New paper accepted in the conference Building-Simulation 2017 . In this paper, we show that Gaussian Process (GP) regression can reliably predict the energy consumption of a building design. Traditionally, designers rely on simulators to assess energy efficiency of their designs, but this could be painfully slow. We show that a GP based emulator gives accurate results within seconds. This work is in collaboration with Dr. Parag Rastogi and Prof. Marilyn Anderson from EPFL.
Humans, animals, and other living beings have a natural ability to autonomously learn throughout their lives and quickly adapt to their surroundings, but computers lack such abilities. My goal is to bridge such gaps between the learning of living-beings and computers.
Bayesian Deep Learning Workshop | NeurIPS 2021