Company Filing History:
Years Active: 2022-2023
Title: Miguel Lazaro Gredilla: Innovator in Event Prediction and Deep Learning
Introduction
Miguel Lazaro Gredilla is a notable inventor based in Union City, CA (US). He has made significant contributions to the fields of event prediction and deep learning, holding a total of 2 patents. His work focuses on developing systems that enhance predictive capabilities and optimize learning processes.
Latest Patents
Gredilla's latest patents include "Systems and methods for event prediction using schema networks." This innovative system utilizes a first antecedent entity state that represents a first entity at a first time, along with a first consequent entity state that represents the same entity at a second time. Additionally, it incorporates a second antecedent entity state representing a second entity at the first time, and a first schema factor that connects the antecedent states to the consequent state, enabling accurate predictions.
Another significant patent is "Systems and methods for deep learning with small training sets." This invention features a hierarchical compositional network, which is representable in Bayesian network form. It includes multiple parent feature nodes, pool nodes, weight nodes, and child feature nodes, all designed to enhance the efficiency of deep learning processes, especially when training data is limited.
Career Highlights
Gredilla is currently associated with Intrinsic Innovation LLC, where he continues to push the boundaries of technology through his inventive work. His career is marked by a commitment to advancing the fields of artificial intelligence and machine learning.
Collaborations
Some of his notable coworkers include Kenneth Alan Kansky and Tom Silver, who contribute to the innovative environment at Intrinsic Innovation LLC.
Conclusion
Miguel Lazaro Gredilla is a prominent figure in the realm of innovation, particularly in event prediction and deep learning. His patents reflect a deep understanding of complex systems and a dedication to improving technological capabilities.