Padua, Italy

Andrea Loreggia

This inventor holds 1 USPTO granted patent and 1 published patent application. Top assignee: International Business Machines Corporation. Active years: 2017.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Andrea Loreggia. Retrieved from https://idiyas.com/inventor/andrea-loreggia

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Calculating rank
USPTO Granted Patents = 1 

% Patents Active = 100.0

Average Co-Inventor Count = 4.0

ph-index = 1

Forward Citations = 19(Granted Patents)


Company Filing History:


Years Active: 2017

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Andrea Loreggia: Inventor in Machine Learning and Algorithm Portfolios.

Introduction

Andrea Loreggia is an inventor associated with Padua, Italy, and International Business Machines Corporation. Her patent work describes applying deep learning to select suitable problem-solving algorithms.

Latest Patents

The provided information lists one patent for Loreggia: “Deep learning for algorithm portfolios.” The invention generates a grayscale image from text representing a problem instance, then resizes the image to a predefined smaller size. The resulting image represents features of the problem instance and is supplied to a convolutional neural network. The network learns to identify one or more suitable problem solvers from a portfolio. Loreggia is credited with 1 patent.

Career Highlights

Loreggia’s described invention combines automated feature construction with machine learning. By converting problem-instance text into image-based features, the approach enables a neural network to learn which solver or solvers may be appropriate.

Collaborations

The provided information names Yuri Malitsky and Vijay Anand Saraswat as Loreggia’s coworkers. It does not specify their roles in the patent or the invention.

Conclusion

Andrea Loreggia’s patent illustrates an approach to algorithm selection that uses image representations and convolutional neural networks to match problem instances with suitable solvers.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…