This w orkshows how to train the activation function in neuro-wavelet parametric modeling and how this improves performance in a number of modeling, classi cation and forecasting.
Valentina Colla, Mirko Sgarbi, Leonardo Maria Reyn...
We introduce the notion of functional stream derivative, generalising the notion of input derivative of rational expressions (Brzozowski 1964) to the case of stream functions over...
Bisubmodularity extends the concept of submodularity to set functions with two arguments. We show how bisubmodular maximization leads to richer value-of-information problems, usin...
We introduce a new cryptographic tool: multiset hash functions. Unlike standard hash functions which take strings as input, multiset hash functions operate on multisets (or sets). ...
Dwaine E. Clarke, Srinivas Devadas, Marten van Dij...
Conventions for conducting work with groupware are essential. They include rules for how the groupware functionality should be used for communication about work, for how data shoul...