IDiyas

For the Inventor, By the Inventor

London, United Kingdom

Tom Schaul

USPTO Granted Patents = 15 

 

Average Co-Inventor Count = 3.9

ph-index = 3

Forward Citations = 38(Granted Patents)


Company Filing History:

goldMedal14 out of 308 
 
Deepmind Technologies Limited
 patents
silverMedal1 out of 832,680 
Other
 patents

Years Active: 2018-2025

Loading Chart...
Loading Chart...
15 patents (USPTO):
1. 12271823 - Training machine learning models by determining update rules using neural networks (2025-04-08),
2. 12154029 - Continual reinforcement learning with a multi-task agent (2024-11-26),
3. 12141677 - Environment prediction using reinforcement learning (2024-11-12),
4. 12086714 - Training neural networks using a prioritized experience memory (2024-09-10),
5. 12061964 - Modulating agent behavior to optimize learning progress (2024-08-13),
6. 11842281 - Reinforcement learning with auxiliary tasks (2023-12-12),
7. 11676035 - Learning non-differentiable weights of neural networks using evolutionary strategies (2023-06-13),
8. 11615310 - Training machine learning models by determining update rules using recurrent neural networks (2023-03-28),
9. 11568250 - Training neural networks using a prioritized experience memory (2023-01-31),
10. 10956820 - Reinforcement learning with auxiliary tasks (2021-03-23),
11. 10733501 - Environment prediction using reinforcement learning (2020-08-04),
12. 10650310 - Training neural networks using a prioritized experience memory (2020-05-12),
13. 10628733 - Selecting reinforcement learning actions using goals and observations (2020-04-21),
14. 10282662 - Training neural networks using a prioritized experience memory (2019-05-07),
15. 10055687 - Method for creating predictive knowledge structures from experience in an artificial agent (2018-08-21),

Title: The Innovations of Tom Schaul

Introduction

Tom Schaul is a prominent inventor based in London, GB, known for his significant contributions to the field of machine learning. With a total of 15 patents to his name, he has made remarkable strides in developing advanced techniques for training machine learning models.

Latest Patents

Schaul's latest patents include groundbreaking methods for training machine learning models. One notable patent focuses on training machine learning models by determining update rules using neural networks. This method involves obtaining a machine learning model with one or more model parameters, which is trained using gradient descent techniques to optimize an objective function. The process includes determining an update rule for the model parameters using a recurrent neural network (RNN) and applying this rule for a final time step in a sequence of multiple time steps.

Another significant patent is centered around continual reinforcement learning with a multi-task agent. This method describes training an action selection neural network for controlling an agent that interacts with an environment to perform various tasks. The training process includes obtaining a trajectory of transitions generated while the agent performs an episode of the first task and adjusting control policies for multiple tasks based on the generated transitions.

Career Highlights

Throughout his career, Tom Schaul has worked with notable companies, including DeepMind Technologies Limited. His work has significantly impacted the development of machine learning technologies and their applications in various fields.

Collaborations

Schaul has collaborated with esteemed colleagues such as David Silver and John Quan, contributing to the advancement of machine learning research and applications.

Conclusion

Tom Schaul's innovative work in machine learning has led to the development of advanced techniques that enhance the training of models. His contributions continue to shape the future of artificial intelligence and machine learning technologies.

This text is generated by artificial intelligence and may not be accurate.
Please report any incorrect information to support@idiyas.com
Loading…