A thermal regulator that uses neural networks to learn about your house as the seasons change has been developed by a spinoff from École Polytechnique Fédérale de Lausanne (EPFL) and the Swiss Center for Electronics and Microtechnology (CSEM).

Most home thermal regulators only react to a single parameter — the outside temperature — in regulating their output.

EPFL researchers developed a system, called Neurobat (Neuron + Batiment, French for building), that allows for savings of up to 65% on fuel. It monitors multiple parameters and learns what is best for your house by imitating the brain. These include sunlight level, the way the dwelling itself reacts (using a thermometer placed in a dedicated room), and a presence sensor (lowers temperature when no one is home).

“The more the system ‘learns,’ the more precise the adjustments can be,” says David Lindelöf, technical director of Neurobat SA. “Eventually, it becomes capable of establishing predictive meteorological models that are specific to a given dwelling, and therefore more precise — and less expensive — than those provided by meteorological offices.”