Preprints

Disentangling and Mitigating the Impact of Task Similarity for Continual Learning

Naoki Hiratani

arXiv:2405.20236 (2024; accepted to NeurIPS 2024)

[PDF] [Code]

Publications

Sequential activity of CA1 hippocampal cells constitutes a temporal memory map for associative learning in mice

Ma M , Simoes de Souza F , Futia G , Anderson S , Riguero J , Tollin D , Gentile-Polese A , Platt J , Hiratani N , Gibson EA, Restrepo D.

Current Biology, 2024; DOI:10.1016/j.cub.2024.01.021

[Paper]

Evolution of neural activity in circuits bridging sensory and abstract knowledge 

Mastrogiuseppe F, Hiratani N, Latham PE

ELife, 2023;12:e79908

[Paper]

Optimal quadratic binding for relational reasoning in vector symbolic neural architectures

Hiratani N, Sompolinsky H

Neural Computation 35 (2): 105–155, 2023.

[Paper] [Preprint] [Code]

On the stability and scalability of node perturbation learning

Hiratani N, Mehta Y, Lillicrap TP, Latham PE 

NeurIPS 2022

[Paper] [Supplementary Information] [Code]

Developmental and evolutionary constraints on olfactory circuit selection

Hiratani N, Latham PE

Proc. Natl. Acad. Sci. U.S.A., 119 (11), e2100600119 (2022)

[Paper] [Supplementary Information] [Code]

The Olfactory Bulb Facilitates Use of Category Bounds for Classification of Odorants in Different Intensity Groups

Losacco J, George NM, Hiratani N, Restrepo D

Frontiers in Cellular Neuroscience 14, 430 (2020) 

[Paper] [Code]

Rapid Bayesian learning in the mammalian olfactory system

Hiratani N, Latham PE

Nature communications 11, 3845 (2020)

[Paper] [Code]

Interactive reservoir computing for chunking information streams.

Asabuki T, Hiratani N, Fukai T

PLOS Computational Biology, 14(10), e1006400 (2018). 

[Paper]

Redundancy in synaptic connections enables neurons to learn optimally. 

Hiratani N, Fukai T

Proc. Natl. Acad. Sci. U.S.A. 115 (29) E6871-E6879 (2018).

[Paper] [Code]

Detailed dendritic excitatory/inhibitory balance through heterosynaptic spike-timing-dependent plasticity. 

Hiratani N, Fukai T

Journal of Neuroscience, 37 (50) 12106-12122 (2017).

[Paper]

Earlier works

  • Hiratani N, Fukai T. Hebbian Wiring Plasticity Generates Efficient Network Structures for Robust Inference with Synaptic Weight Plasticity. Frontiers in Neural Circuits 10:41 (2016) .

  • Hiratani N, Fukai T. Mixed Signal Learning by Spike Correlation Propagation in Feedback Inhibitory Circuits. PLOS Computational Biology 11(4): e1004227 (2015).

  • Hiratani N, Fukai T. Interplay between short- and long-term plasticity in cell-assembly formation. PLOS ONE. 9(7):e101535 (2014).

  • Hiratani N, Teramae J-N, Fukai T. Associative memory model with long-tail-distributed Hebbian synaptic connections. Frontiers in Computational Neuroscience 6:102 (2013).