Optics Express · 2019 · 147 citations · 24 references
Natural SciencesMaterials ScienceMachine LearningNanomaterialsNanotechnologyPhotonic MaterialsReinforcement LearningDeep Reinforcement LearningHuman IntelligenceNanostructures
Recently, a novel machine learning model has emerged in the field of reinforcement learning known as deep Q-learning. This model is capable of finding the best possible solution in systems consisting of millions of choices, without ever experiencing it before, and has been used to beat the best human minds at complex games such as, Go and chess, which both have a huge number of possible decisions and outcomes for each move. With a human-level intelligence, it has solved the problems that no other machine learning model has done before. Here, we show the steps needed for implementing this model to an optical problem. We investigate the colour generation by dielectric nanostructures and show that this model can find geometrical properties that can generate much purer red, green and blue colours compared to previously reported results. The model found these results in 9000 steps from a possible 34.5 million solutions. This technique can easily be extended to predict and optimise the design parameters for other optical structures.
24
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations
Mastering the game of Go with deep neural networks and tree search
David Silver, Aja Huang, Chris J. Maddison et al. · Nature · 2016 · 15.8K citations
Temporal difference learning and TD-Gammon
Communications of the ACM · 1995 · 1.5K citations · Full text
Training Deep Neural Networks for the Inverse Design of Nanophotonic Structures
Dianjing Liu, Yixuan Tan, Erfan Khoram et al. · ACS Photonics · 2018 · 1.1K citations · Full text