Search papers, labs, and topics across Lattice.
This paper introduces a deep learning approach to model-based design of experiments (MBDOE) that overcomes the computational bottleneck of traditional adaptive MBDOE. They combine Deep Adaptive Design (DAD) with differentiable mechanistic models, amortizing the sequential design process into a neural network policy trained offline. The method is validated on four dynamical systems, including a real-time DC motor experiment, demonstrating its ability to efficiently estimate parameters in nonlinear dynamical systems.
By amortizing sequential design into a neural network, this method achieves real-time model-based design of experiments, unlocking new possibilities for efficient parameter estimation in complex dynamical systems.
Model-based design of experiments (MBDOE) is essential for efficient parameter estimation in nonlinear dynamical systems. However, conventional adaptive MBDOE requires costly posterior inference and design optimization between each experimental step, precluding real-time applications. We address this by combining Deep Adaptive Design (DAD), which amortizes sequential design into a neural network policy trained offline, with differentiable mechanistic models. For dynamical systems with known governing equations but uncertain parameters, we extend sequential contrastive training objectives to handle nuisance parameters and propose a transformer-based policy architecture that respects the temporal structure of dynamical systems. We demonstrate the approach on four systems of increasing complexity: a fed-batch bioreactor with Monod kinetics, a Haldane bioreactor with uncertain substrate inhibition, a two-compartment pharmacokinetic model with nuisance clearance parameters, and a DC motor for real-time deployment.