Since many domains are constantly evolving, the associated domain specific languages (DSL) inevitably have to evolve too, to retain their value. But the evolution of a DSL can be ...
We study online learning in an oblivious changing environment. The standard measure of regret bounds the difference between the cost of the online learner and the best decision in...
Cognitive scientists and developmental psychologists have suggested that development in perceptual, motor and memory functions of human infants as well as adaptive evaluation by ca...
We introduce flexible algorithms that can automatically learn mappings from images to actions by interacting with their environment. They work by introducing an image classifier i...
In this work we present a novel approach for learning nonhomogenous textures without facing the unlearning problem. Our learning method mimics the human behavior of selective lear...