Konrad Kording



  • Fellow
  • Learning in Machines & Brains


  • University of Pennsylvania
Departments of Bioengineering and Neuroscience


  • United States


Physics, ETH Zurich


Konrad Kording seeks to understand the brain as a computational device.

He sees considerable limitations in the standard way neuroscience studies the brain and how to mine neural data for causal relations. Deep learning provides an alternative way of thinking about brains, focusing on cost functions, optimization algorithms and specialized structures. Working towards a deep learning–based view of the brain, the Kording lab broadly uses data analysis methods, including machine learning, to ask fundamental questions.


NIH Transformative Research Award (R01)

PIK Professor, University of Pennsylvania

Relevant Publications

Glaser, J.I. et al. "Machine learning for neural decoding." arXiv:1708.00909 (2017–18).

Vilares, I., and K.P. Kording. "Dopaminergic Medication Increases Reliance on Current Information in Parkinson's Disease." Nature Human Behaviour 1 (2017).

Saeb, S. et al. "The need to approximate the use-case in clinical machine learning." GigaScience 6, no. 5:1–9.

Jonas, E., and K.P. Kording. "Could a neuroscientist understand a microprocessor?" PLoS computational biology 13, no. 1:e1005268.

Glaser, J.I. et al. "Population Coding Of Conditional Probability Distributions In Dorsal Premotor Cortex." Nat Commun. 9 (2018).