Hi, I'm Noor.
I think about the computational principles underlying natural decision-making in health and disease.
My research is grounded in developing generative models for understanding and mimicking natural decision-making to investigate how artificial agents can adapt to and learn from environmental perturbations, similar to humans and animals. Importantly, these models can serve as a useful tool to understand neural (dys)function and design causal interventions post-neurological damage.
Briefly, I investigate the computations necessary for (1) designing appropriate generative models for decision-making, and (2) using them to investigate decision-making in health and damage.
Designing generative models for decision-making by considering:
How to encode robust environment dynamics?
(Fountas, Sajid, et al, NeurIPs, 2020; Yuan*, Sajid*, et al, Nature Machine Intelligence, 2023; Gumbsch, Sajid, et al, ICLR Spotlight, 2024)
What sorts of context-dependent planning strategies are needed?
(Sajid, Ball, et al, Neural Computation, 2021; Sajid, Tigas, et al, ICML URL, 2021)
How do the underlying inference & learning schemes influence behaviour?
(Sajid*, Faccio*, et al Neural Computations, 2022; Sajid, Convertino, Friston, Entropy, 2021; Parr, Sajid, Friston, Entropy, 2020)
Investigating natural decision-making in health and damage.
How to formalise function in neuronal architectures?
(Sajid, Parr, et al, Cerebral Cortex, 2020; Sajid, Gajardo-Vidal, et al, Biological Communications, 2023)
What sorts of lesions give rise to (mal)adaptive behaviour?
(Sajid, Holmes, et al, Scientific Reports, 2021, Sajid, Parr, et al, Brain Communications, 2021)
Gumbsch, C., Sajid, N., Martius, G. et al. (2024) Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics. ICRL Spotlight.
Yuan, K.*, Sajid, N.*, Friston, K. et al. (2023) Hierarchical generative modelling for autonomous robots. Nat Mach Intell 5, 1402–1414.
[paper]
Featured Talks
Maths in the Brain Workshop (2023)
Information-Theoretic Principles in Cognitive Systems (InfoCog) workshop at NeurIPs (2022)
Active Inference Symposium on Robotics (2022)
Workshops
Co-organiser: NeuroAI at NeurIPS2024
Co-organiser: Temporal representations in reinforcement learning (TRiRL) workshop at RLDM2022
Co-organiser: International workshop on Active Inference (IWAI) 2022 at ECML/PKDD2022; IWAI 2023; IWAI 2024
Co-organiser: WiML UnWorkshop 2022 at ICML2022
Co-organiser: Postgraduate Research Conference 2022 at UCL IoN
Public Engagement
UCL Pint of Science on modelling human-like behaviour (2024)
Minds Matter Podcast on modelling and active inference (2022)
Data Study Group lead at Alan Turing Institute (2019)
Data Science Award Judge for TeenTechUK (2018)
Data Student Participant at Alan Turing Institute (2018)
STEM Mentor for TeenTechUK (2017-2018)