TY - JOUR AU - Wigley, PB AU - Everitt, PJ AU - van den Hengel, A AU - Bastian, JW AU - Sooriyabandara, MA AU - McDonald, GD AU - Hardman, KS AU - Quinlivan, CD AU - Manju, P AU - Kuhn, CCN AU - Petersen, IR AU - Luiten, AN AU - Hope, JJ AU - Robins, NP AU - Hush, MR Y2 - 2020/12/22 Y1 - 2016/05/16 SN - 2045-2322 UR - http://hdl.handle.net/11343/257937 AB - We apply an online optimization process based on machine learning to the production of Bose-Einstein condensates (BEC). BEC is typically created with an exponential evaporation ramp that is optimal for ergodic dynamics with two-body s-wave interactions and no other loss rates, but likely sub-optimal for real experiments. Through repeated machine-controlled scientific experimentation and observations our 'learner' discovers an optimal evaporation ramp for BEC production. In contrast to previous work, our learner uses a Gaussian process to develop a statistical model of the relationship between the parameters it controls and the quality of the BEC produced. We demonstrate that the Gaussian process machine learner is able to discover a ramp that produces high quality BECs in 10 times fewer iterations than a previously used online optimization technique. Furthermore, we show the internal model developed can be used to determine which parameters are essential in BEC creation and which are unimportant, providing insight into the optimization process of the system. LA - eng PB - Springer Science and Business Media LLC T1 - Fast machine-learning online optimization of ultra-cold-atom experiments. DO - 10.1038/srep25890 IS - Scientific Reports VL - 6 IS - 1 SP - 25890- L1 - /bitstream/handle/11343/257937/PMC4867626.pdf?sequence=1&isAllowed=y ER -