Eric Cosatto NEC Labs AmericaEric Cosatto is a Senior Researcher in the Machine Learning Department at NEC Laboratories America in Princeton, NJ. He earned his BS in math from the Lycée Collège Cantonal des Creusets, Sion, and his MS and PhD in Computer Science from EPFL in Lausanne. With decades of experience in AI, he has contributed to foundational systems in handwriting recognition, image segmentation, and biomedical diagnostics.

At NEC Labs America, Dr. Cosatto has been instrumental in advancing digital pathology solutions using AI, including deep learning tools for cancer detection and cell classification. His work integrates domain-specific constraints into interpretable neural network models and has appeared in top-tier journals and conferences in computer vision and machine learning. Known for his applied focus, he frequently collaborates with healthcare institutions and domain experts to ensure the clinical utility of AI systems. His research bridges theoretical innovation and real-world impact, supporting NEC’s initiatives in trustworthy and efficient machine learning.

Posts

Size and Alignment Independent Classification of the High-order Spatial Modes of a Light Beam Using a Convolutional Neural Network

/in /by

The higher-order spatial modes of a light beam are receiving significant interest. They can be used to further increase the data speeds of high speed optical communication, and for novel optical sensing modalities. As such, the classification of higher-order spatial modes is ubiquitous. Canonical classification methods typically require the use of unconventional optical devices. However, in addition to having prohibitive cost, complexity, and efficacy, such methods are dependent on the light beam’s size and alignment. In this work, a novel method to classify higher-order spatial modes is presented, where a convolutional neural network is applied to images of higher-order spatial modes that are taken with a conventional camera. In contrast to previous methods, by training the convolutional neural network with higher-order spatial modes of various alignments and sizes, this method is not dependent on the light beam’s size and alignment. As a proof of principle, images of 4 Hermite-Gaussian modes (HG00, HG01, HG10, and HG11) are numerically calculated via known solutions to the electromagnetic wave equation, and used to synthesize training examples. It is shown that as compared to training the convolutional neural network with training examples that have the same sizes and alignments, a?~2×?increase in accuracy can be achieved.

Read more