My work bridges mathematical neuroscience and machine learning. Leveraging dynamical systems theory, stochastic analysis, and physics-informed machine learning, I develop data-driven models of neurons and large-scale brain activity to better understand pathological dynamics in disorders such as epilepsy and Parkinson’s disease. Drawing inspiration from neural computation, I design neuroscience-inspired machine-learning algorithms that deepen our fundamental insight into brain function while powering new algorithms, neurotechnologies, and medical applications.

 

Research projects

  • Dynamical systems theory
  • Stochastic analysis
  • Statistical physics
  • Mathematical and computational neuroscience
  • Data-driven methods for neuronal and brain dynamics
  • Mathematical and data-driven modelling of epilepsy and Parkinson’s disease
  • Neuroscience-inspired machine learning (e.g., liquid-state machines)
  • Physics-informed machine learning and constrained optimisation

Related Research Fields:

Contact: