AIConfPaper
← Search

Dmitri Chklovskii

13 accepted papers

2026

A Network of Biologically Inspired Rectified Spectral Units (ReSUs) Learns Hierarchical Features Without Error Backpropagation

Shanshan Qin, Joshua L. Pughe-Sanford, Alexander Genkin, Pembe Gizem Ozdil, Philip Greengard, Anirvan M. Sengupta +1
AAAI 2026technical

We introduce a biologically inspired, multilayer neural architecture composed of Rectified Spectral Units (ReSUs). Each ReSU projects a recent window of its input history onto a canonical direction obtained via canonical correlation analysis (CCA) of previously observed past–future input pairs, and

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Neurons as Detectors of Coherent Sets in Sensory Dynamics

Joshua L. Pughe-Sanford, Xuehao Ding, Jason J Moore, Anirvan M. Sengupta, Charles Epstein, Philip Greengard +1
NeurIPS 2025poster

We model sensory streams as observations from high-dimensional stochastic dynamical systems and conceptualize sensory neurons as self-supervised learners of compact representations of such dynamics. From prior experience, neurons learn {\it coherent sets}—regions of stimulus state space whose trajec…

Cited by 1Source ↗Scholar ↗
2023

Adaptive Whitening in Neural Populations with Gain-modulating Interneurons

Lyndon Duong, David Lipshutz, David Heeger, Dmitri Chklovskii, Eero P Simoncelli
ICML 2023poster

Statistical whitening transformations play a fundamental role in many computational systems, and may also play an important role in biological sensory systems. Existing neural circuit models of adaptive whitening operate by modifying synaptic interactions; however, such modifications would seem both…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2023

Adaptive whitening with fast gain modulation and slow synaptic plasticity

Lyndon Duong, Eero P Simoncelli, Dmitri Chklovskii, David Lipshutz
NeurIPS 2023spotlight

Neurons in early sensory areas rapidly adapt to changing sensory statistics, both by normalizing the variance of their individual responses and by reducing correlations between their responses. Together, these transformations may be viewed as an adaptive form of statistical whitening. Existing mecha…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2023

Interneurons accelerate learning dynamics in recurrent neural networks for statistical adaptation

David Lipshutz, Cengiz Pehlevan, Dmitri Chklovskii
ICLR 2023poster

Early sensory systems in the brain rapidly adapt to fluctuating input statistics, which requires recurrent communication between neurons. Mechanistically, such recurrent communication is often indirect and mediated by local interneurons. In this work, we explore the computational benefits of mediati…

Cited by 10Source ↗PDF ↗Scholar ↗
2022

Biological Learning of Irreducible Representations of Commuting Transformations

Alexander Genkin, David Lipshutz, Siavash Golkar, Tiberiu Tesileanu, Dmitri Chklovskii
NeurIPS 2022accept

A longstanding challenge in neuroscience is to understand neural mechanisms underlying the brain’s remarkable ability to learn and detect transformations of objects due to motion. Translations and rotations of images can be viewed as orthogonal transformations in the space of pixel intensity vectors…

Cited by 4Source ↗PDF ↗Scholar ↗
2022

Constrained Predictive Coding as a Biologically Plausible Model of the Cortical Hierarchy

Siavash Golkar, Tiberiu Tesileanu, Yanis Bahroun, Anirvan M. Sengupta, Dmitri Chklovskii
NeurIPS 2022accept

Predictive coding (PC) has emerged as an influential normative model of neural computation with numerous extensions and applications. As such, much effort has been put into mapping PC faithfully onto the cortex, but there are issues that remain unresolved or controversial. In particular, current imp…

Cited by 16Source ↗PDF ↗code ↗Scholar ↗
2021

A Normative and Biologically Plausible Algorithm for Independent Component Analysis

Yanis Bahroun, Dmitri Chklovskii, Anirvan M. Sengupta
NeurIPS 2021spotlight

The brain effortlessly solves blind source separation (BSS) problems, but the algorithm it uses remains elusive. In signal processing, linear BSS problems are often solved by Independent Component Analysis (ICA). To serve as a model of a biological circuit, the ICA neural network (NN) must satisfy a…

Cited by 11Source ↗PDF ↗Scholar ↗
2021

Neural optimal feedback control with local learning rules

Johannes Friedrich, Siavash Golkar, Shiva Farashahi, Alexander Genkin, Anirvan M. Sengupta, Dmitri Chklovskii
NeurIPS 2021spotlight

A major problem in motor control is understanding how the brain plans and executes proper movements in the face of delayed and noisy stimuli. A prominent framework for addressing such control problems is Optimal Feedback Control (OFC). OFC generates control actions that optimize behaviorally relevan…

Cited by 16Source ↗PDF ↗Scholar ↗
2019

A Similarity-preserving Network Trained on Transformed Images Recapitulates Salient Features of the Fly Motion Detection Circuit

Yanis Bahroun, Dmitri Chklovskii, Anirvan Sengupta
NeurIPS 2019poster

Learning to detect content-independent transformations from data is one of the central problems in biological and artificial intelligence. An example of such problem is unsupervised learning of a visual motion detector from pairs of consecutive video frames. Rao and Ruderman formulated this problem…

Cited by 15Source ↗PDF ↗Scholar ↗
2018

Manifold-tiling Localized Receptive Fields are Optimal in Similarity-preserving Neural Networks

Anirvan Sengupta, Cengiz Pehlevan, Mariano Tepper, Alexander Genkin, Dmitri Chklovskii
NeurIPS 2018poster

Many neurons in the brain, such as place cells in the rodent hippocampus, have localized receptive fields, i.e., they respond to a small neighborhood of stimulus space. What is the functional significance of such representations and how can they arise? Here, we propose that localized receptive field…

Cited by 46Source ↗PDF ↗code ↗Scholar ↗
2017

OnACID: Online Analysis of Calcium Imaging Data in Real Time

Andrea Giovannucci, Johannes Friedrich, Matt Kaufman, Anne Churchland, Dmitri Chklovskii, Liam Paninski +1
NeurIPS 2017poster

Optical imaging methods using calcium indicators are critical for monitoring the activity of large neuronal populations in vivo. Imaging experiments typically generate a large amount of data that needs to be processed to extract the activity of the imaged neuronal sources. While deriving such proces…

Cited by 85Source ↗PDF ↗Scholar ↗
2015

A Normative Theory of Adaptive Dimensionality Reduction in Neural Networks

Cengiz Pehlevan, Dmitri Chklovskii
NeurIPS 2015poster

To make sense of the world our brains must analyze high-dimensional datasets streamed by our sensory organs. Because such analysis begins with dimensionality reduction, modelling early sensory processing requires biologically plausible online dimensionality reduction algorithms. Recently, we derived…

Cited by 63Source ↗PDF ↗Scholar ↗