Related papers: Programming the scalable optical learning operator…
Similar to algorithms, which consume time and memory to run, hardware requires resources to function. For devices processing physical waves, implementing operations needs sufficient "space," as dictated by wave physics. How much space is…
Once-for-All (OFA) training enables a single super-net to generate multiple sub-nets tailored to diverse deployment scenarios, supporting flexible trade-offs among accuracy, robustness, and model-size without retraining. However, as the…
The sequential minimal optimization (SMO) algorithm and variants thereof are the de facto standard method for solving large quadratic programs for support vector machine (SVM) training. In this paper we propose a simple yet powerful…
The increasing complexity of neural networks and the energy consumption associated with training and inference create a need for alternative neuromorphic approaches, e.g. using optics. Current proposals and implementations rely on physical…
In this work we present the first application of software-defined optoelectronics (SDO) for bidimensional optoacoustic tomography (OAT). The SDO concept refers to optoelectronic systems where the functionality associated with the…
The joint detection and classification of RF signals has been a critical problem in the field of wideband RF spectrum sensing. Recent advancements in deep learning models have revolutionized this field, remarkably through the application of…
Automated medical diagnosis through image-based neural networks has increased in popularity and matured over years. Nevertheless, it is confined by the scarcity of medical images and the expensive labor annotation costs. Self-Supervised…
We describe a new algorithm for the "perfect" extraction of one-dimensional spectra from two-dimensional (2D) digital images of optical fiber spectrographs, based on accurate 2D forward modeling of the raw pixel data. The algorithm is…
Making the most of next-generation galaxy clustering surveys requires overcoming challenges in complex, non-linear modelling to access the significant amount of information at smaller cosmological scales. Field-level inference has provided…
Optical computing offers potential for ultra high-speed and low latency computation by leveraging the intrinsic properties of light. Here, we explore the use of highly nonlinear optical fibers (HNLFs) as platforms for optical computing…
Stochastic compositional optimization (SCO) has attracted considerable attention because of its broad applicability to important real-world problems. However, existing works on SCO assume that the projection within a solution update is…
Reservoir computing is a recently introduced, highly efficient bio-inspired approach for processing time dependent data. The basic scheme of reservoir computing consists of a non linear recurrent dynamical system coupled to a single input…
The use of machine learning techniques to improve the performance of branch-and-bound optimization algorithms is a very active area in the context of mixed integer linear problems, but little has been done for non-linear optimization. To…
Spiking neural network (SNN) has emerged as a promising paradigm in computational neuroscience and artificial intelligence, offering advantages such as low energy consumption and small memory footprint. However, their practical adoption is…
Stochastic computer simulations enable users to gain new insights into complex physical systems. Optimization is a common problem in this context: users seek to find model inputs that maximize the expected value of an objective function.…
Scientific computing applications heavily rely on multi-level loop nests operating on multidimensional arrays. This presents multiple optimization opportunities from exploiting parallelism to reducing data movement through prefetching and…
Imaging through a single optical fiber offers attractive possibilities in many applications such as microendoscopy or remote sensing. However, the direct transmission of an image through an optical fiber is difficult because spatial…
Nonlinear computation is essential for various information processing tasks. Optical implementations are attractive because passive light propagation can manipulate high-dimensional signals with extreme throughput and parallelism; yet…
Recent progress in effective nonlinearity, achieved by exploiting multiple scatterings within the linear optical regime, has been demonstrated to be a promising approach to enable nonlinear optical processing without relying on actual…
Self-supervised learning (SSL) has enabled the development of vision foundation models for Earth Observation (EO), demonstrating strong transferability across diverse remote sensing tasks. While prior work has focused on network…