Graduate Student
The work will entail:
We are leveraging quantum tools to benchmark methods that study the geometry and topology of large
datasets, culminating in a submission to Neurips2025. We aim to utilize geometric and topological
features to increase interpretability and optimize training time of neural networks.
Quantum-inspired benchmarks for large datasets
- One year of relevant graduate-level research experience in neural networks.
- Familiarity with coding and running neural networks.
- Strong oral and written communication skills.
Key responsibilities will include but are not limited to:
- Developing computational tools to study the geometry and topology of human-made datasets
- Running benchmarks that compare different techniques to study various datasets
- Writing manuscripts and submitting to top conferences such as Neurips.