Amgen Scholars: Announcements of Opportunity
Related Pages 
Below are Announcements of Opportunity posted by Caltech faculty for the Amgen Scholars program.
Announcements of Opportunity are posted as they are received. Please check back regularly for new AO submissions! Remember: This is just one way that you can go about identifying a suitable project and/or mentor. For additional tips on identifying a mentor click here.
Please remember:
- Students pursuing Amgen must be U.S. citizens, U.S. permanent residents, or students with DACA status.
- Students pursuing Amgen must complete the 10-week program from June 21 - August 25, 2023. Students must commit to these dates. No exceptions will be made.
- Accepted students must live in provided Caltech housing.
<< Prev
Record
28 of
59
Next >>
Back To List
| Project: | Exploring the future of machine learning in astronomy | ||||||||
| Disciplines: | Astronomy, Data Science | ||||||||
| Mentor: |
Matthew Graham,
Prof., (PMA),
mjg@caltech.edu, |
||||||||
| Mentor URL: | https://www.astro.caltech.edu/~mjg (opens in new window) | ||||||||
| Background: |
Opinions on quantum computing (QC) in both the scientific literature and popular press range from it being the future and solution to all computing problems to it being just the latest version of the Emperor's New Clothes. Beyond the hype, however, QC offers a more effective approach to tackling complex problems (and the only practicable approach in some cases). Quantum machine learning (QML) can be seen as an extension of classical machine learning where computationally difficult elements - too slow or too large - are replaced by QC components that promise significant improvements in speed and/or storage. In the current Noisy Intermediate-Scale Quantum (NISQ) computing era, quantum algorithms with known speedups over classical algorithms, such as Shor's factoring algorithm or Grover's search algorithm, are not yet possible at a meaningful scale. However, hybrid classical-quantum systems where the quantum processor prepares quantum states but measurements and optimization are done by a classical computer are considered optimal for the NISQ era. In particular, Quantum Variational Circuits (QVCs) are seen as the equivalent of a traditional neural network and training consists of finding values for the free parameters of the circuit that optimize some cost function. As with many sciences, astronomy is seeing ever larger and more complex data sets and the fastest machine learning solutions can be important for rapid classification and optimal decision taking. Although QML is still in its early stages, it is developed enough to begin to explore potential applications to astronomical problems to inform areas of future development. |
||||||||
| Description: | The project will consist of creating quantum versions of machine-learning algorithms that are used in the Zwicky Transient Facility (ZTF) with image and time series data using industry toolkits such as Qiskit. The performance of these will be compared to their classical counterparts using a quantum simulator or limited capability quantum systems. | ||||||||
| References: | Qiskit: qiskit.org | ||||||||
| Student Requirements: | Fluency with Python; some experience with machine learning | ||||||||
| Programs: |
This AO can be done under the following programs:
|
<< Prev Record 28 of 59 Next >> Back To List