Multiparameter optimisation of a magneto-optical trap using deep learning

Abstract

Many important physical processes have dynamics that are too complex to completely model analytically. Optimisation of such processes often relies on intuition, trial-and-error, or the construction of empirical models. Machine learning based on artificial neural networks has emerged as an efficient means to develop empirical models of complex systems. We implement a deep artificial neural network to optimise the magneto-optic cooling and trapping of neutral atomic ensembles. Cold atomic ensembles have become commonplace in laboratories around the world, however, many-body interactions give rise to complex dynamics that preclude precise analytic optimisation of the cooling and trapping process. The solution identified by machine learning is radically different to the smoothly varying adiabatic solutions currently used. Despite this, the solutions vastly outperform best known solutions producing higher optical densities. This may provide a pathway to a new understanding of the dynamics of the cooling and trapping processes in cold atomic ensembles.

References in corpus (11)

• Shortcuts to adiabaticity
• Highly efficient optical quantum memory with long coherence time in cold atoms
• Fast machine-learning online optimization of ultra-cold-atom experiments
• Exploring the Quantum Speed Limit with Computer Games
• Learning in Quantum Control: High-Dimensional Global Optimization for Noisy Quantum Dynamics
• Creation of a Bose-condensed gas of rubidium 87 by laser cooling
• Prediction and real-time compensation of qubit decoherence via machine-learning
• Using Recurrent Neural Networks to Optimize Dynamical Decoupling for Quantum Memory
• Gradient echo memory in an ultra-high optical depth cold atomic ensemble
• Evolutionary optimization of an experimental apparatus
• Quantitative simulation of a magneto-optical trap operating near the photon recoil limit

Cited by in corpus (32)

• Challenges and Opportunities in Quantum Machine Learning
• Intelligent metaphotonics empowered by machine learning
• Deep learning enhanced Rydberg multifrequency microwave recognition
• Photonic integrated beam delivery in a rubidium 3D magneto-optical trap
• Unsupervised machine learning of topological phase transitions from experimental data
• Stand-alone vacuum cell for compact ultracold quantum technologies
• Applying machine learning optimization methods to the production of a quantum gas
• Machine-learning-accelerated Bose-Einstein condensation
• Approaching the adiabatic timescale with machine-learning
• Optimal quantum control with poor statistics
• Learning quantum dynamics with latent neural ODEs
• An unsupervised deep learning algorithm for single-site reconstruction in quantum gas microscopes
• Single-exposure absorption imaging of ultracold atoms using deep learning
• Preparation of ordered states in ultra-cold gases using Bayesian optimization
• Integration of spectator qubits into quantum computer architectures for hardware tuneup and calibration
• Machine learner optimization of optical nanofiber-based dipole traps for cold ${}^{87}$Rb atoms
• Continuous field tracking with machine learning and steady state spin squeezing
• Active Learning Approach to Optimization of Experimental Control
• Dispersion Characterization and Pulse Prediction with Machine Learning
• Experimental graybox quantum system identification and control
• Time-reversed and coherently-enhanced memory: A single-mode quantum atom-optic memory without a cavity
• Quantum Reservoir Computing for Speckle-Disorder Potentials
• High-dimensional reinforcement learning for optimization and control of ultracold quantum gases
• Light-induced fictitious magnetic fields for quantum storage in cold atomic ensembles
• Review and experimental benchmarking of machine learning algorithms for efficient optimization of cold atom experiments
• Bayesian Optimization for Robust State Preparation in Quantum Many-Body Systems
• Combining machine learning with physics: A framework for tracking and sorting multiple dark solitons
• Adaptive filtering of projective quantum measurements using discrete stochastic methods
• Automating Experimental Optics with Sample Efficient Machine Learning Methods
• Observation of cross phase modulation in cold atom gradient echo memory
• Bose-Einstein condensation by polarization gradient laser cooling
• Fingerprint Recognition of Partial Discharge Signals in Deep Learning Enhanced Rydberg Atomic Sensors