Chelsea Finn is an American computer scientist and assistant professor at Stanford University. Her research investigates intelligence through the interactions of robots, with the hope to create robotic systems that can learn how to learn. She is part of the Google Brain group.
Chelsea Finn | |
|---|---|
 Finn as a graduate student at UC Berkeley in 2017 | |
| Alma mater | University of California, Berkeley Massachusetts Institute of Technology |
| Known for | Deep reinforcement learning |
| Scientific career | |
| Institutions | Stanford University |
| Thesis | Learning to Learn with Gradients (2018) |
| Doctoral advisor | Sergey Levine Pieter Abbeel |
| Website | IRIS LAB |
Early life and education
editFinn was an undergraduate student in electrical engineering and computer science at Massachusetts Institute of Technology. She then moved to the University of California, Berkeley, where she earned her Ph.D. in 2018 under Pieter Abbeel and Sergey Levine. Her work in the Berkeley Artificial Intelligence Lab (BAIR) focused on gradient based algorithms .[1] Such algorithms allow machines to 'learn to learn', more akin to human learning than traditional machine learning systems.[2][3] These “meta-learning” techniques train machines to quickly adapt, such that when they encounter new scenarios they can learn quickly.[4] As a doctoral student she worked as an intern at Google Brain, where she worked on robot learning algorithms from deep predictive models. She delivered a massive open online course on deep reinforcement learning.[5][6] She was the first woman to win the C.V. & Daulat Ramamoorthy Distinguished Research Award.[7]
Research and career
editFinn investigates the capabilities of robots to develop intelligence through learning and interaction.[8] She has made use of deep learning algorithms to simultaneously learn visual perception and control robotic skills.[9]
She developed meta-learning approaches to train neural networks to take in student code and output useful feedback.[10] She showed that the system could quickly adapt without too much input from the instructor.[10] She trialled the programme on Code in Place, a 12,000 student course delivered by Stanford University every year. She found that 97.9% of the time the students agreed with the feedback being given.[10][11]
Awards and honors
edit- 2016 C.V. & Daulat Ramamoorthy Distinguished Research Award[7]
- 2017 Electrical engineering and computer science rising star[12]
- 2018 MIT Technology Review 35 Under 35[13][14]
- 2018 ACM Doctoral Dissertation Award[15]
- 2020 Samsung Advanced Institute of Technology AI Researcher of the Year[16]
- 2020 Intel Rising Star Faculty Award[17]
- 2021 Office of Naval Research Young Investigator Award[18]
- 2022 IEEE Robotics and Automation Society Early Academic Career Award[19]
Select publications
edit- Finn, Chelsea; Abbeel, Pieter; Levine, Sergey (2017-07-17). "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks". International Conference on Machine Learning. PMLR: 1126–1135. arXiv:1703.03400.
- Sergey Levine; Chelsea Finn; Trevor Darrell; Pieter Abbeel (2016). "End-to-End Training of Deep Visuomotor Policies". Journal of Machine Learning Research. 17 (39): 1–40. arXiv:1504.00702. ISSN 1533-7928. Wikidata Q90313375.
- Chelsea Finn; Ian Goodfellow; Sergey Levine (2016). "Unsupervised Learning for Physical Interaction through Video Prediction" (PDF). Advances in Neural Information Processing Systems 29. Advances in Neural Information Processing Systems. Wikidata Q46993574.
References
edit- ^ "Chelsea Finn: Teaching robots to learn". Berkeley Engineering. 2018-05-08. Retrieved 2022-05-20.
- ^ "An Interview with Chelsea Finn: AI for Robotics". Technovation. Retrieved 2022-05-20.
- ^ Natarajan, Nikhila. "Chelsea Finn is teaching Brett the Robot how the world works". ORF. Retrieved 2022-05-20.
- ^ Finn, Chelsea (2018). Learning to Learn with Gradients (PDF). OCLC 1083628768. Archived from the original (PDF) on 2022-01-20. Retrieved 2022-05-20.
- ^ "CS 294 Deep Reinforcement Learning, Fall 2017". rail.eecs.berkeley.edu. Retrieved 2022-05-20.
- ^ Kurenkov, Andrey (2021-10-14). "Chelsea Finn on Meta Learning & Model Based Reinforcement Learning". The Gradient. Retrieved 2022-05-20.
- ^ a b "Student Award: C.V. & Daulat Ramamoorthy Distinguished Research Award | EECS at UC Berkeley". www2.eecs.berkeley.edu. Retrieved 2022-05-20.
- ^ "Chelsea Finn". CIFAR. Retrieved 2022-05-20.
- ^ Interview with Professor Chelsea Finn, Stanford, 28 September 2020, retrieved 2022-05-20
- ^ a b c Metz, Cade (2021-07-20). "Can A.I. Grade Your Next Test?". The New York Times. ISSN 0362-4331. Retrieved 2022-05-20.
- ^ Wu, Mike; Goodman, Noah; Piech, Chris; Finn, Chelsea (2021-10-04). "ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback". arXiv:2107.14035 [cs.CY].
- ^ "Chelsea Finn – Rising Stars in EECS 2017". Retrieved 2022-05-20.
- ^ "Chelsea Finn". MIT Technology Review. Retrieved 2022-05-20.
- ^ "News". EECS at UC Berkeley. Retrieved 2022-05-20.
- ^ "Chelsea Finn". Association for Computing Machinery. Retrieved 2022-05-28.
- ^ "Samsung AI Researcher of the Year". Samsung Advanced Institute of Technology. Retrieved 2022-05-20.
- ^ "Intel's 2020 Rising Stars Awards". Intel. Retrieved 2022-05-20.
- ^ "2021 Young Investigators - Office of Naval Research". www.onr.navy.mil. 18 March 2022. Retrieved 2022-05-20.
- ^ "RAS Early Career Award - Academic - IEEE Robotics and Automation Society". www.ieee-ras.org. Retrieved 2022-05-20.