Fabio Maria Carlucci

Title: Fabio Maria Carlucci: Inventor in Deep Learning

Introduction

Fabio Maria Carlucci is an inventor based in Cambridge, Great Britain, and is associated with Huawei Technologies Co., Ltd. His patent work concerns normalization methods for training deep convolutional neural networks.

Latest Patents

Carlucci is named on one patent, Normalization in Deep Convolutional Neural Networks. The invention describes a machine-learning device with two neural network layers and an intervening normalization layer. During training, the normalization layer receives outputs for multiple samples, groups data values according to indices across two dimensions, and produces normalized outputs for the next layer. The approach is intended to support stable, effective training across different batch sizes and to generalize across vision tasks. Carlucci’s reported patent portfolio includes 1 patent.

Career Highlights

Carlucci’s listed invention addresses a practical challenge in deep-learning training: maintaining performance and stability as batch sizes and tasks vary. His work is associated with Huawei Technologies Co., Ltd.

Collaborations

The provided information lists Jiacheng Sun and Zewei Chen as Carlucci’s coworkers. They are also named in connection with his professional collaborations.

Conclusion

Fabio Maria Carlucci’s patent work focuses on neural-network normalization designed to make deep-learning training more stable and adaptable across vision applications.