This paper presents and compares results for three types of connectionist networks on perceptual learning tasks: [A] Multi-layered converging networks of neuron-like units, with e...
We present a new subgoal-based method for automatically creating useful skills in reinforcement learning. Our method identifies subgoals by partitioning local state transition gra...
Local features have proven very useful for recognition.
Manifold learning has proven to be a very powerful tool in
data analysis. However, manifold learning application for
imag...
Abstract— Learning inverse kinematics has long been fascinating the robot learning community. While humans acquire this transformation to complicated tool spaces with ease, it is...
Abstract. Incremental learning of sensorimotor transformations in high dimensional spaces is one of the basic prerequisites for the success of autonomous robot devices as well as b...