This inventor holds 1 USPTO granted patent. Top assignees: International Business Machines Corporation, Rensselaer Polytechnic Institute. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
1 out of 166,425 
1 out of 652 
Years Active: 2026
Title: Luigi Vanfretti: Inventor of Neural Network Architectures
Introduction
Luigi Vanfretti is an inventor associated with Troy, New York. His work includes a patented approach to recurrent neural networks inspired by discrete-time dynamical systems.
Latest Patents
Vanfretti is credited with 1 patent: “Designing Ladder and Laguerre Orthogonal Recurrent Neural Network Architectures Inspired by Discrete-Time Dynamical Systems.” The invention describes a method and system for making predictions with a recurrent neural network (RNN) modeling a discrete-time linear time-invariant system.
The RNN receives memory, external input, state, and hidden-output flows. It computes an updated state flow through a linear combination of the external input and memory flow, constrained by matrices corresponding to a Laguerre orthogonal basis. Using a coordinate matrix, it then derives an updated memory flow. An activation function updates the hidden-output flow, and a weighted sum of the hidden-output, state, and memory flows produces the output.
Career Highlights
Vanfretti’s listed professional affiliations include International Business Machines Corporation and Rensselaer Polytechnic Institute. These organizations connect his work with both industry and academic research.
Collaborations
Sergio Dorado is identified as a coworker of Vanfretti.
Conclusion
Luigi Vanfretti’s patent applies Laguerre orthogonal basis concepts to recurrent neural network design, linking dynamical-system methods with prediction.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile