Room temperature magnetic quantum cellular automata

All computers process information electronically. A processing method based on magnetism is reported here, in which networks of interacting submicrometer magnetic dots are used to perform logic operations and propagate information at room temperature. The logic states are signaled by the magnetization direction of the single-domain magnetic dots; the dots couple to their nearest neighbors through magnetostatic interactions. Magnetic solitons carry information through the networks, and an applied oscillating magnetic field feeds energy into the system and serves as a clock. These networks offer a several thousandfold increase in integration density and a hundredfold reduction in power dissipation over current microelectronic technology.

Probabilistic graphical models for semi-supervised traffic classification

Traffic classification using machine learning continues to be an active research area. The majority of work in this area uses off-the-shelf machine learning tools and treats them as black-box classifiers. This approach turns all the modelling complexity into a feature selection problem. In this paper, we build a problem-specific solution to the traffic classification problem by designing a custom probabilistic graphical model. Graphical models are a modular framework to design classifiers which incorporate domain-specific knowledge. More specifically, our solution introduces semi-supervised learning which means we learn from both labelled and unlabelled traffic flows. We show that our solution performs competitively compared to previous approaches while using less data and simpler features. Copyright © 2010 ACM.

Probabilistic inference for fast learning in control

A novel framework is provided for very fast model-based reinforcement learning in continuous state and action spaces. It requires probabilistic models that explicitly characterize their levels of condence. Within the framework, exible, non-parametric models are used to describe the world based on previously collected experience. It demonstrates learning on the cart-pole problem in a setting where very limited prior knowledge about the task has been provided. Learning progressed rapidly, and a good policy found after only a small number of iterations.