Few-Shot Class-Incremental Learning (FSCIL) enables machine learning systems to expand
their inference capabilities to new classes using only a few labeled examples, without …

In the field of machine learning, deep neural networks have become the
inescapablereference for a very large number of problems. These systems are made of an …

In this paper, we tackle the problem of incrementally learning a classifier, one example at a
time, directly on chip. To this end we propose an efficient hardware implementation of a …

In dynamic environments, the inputs to machine learning models may exhibit statistical
changes over time, through what is called concept drift. Incremental training can allow …

Interestingly, when I began my PhD back in 2008, neural networks were almost unanimously
considered obsolete. Their inaptitude to solve real world problems, added to the …

Abstract Deep Neural Networks (DNNs) are widely used in various application domains and
achieve remarkable results. However, DNNs require a large number of computations for …