Vladimir Ceperic

TL;DR: Two important improvements to the SVR based load forecasting method are introduced, i.e., procedure for generation of model inputs and subsequent model input selection using feature selection algorithms and the use of the particle swarm global optimization based technique for the optimization of SVR hyper-parameters reduces the operator interaction.

TL;DR: This work presents the Photonic Recurrent Ising Sampler (PRIS), a heuristic method tailored for parallel architectures allowing fast and efficient sampling from distributions of arbitrary Ising problems, and suggests speedups in heuristic methods via photonic implementations of the PRIS.

TL;DR: A proof-of-principle integrated nanophotonic recurrent Ising sampler (INPRIS) is experimentally demonstrated, using a hybrid scheme combining electronics and silicon-on-insulator photonics, that is capable of converging to the ground state of various four-spin graphs with high probability.

TL;DR: This article uses a neural network-based architecture for symbolic regression called the equation learner (EQL) network and integrates it with other deep learning architectures such that the whole system can be trained end-to-end through backpropagation.

TL;DR: This work builds a data set of 20,000 two-dimensional photonic crystal unit cells and their associated band structures, enabling the training of supervised learning models and demonstrates a high-accuracy convolutional neural network for band structure prediction, with orders ofmagnitude speedup compared to conventional theory-driven solvers.