Very encouraging considering Google’s track record for making these kinds of things opensource. Having this tool should help to integrate Neural Networking into Intelligent Building Systems.
Average features: This composite image represents the ideal stimulus for Google’s software to detect a human face in a photo.
From MIT’s Technology Review: This summer Google set a new landmark in the field of artificial intelligence with software that learned how to recognize cats, people, and other things simply by watching YouTube videos (see “Self-Taught Software“). That technology, modeled on how brain cells operate, is now being put to work making Google’s products smarter, with speech recognition being the first service to benefit.
Energy consumption by buildings has increased to the point that it has overtaken the industrial and transportation sectors. This research seeks to develop Intelligent Adaptive Building Systems as a means of offsetting energy consumption, as well as improving numerous building performance metrics for all stakeholders. To achieve this, several existing technologies are married to form a contextually aware agent based network consisting of many semi-autonomous components. Through this research, two prototypes have been developed. The first served largely as a learning tool, setting the foundation for subsequent versions by necessitating lessons in physical computing and computer programming. A second generation prototype was developed which furthered insight into these lessons, and led to discoveries related to the potential of actuators and sensors, device networking, data mining, and agent based networks. Details about the first two prototypes, their successes, and failures will be presented. With these lessons in hand, it is now necessary to develop a third generation of prototypes to: further the understanding of adaptive facade capabilities and feasibility, intelligent computer behavior development, building performance metrics, and human interfacing methods. By developing several, rather than one 3rd generation prototype, the ability to draw comparisons between technologies and components will be vastly improved. This paper will focus on what form these prototypes should take, and what can be learned from them.
Full Paper PDF