Zobrazeno 1 - 10
of 219
pro vyhledávání: '"Olshausen, Bruno A."'
Autor:
Kymn, Christopher J., Mazelet, Sonia, Thomas, Anthony, Kleyko, Denis, Frady, E. Paxon, Sommer, Friedrich T., Olshausen, Bruno A.
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 rep
Externí odkaz:
http://arxiv.org/abs/2406.18808
Compositional Factorization of Visual Scenes with Convolutional Sparse Coding and Resonator Networks
Publikováno v:
2024 Neuro Inspired Computational Elements Conference (NICE)
We propose a system for visual scene analysis and recognition based on encoding the sparse, latent feature-representation of an image into a high-dimensional vector that is subsequently factorized to parse scene content. The sparse feature representa
Externí odkaz:
http://arxiv.org/abs/2404.19126
Autor:
Kymn, Christopher J., Kleyko, Denis, Frady, E. Paxon, Bybee, Connor, Kanerva, Pentti, Sommer, Friedrich T., Olshausen, Bruno A.
We introduce Residue Hyperdimensional Computing, a computing framework that unifies residue number systems with an algebra defined over random, high-dimensional vectors. We show how residue numbers can be represented as high-dimensional vectors in a
Externí odkaz:
http://arxiv.org/abs/2311.04872
Unsupervised representation learning has seen tremendous progress but is constrained by its reliance on data modality-specific stationarity and topology, a limitation not found in biological intelligence systems. For instance, human vision processes
Externí odkaz:
http://arxiv.org/abs/2310.04496
Autor:
Kleyko, Denis, Bybee, Connor, Huang, Ping-Chen, Kymn, Christopher J., Olshausen, Bruno A., Frady, E. Paxon, Sommer, Friedrich T.
Publikováno v:
Neural Computation, 2023
We investigate the task of retrieving information from compositional distributed representations formed by Hyperdimensional Computing/Vector Symbolic Architectures and present novel techniques which achieve new information rate bounds. First, we prov
Externí odkaz:
http://arxiv.org/abs/2305.16873
When interacting in a three dimensional world, humans must estimate 3D structure from visual inputs projected down to two dimensional retinal images. It has been shown that humans use the persistence of object shape over motion-induced transformation
Externí odkaz:
http://arxiv.org/abs/2303.17776
Autor:
Frady, E. Paxon, Kent, Spencer, Tran, Quinn, Kanerva, Pentti, Olshausen, Bruno A., Sommer, Friedrich T.
Complex visual scenes that are composed of multiple objects, each with attributes, such as object name, location, pose, color, etc., are challenging to describe in order to train neural networks. Usually,deep learning networks are trained supervised
Externí odkaz:
http://arxiv.org/abs/2303.13691
Autor:
Pergament, Evgenya, Tandon, Pulkit, Rippel, Oren, Bourdev, Lubomir, Anderson, Alexander G., Olshausen, Bruno, Weissman, Tsachy, Katti, Sachin, Tatwawadi, Kedar
Human perception is at the core of lossy video compression, with numerous approaches developed for perceptual quality assessment and improvement over the past two decades. In the determination of perceptual quality, different spatio-temporal regions
Externí odkaz:
http://arxiv.org/abs/2212.10674
Autor:
Bybee, Connor, Kleyko, Denis, Nikonov, Dmitri E., Khosrowshahi, Amir, Olshausen, Bruno A., Sommer, Friedrich T.
A prominent approach to solving combinatorial optimization problems on parallel hardware is Ising machines, i.e., hardware implementations of networks of interacting binary spin variables. Most Ising machines leverage second-order interactions althou
Externí odkaz:
http://arxiv.org/abs/2212.03426
Autor:
Zador, Anthony, Escola, Sean, Richards, Blake, Ölveczky, Bence, Bengio, Yoshua, Boahen, Kwabena, Botvinick, Matthew, Chklovskii, Dmitri, Churchland, Anne, Clopath, Claudia, DiCarlo, James, Ganguli, Surya, Hawkins, Jeff, Koerding, Konrad, Koulakov, Alexei, LeCun, Yann, Lillicrap, Timothy, Marblestone, Adam, Olshausen, Bruno, Pouget, Alexandre, Savin, Cristina, Sejnowski, Terrence, Simoncelli, Eero, Solla, Sara, Sussillo, David, Tolias, Andreas S., Tsao, Doris
Neuroscience has long been an essential driver of progress in artificial intelligence (AI). We propose that to accelerate progress in AI, we must invest in fundamental research in NeuroAI. A core component of this is the embodied Turing test, which c
Externí odkaz:
http://arxiv.org/abs/2210.08340