Bruno Olshausen — accepted AI-conference papers

2024

Binding in hippocampal-entorhinal circuits enables compositionality in cognitive maps

Christopher Kymn, Sonia Mazelet, Anthony Hitchcock Thomas, Denis Kleyko, Edward Paxon Frady, Friedrich Sommer +1

NeurIPS 2024poster

We propose a normative model for spatial representation in the hippocampal formation that combines optimality principles, such as maximizing coding range and spatial information per neuron, with an algebraic framework for computing in distributed representation. Spatial position is encoded in a resi…

Cited by 4 Source ↗PDF ↗Scholar ↗

2023

Bispectral Neural Networks

Sophia Sanborn, Christian A Shewmake, Bruno Olshausen, Christopher J. Hillar

ICLR 2023poster

We present a neural network architecture, Bispectral Neural Networks (BNNs) for learning representations that are invariant to the actions of compact commutative groups on the space over which a signal is defined. The model incorporates the ansatz of the bispectrum, an analytically defined group inv…

Cited by 20 Source ↗PDF ↗code ↗Scholar ↗

2023

Emergence of Sparse Representations from Noise

Trenton Bricken, Rylan Schaeffer, Bruno Olshausen, Gabriel Kreiman

ICML 2023poster

A hallmark of biological neural networks, which distinguishes them from their artificial counterparts, is the high degree of sparsity in their activations. This discrepancy raises three questions our work helps to answer: (i) Why are biological networks so sparse? (ii) What are the benefits of this…

Cited by 16 Source ↗PDF ↗Scholar ↗

2023

Minimalistic Unsupervised Representation Learning with the Sparse Manifold Transform

Yubei Chen, Zeyu Yun, Yi Ma, Bruno Olshausen, Yann LeCun

ICLR 2023top-25%

We describe a minimalistic and interpretable method for unsupervised representation learning that does not require data augmentation, hyperparameter tuning, or other engineering designs, but nonetheless achieves performance close to the state-of-the-art (SOTA) SSL methods. Our approach leverages the…

Cited by 8 Source ↗PDF ↗Scholar ↗

2021

Tent: Fully Test-Time Adaptation by Entropy Minimization

Dequan Wang, Evan Shelhamer, Shaoteng Liu, Bruno Olshausen, Trevor Darrell

ICLR 2021spotlight

A model must adapt itself to generalize to new and different data during testing. In this setting of fully test-time adaptation the model has only the test data and its own parameters. We propose to adapt by test entropy minimization (tent): we optimize the model for confidence as measured by the en…

Cited by 1373 Source ↗PDF ↗code ↗Scholar ↗

2019

Superposition of many models into one

Brian Cheung, Alexander Terekhov, Yubei Chen, Pulkit Agrawal, Bruno Olshausen

NeurIPS 2019poster

We present a method for storing multiple models within a single set of parameters. Models can coexist in superposition and still be retrieved individually. In experiments with neural networks, we show that a surprisingly large number of models can be effectively stored within a single parameter inst…

Cited by 154 Source ↗PDF ↗Scholar ↗

2018

The Sparse Manifold Transform

Yubei Chen, Dylan Paiton, Bruno Olshausen

NeurIPS 2018poster

We present a signal representation framework called the sparse manifold transform that combines key ideas from sparse coding, manifold learning, and slow feature analysis. It turns non-linear transformations in the primary sensory signal space into linear interpolations in a representational embeddi…

Cited by 73 Source ↗PDF ↗Scholar ↗

2017

Emergence of foveal image sampling from learning to attend in visual scenes

Brian Cheung, Eric Weiss, Bruno Olshausen

ICLR 2017poster

We describe a neural attention model with a learnable retinal sampling lattice. The model is trained on a visual search task requiring the classification of an object embedded in a visual scene amidst background distractors using the smallest number of fixations. We explore the tiling properties tha…

Cited by 52 Source ↗Scholar ↗