arXiv subjects

Samuel Kim

Publications and source records attributed to Samuel Kim.

24 records · Page 2Linked to original sources

arXiv2022

Automated Discovery and Optimization of 3D Topological Photonic Crystals

Topological photonic crystals have received considerable attention for their ability to manipulate and guide light in unique ways. They are typically designed by hand based on careful analysis of their bands and mode profiles, but recent theoretical advances have revealed new and powerful insights into the connection between band symmetry, connectivity, and topology. Here we propose a combined global and local optimization framework that integrates a flexible symmetry-constrained level-set parameterization with standard gradient-free optimization algorithms to optimize topological photonic crystals, a problem setting where the objective function may be highly non-convex and non-continuous. Our framework can be applied to any symmetry-identifiable band topology, and we demonstrate its applicability to several prominent kinds of three-dimensional band topology, namely $Γ$-enforced nodal lines, Weyl points, and Chern insulators. Requiring no prior examples of topological photonic crystals or prior knowledge on the connection between structure and band topology, our approach indicates a path towards the automated discovery of novel topological photonic crystal designs.

physics.optics↗

arXiv2021

Surrogate- and invariance-boosted contrastive learning for data-scarce applications in science

Deep learning techniques have been increasingly applied to the natural sciences, e.g., for property prediction and optimization or material discovery. A fundamental ingredient of such approaches is the vast quantity of labelled data needed to train the model; this poses severe challenges in data-scarce settings where obtaining labels requires substantial computational or labor resources. Here, we introduce surrogate- and invariance-boosted contrastive learning (SIB-CL), a deep learning framework which incorporates three ``inexpensive'' and easily obtainable auxiliary information sources to overcome data scarcity. Specifically, these are: 1)~abundant unlabeled data, 2)~prior knowledge of symmetries or invariances and 3)~surrogate data obtained at near-zero cost. We demonstrate SIB-CL's effectiveness and generality on various scientific problems, e.g., predicting the density-of-states of 2D photonic crystals and solving the 3D time-independent Schrodinger equation. SIB-CL consistently results in orders of magnitude reduction in the number of labels needed to achieve the same network accuracies.

cs.LG↗

arXiv2020

Extracting Interpretable Physical Parameters from Spatiotemporal Systems using Unsupervised Learning

Experimental data is often affected by uncontrolled variables that make analysis and interpretation difficult. For spatiotemporal systems, this problem is further exacerbated by their intricate dynamics. Modern machine learning methods are particularly well-suited for analyzing and modeling complex datasets, but to be effective in science, the result needs to be interpretable. We demonstrate an unsupervised learning technique for extracting interpretable physical parameters from noisy spatiotemporal data and for building a transferable model of the system. In particular, we implement a physics-informed architecture based on variational autoencoders that is designed for analyzing systems governed by partial differential equations (PDEs). The architecture is trained end-to-end and extracts latent parameters that parameterize the dynamics of a learned predictive model for the system. To test our method, we train our model on simulated data from a variety of PDEs with varying dynamical parameters that act as uncontrolled variables. Numerical experiments show that our method can accurately identify relevant parameters and extract them from raw and even noisy spatiotemporal data (tested with roughly 10% added noise). These extracted parameters correlate well (linearly with $R^2 > 0.95$) with the ground truth physical parameters used to generate the datasets. We then apply this method to nonlinear fiber propagation data, generated by an ab-initio simulation, to demonstrate its capabilities on a more realistic dataset. Our method for discovering interpretable latent parameters in spatiotemporal systems will allow us to better analyze and understand real-world phenomena and datasets, which often have unknown and uncontrolled variables that alter the system dynamics and cause varying behaviors that are difficult to disentangle.

physics.comp-ph↗

arXiv2020

Integration of Neural Network-Based Symbolic Regression in Deep Learning for Scientific Discovery

Symbolic regression is a powerful technique that can discover analytical equations that describe data, which can lead to explainable models and generalizability outside of the training data set. In contrast, neural networks have achieved amazing levels of accuracy on image recognition and natural language processing tasks, but are often seen as black-box models that are difficult to interpret and typically extrapolate poorly. Here we use a neural network-based architecture for symbolic regression called the Equation Learner (EQL) network and integrate it with other deep learning architectures such that the whole system can be trained end-to-end through backpropagation. To demonstrate the power of such systems, we study their performance on several substantially different tasks. First, we show that the neural network can perform symbolic regression and learn the form of several functions. Next, we present an MNIST arithmetic task where a separate part of the neural network extracts the digits. Finally, we demonstrate prediction of dynamical systems where an unknown parameter is extracted through an encoder. We find that the EQL-based architecture can extrapolate quite well outside of the training data set compared to a standard neural network-based architecture, paving the way for deep learning to be applied in scientific exploration and discovery.

cs.LG↗

arXiv2019

Toward estimating personal well-being using voice

Estimating personal well-being draws increasing attention particularly from healthcare and pharmaceutical industries. We propose an approach to estimate personal well-being in terms of various measurements such as anxiety, sleep quality and mood using voice. With clinically validated questionnaires to score those measurements in a self-assessed way, we extract salient features from voice and train regression models with deep neural networks. Experiments with the collected database of 219 subjects show promising results in predicting the well-being related measurements; concordance correlation coefficients (CCC) between self-assessed scores and predicted scores are 0.41 for anxiety, 0.44 for sleep quality and 0.38 for mood.

cs.CL↗

arXiv2015

Enhanced strain coupling of nitrogen vacancy spins to nanoscale diamond cantilevers

Nitrogen vacancy (NV) centers can couple to confined phonons in diamond mechanical resonators via the effect of lattice strain on their energy levels. Access to the strong spin-phonon coupling regime with this system requires resonators with nanoscale dimensions in order to overcome the weak strain response of the NV ground state spin sublevels. In this work, we study NVs in diamond cantilevers with lateral dimensions of a few hundred nm. Coupling of the NV ground state spin to the mechanical mode is detected in electron spin resonance (ESR), and its temporal dynamics are measured via spin echo. Our small mechanical mode volume leads to a 10-100X enhancement in spin-phonon coupling strength over previous NV-strain coupling demonstrations. This is an important step towards strong spin-phonon coupling, which can enable phonon-mediated quantum information processing and quantum metrology.

quant-ph↗