معرفی
Amos Storkey is a Professor at the School of Informatics, University of Edinburgh, with a focus on machine learning, Bayesian methods, and their applications in neuroscience and astronomy. His research spans deep learning, generative models, and stochastic optimization under real-world constraints.
Education:
- MA in Mathematics, Trinity College, Cambridge (1989)
- Part III (Theoretical Physics), Trinity College, Cambridge (1992)
- PhD in Neural Networks, Imperial College London (1995)
Research Interests: Storkey’s work addresses core challenges in machine learning, including model understanding, efficiency, and transfer learning. Key topics include:
- Generative Models: Applications in medical imaging (brain/retinal) and music generation.
- Bayesian & Probabilistic Methods: In healthcare, astronomy, and diffusion processes.
- Optimization & Reinforcement Learning: Stochastic systems, meta-learning, and few-shot learning.
- Medical Applications: Structural connectivity analysis in ALS and aging studies.
Article Trends: Recent publications emphasize interdisciplinary applications of machine learning, with 5/15 focused on neuroscience (fMRI, ALS, aging), 3/15 on optimization/sampling, and 2/15 on astronomical data analysis. Emerging themes include machine learning markets and generative models for hallucinations.
