Skip to content
Physics of Intelligence

Publications

Publications.

Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks

Rahul Ramesh, Ekdeep Singh Lubana, Mikail Khona, R.P. Dick, Hidenori Tanaka

ICML 2024 ICML 2024

Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space

Core Francisco Park, Maya Okawa, A. Lee, Hidenori Tanaka, Ekdeep Singh Lubana

NeurIPS 2024 NeurIPS 2024

In-Context Learning Dynamics with Random Binary Sequences

Eric Bigelow, Ekdeep Singh Lubana, R.P. Dick, Hidenori Tanaka, Tomer Ullman

ICLR 2024 ICLR 2024

Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks

S. Jain, R. Kirk, Ekdeep Singh Lubana, R.P. Dick, Hidenori Tanaka, T. Rocktäschel, E. Grefenstette, David Krueger

ICLR 2024 ICLR 2024

Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model

Mikail Khona, Maya Okawa, J. Hula, Rahul Ramesh, Kento Nishi, R.P. Dick, Ekdeep Singh Lubana, Hidenori Tanaka

ICML 2024 ICML 2024

CORNN: Convex optimization of recurrent neural networks for rapid inference of neural dynamics

Fatih Dinc, A. Shai, M. Schnitzer, Hidenori Tanaka

NeurIPS 2023 NeurIPS 2023

Interpreting the retinal neural code for natural scenes: from computations to neurons

N. Maheswaranathan, L.T. McIntosh, Hidenori Tanaka, S. Grant, D.B. Kastner, J.B. Melander, A. Nayebi, L. Brezovec, J. Wang, Surya Ganguli, S.A. Baccus

Neuron 2023 Neuron (2023)

Mechanistic Mode Connectivity

Ekdeep Singh Lubana, Eric Bigelow, R.P. Dick, David Krueger, Hidenori Tanaka

ICML 2023 ICML 2023

Rethinking the limiting dynamics of SGD: modified loss, phase space oscillations and anomalous diffusion

Daniel Kunin, J. Sagastuy-Brena, L. Gillespie, E. Margalit, Hidenori Tanaka, Surya Ganguli, D.L.K. Yamins

Neural Computation 2023 Neural Computation (2023)

What shapes the loss landscape of self-supervised learning?

Ziyin Liu, Ekdeep Singh Lubana, M. Ueda, Hidenori Tanaka

ICLR 2023 ICLR 2023

A lexical approach for identifying behavioural action sequences

Gautam Reddy, L. Desban, Hidenori Tanaka, J. Roussel, O. Mirat, C. Wyart

PLoS Computational Biology 2022 PLoS Computational Biology (2022)

Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning

Ekdeep Singh Lubana, R.P. Dick, Hidenori Tanaka

NeurIPS 2021 NeurIPS 2021

Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics

Daniel Kunin, J. Sagastuy-Brena, Surya Ganguli, D.L.K. Yamins, Hidenori Tanaka

ICLR 2021 ICLR 2021

Noether's Learning Dynamics: Role of Symmetry Breaking in Neural Networks

Hidenori Tanaka, Daniel Kunin

NeurIPS 2021 NeurIPS 2021

Pruning neural networks without any data by iteratively conserving synaptic flow

Hidenori Tanaka, Daniel Kunin, D. Yamins, Surya Ganguli

NeurIPS 2020 NeurIPS 2020

Non-Hermitian quasi-localization and ring attractor neural networks

Hidenori Tanaka, David Nelson

Physical Review E 2018 Physical Review E (2018)

Hot particles attract in a cold bath

Hidenori Tanaka, A.A. Lee, Michael Brenner

Physical Review Fluids 2017 Physical Review Fluids (2017)

Spatial gene drives and pushed genetic waves

Hidenori Tanaka, H.A. Stone, David Nelson

PNAS 2017 PNAS (2017)

Mutation at expanding front of self-replicating colloidal clusters

Hidenori Tanaka, Z. Zeravcic, Michael Brenner

Physical Review Letters 2016 Physical Review Letters (2016)

Quenched metastable vortex states in Sr2RuO4

D. Shibata, Hidenori Tanaka, S. Yonezawa, T. Nojima, Y. Maeno

Physical Review B 2015 Physical Review B (2015)