The Kording Lab at the University of Pennsylvania, led by Nathan Mossell University Professor Konrad Kording, operates at the cutting edge intersection of causality, machine learning, and neuroscience. The lab's primary focus has evolved from computational motor control to tackling one of science's most fundamental challenges: understanding causal relationships in complex systems where randomization isn't possible. Kording's team develops innovative approaches that combine deep learning with causal inference methods to analyze neural data, understand brain function, and advance neurotechnology. Beyond traditional neuroscience, the lab champions open science and educational equity through initiatives like Neuromatch, which has trained thousands of students worldwide, and the Community for Rigor, which addresses biases and logical fallacies in research. Their work spans from theoretical frameworks linking artificial and biological intelligence to practical applications in brain-computer interfaces, neural data analysis, and novel imaging technologies. With a uniquely interdisciplinary and collaborative approach, the Kording Lab has become a hub for researchers interested in using data-driven methods to understand how brains compute, how causality can be inferred from observational data, and how machine learning principles can illuminate neural mechanisms—all while maintaining a strong commitment to scientific rigor and global accessibility of knowledge.

Causality and Machine learning.
Machine Learning and Deep Learning for Neuroscience.
Neuroscience for Deep Learning.
and Machine Learning for Movement/Meta-Science. KordingLab    KordingLab    kording@upenn.edu