Jelena Luketina

Title: Jelena Luketina: Innovator in Neural Networks

Introduction

Jelena Luketina is a prominent inventor based in Oxford, GB. She has made significant contributions to the field of machine learning, particularly in the area of neural networks. Her innovative work focuses on scalable continual learning, which is essential for developing intelligent systems that can adapt to new tasks over time.

Latest Patents

Jelena holds a patent titled "Neural networks for scalable continual learning in domains with sequentially learned tasks." This patent encompasses methods, systems, and apparatus, including computer programs encoded on computer storage media, for scalable continual learning using neural networks. One of the key methods involves receiving new training data for a new machine learning task. It also includes training an active subnetwork on the new training data to determine trained values of the active network parameters while holding current values of the knowledge parameters fixed. Additionally, it describes training a knowledge subnetwork on the new training data to determine updated values of the knowledge parameters.

Career Highlights

Jelena is currently employed at DeepMind Technologies Limited, where she continues to push the boundaries of artificial intelligence research. Her work is instrumental in developing advanced machine learning techniques that can be applied across various domains.

Collaborations

Some of her notable coworkers include Jonathan Schwarz and Razvan Pascanu, who are also recognized for their contributions to the field of machine learning.

Conclusion

Jelena Luketina's innovative work in neural networks and scalable continual learning positions her as a key figure in the advancement of artificial intelligence. Her contributions are paving the way for more adaptive and intelligent systems in the future.