Stochastic gradient descent (SGD) uses approximate gradients estimated from subsets of the training data and updates the parameters in an online fashion. This learning framework i...
Abstract. In 2002, algebraic attacks using overdefined systems of equations have been proposed as a potentially very powerful cryptanalysis technique against block ciphers. However...
In this paper we describe an online/incremental linear binary classifier based on an interesting approach to estimate the Fisher subspace. The proposed method allows to deal with ...
Alessandro Rozza, Gabriele Lombardi, Marco Rosa, E...
With the shrinking of technology feature sizes, the share of leakage in total power consumption of digital systems continues to grow. Traditional dynamic voltage scaling (DVS) fail...
Abstract—Coping with outliers contaminating dynamical processes is of major importance in various applications because mismatches from nominal models are not uncommon in practice...
Shahrokh Farahmand, Georgios B. Giannakis, Daniele...