Fig. 1: Overview and performance of XLuminA.
From: Automated discovery of experimental designs in super-resolution microscopy with XLuminA
a Software’s workflow shows integrated feedback between the AI discovery tool and the optics simulator. Initial random optical parameters shape the hardware design on a virtual optical table. The optics simulator computes the performance of the experiment through detected light, from which the objective function (for instance, the spot size ϕ, where FWHM stands for Full Width Half Maximum) is evaluated. To improve the cost function metric, the optimizer adjusts the optical parameters, creating an iterative cycle between the simulator and optimizer until convergence. b Average execution time (in seconds) over 100 runs at 2048 × 2048 pixel resolution, for scalar and vectorial field propagation using Rayleigh-Sommerfeld (RS, VRS) and Chirped z-transform (CZT, VCZT) algorithms in Diffractio and XLuminA. Using pre-compiled jitted functions, XLuminA achieves × 2 speedup for RS and CZT and × 2.5 for VRS and VCZT on CPU. GPU implementation improves the performance up to × 64 for RS, × 76 for CZT, × 80 for VRS, and × 78 for VCZT. c Average time (in seconds) over 5 runs for a single gradient evaluation using numerical differentiation (num. diff) with Diffractio’s optical simulator (blue dots) and auto-differentiation (autodiff) methods (green triangles for CPU and magenta squares for GPU) with XLuminA's optical simulator for different resolutions. At 250 × 250 pixel resolution, GPU-based XLuminA’s autodiff methods significantly outperform numerical methods by a factor of × 3.9 ⋅ 105, and a factor of × 1.8 ⋅ 104 in the CPU. d Average time (in seconds) over 5 runs for convergence time, using numerical differentiation with Diffractio’s optical simulator and autodiff methods with XLuminA’s optical simulator for different resolutions. At 250 × 250 pixel resolution, GPU-based XLuminA’s autodiff methods significantly outperform numerical methods by a factor of × 2.1 ⋅ 104 and a factor of × 8.4 ⋅ 102 in the CPU. Standard deviation corresponds to shaded regions. We use BFGS and Adam optimizers, for numerical and autodiff approaches, respectively. The superior efficiency of autodiff over traditional numerical methods allows for highly efficient optimizations, particularly employing the large high resolutions we use (up to 2048 × 2048 pixels).
