Self-supervised predictive learning accounts for cortical layer-specificity
Nejad, K.K., Anastasiades, P., Hertäg, L. and Costa, R.P.
Nature Communications, 16(1), p.6178 (2025)
Kevin Kermani Nejad
Finishing my PhD in ML and Computational Neuroscience at Neural and Machine Learning Group at University of Oxford. My supervisor is Rui Ponte Costa.
My primary research is at the intersection of self-supervised learning in biological and artificial neural networks.
I did my MSc in Applied Mathematics at University of Edinburgh. My supervisor was Ben Leimkuhler. My research was understanding optimisation and learning in artificial neural networks from the lens of molecular dynamics. My undergraduate was Computer Science at King's College London.
I love to talk about topics such as computational creativity, generative models, AI for Scientific Discovery. Please feel free to reach out to me, I'd love to know about others' research and views on these topics and related areas.
Publications
Large language models surpass human experts in predicting neuroscience results
Luo, X., Rechardt, A., Sun, G., Nejad, K.K., Yáñez, F., Yilmaz, B., Lee, K., Cohen, A.O., Borghesani, V., Pashkov, A. and Marinazzo, D.
Nature Human Behaviour, 9(2), pp.305-315 (2025)
Multilevel interpretability of artificial neural networks: leveraging framework and methods from neuroscience
He, Z., Achterberg, J., Collins, K., Nejad, K., Akarca, D., Yang, Y., Gurnee, W., Sucholutsky, I., Tang, Y., Ianov, R. and Ogden, G.
arXiv preprint, arXiv:2408.12664 (2024)