2016.22. 4.351 ing those who are beginning their
careers in deep learning and artificial intelligence research. The other target audience …

Theoretical and empirical evidence indicates that the depth of neural networks is crucial for
their success. However, training becomes more difficult as depth increases, and training of …

There is plenty of theoretical and empirical evidence that depth of neural networks is a
crucial ingredient for their success. However, network training becomes more difficult with …

Inventors have long dreamed of creating machines that think. Ancient Greek myths tell of
intelligent objects, such as animated statues of human beings and tables that arrive full of …

It has long been conjectured that hypotheses spaces suitable for data that is compositional
in nature, such as text or images, may be more efficiently represented with deep hierarchical …

Learning algorithms related to artificial neural networks and in particular for Deep Learning
may seem to involve many bells and whistles, called hyper-parameters. This chapter is …