Searcharxiv⌕ Search

arXiv subjects

Stefano Anzellotti

Publications and source records attributed to Stefano Anzellotti.

5 recordsLinked to original sources
arXiv2026

Machine Learning to Foundation Models: Artificial Intelligence for Nanophotonic Modeling and Scientific Discovery

Artificial intelligence (AI) is increasingly used to model, design, and study nanophotonic systems. This review traces the development of the field from classical machine learning and deep learning to generative models, transfer learning, transformers, and emerging foundation models. It first introduces major nanophotonic platforms, including nanoparticles, nanoholes, metasurfaces, photonic crystals, multilayer thin films, and integrated photonic devices, together with their main forward and inverse problems. It then reviews data-driven methods for predicting optical spectra and fields, generating structures from target responses, improving designs through optimization, and accounting for fabrication constraints. Generative models are discussed as a way to produce multiple valid solutions to nonunique inverse problems, while transfer learning, few-shot learning, and physics-aware training help reduce data requirements and improve generalization. Recent domain-specific foundation models show that different optical structures and responses can be handled within shared representations, but current systems remain limited in scope and physical grounding. Future progress will depend on multimodal models that connect geometry, materials, spectra, electromagnetic (EM) fields, fabrication data, experiments, and scientific literature with reliable simulation and validation tools. Current foundation models remain domain-specific, and their extension to broader nanophotonic tasks will require stronger physical grounding and validation.

physics.optics↗
arXiv2025

Improving action classification with brain-inspired deep networks

Action recognition is also key for applications ranging from robotics to healthcare monitoring. Action information can be extracted from the body pose and movements, as well as from the background scene. However, the extent to which deep neural networks (DNNs) make use of information about the body and information about the background remains unclear. Since these two sources of information may be correlated within a training dataset, DNNs might learn to rely predominantly on one of them, without taking full advantage of the other. Unlike DNNs, humans have domain-specific brain regions selective for perceiving bodies, and regions selective for perceiving scenes. The present work tests whether humans are thus more effective at extracting information from both body and background, and whether building brain-inspired deep network architectures with separate domain-specific streams for body and scene perception endows them with more human-like performance. We first demonstrate that DNNs trained using the HAA500 dataset perform almost as accurately on versions of the stimuli that show both body and background and on versions of the stimuli from which the body was removed, but are at chance-level for versions of the stimuli from which the background was removed. Conversely, human participants (N=28) can recognize the same set of actions accurately with all three versions of the stimuli, and perform significantly better on stimuli that show only the body than on stimuli that show only the background. Finally, we implement and test a novel architecture patterned after domain specificity in the brain with separate streams to process body and background information. We show that 1) this architecture improves action recognition performance, and 2) its accuracy across different versions of the stimuli follows a pattern that matches more closely the pattern of accuracy observed in human participants.

cs.CV↗
arXiv2023

Learning Socio-Temporal Graphs for Multi-Agent Trajectory Prediction

In order to predict a pedestrian's trajectory in a crowd accurately, one has to take into account her/his underlying socio-temporal interactions with other pedestrians consistently. Unlike existing work that represents the relevant information separately, partially, or implicitly, we propose a complete representation for it to be fully and explicitly captured and analyzed. In particular, we introduce a Directed Acyclic Graph-based structure, which we term Socio-Temporal Graph (STG), to explicitly capture pair-wise socio-temporal interactions among a group of people across both space and time. Our model is built on a time-varying generative process, whose latent variables determine the structure of the STGs. We design an attention-based model named STGformer that affords an end-to-end pipeline to learn the structure of the STGs for trajectory prediction. Our solution achieves overall state-of-the-art prediction accuracy in two large-scale benchmark datasets. Our analysis shows that a person's past trajectory is critical for predicting another person's future path. Our model learns this relationship with a strong notion of socio-temporal localities. Statistics show that utilizing this information explicitly for prediction yields a noticeable performance gain with respect to the trajectory-only approaches.

cs.CV↗
arXiv2022

Beyond linear regression: mapping models in cognitive neuroscience should align with research goals

Many cognitive neuroscience studies use large feature sets to predict and interpret brain activity patterns. Feature sets take many forms, from human stimulus annotations to representations in deep neural networks. Of crucial importance in all these studies is the mapping model, which defines the space of possible relationships between features and neural data. Until recently, most encoding and decoding studies have used linear mapping models. Increasing availability of large datasets and computing resources has recently allowed some researchers to employ more flexible nonlinear mapping models instead; however, the question of whether nonlinear mapping models can yield meaningful scientific insights remains debated. Here, we discuss the choice of a mapping model in the context of three overarching desiderata: predictive accuracy, interpretability, and biological plausibility. We show that, contrary to popular intuition, these desiderata do not map cleanly onto the linear/nonlinear divide; instead, each desideratum can refer to multiple research goals, each of which imposes its own constraints on the mapping model. Moreover, we argue that, instead of categorically treating the mapping models as linear or nonlinear, we should instead aim to estimate the complexity of these models. We show that, in many cases, complexity provides a more accurate reflection of restrictions imposed by various research goals. Finally, we outline several complexity metrics that can be used to effectively evaluate mapping models.

q-bio.NC↗