Zobrazeno 1 - 10
of 281
pro vyhledávání: '"Sommer Friedrich T"'
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
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
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
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:
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:
Renner, Alpha, Supic, Lazar, Danielescu, Andreea, Indiveri, Giacomo, Frady, E. Paxon, Sommer, Friedrich T., Sandamirskaya, Yulia
Publikováno v:
Nature Machine Intelligence 6 (2024)
Visual Odometry (VO) is a method to estimate self-motion of a mobile robot using visual sensors. Unlike odometry based on integrating differential measurements that can accumulate errors, such as inertial sensors or wheel encoders, visual odometry is
Externí odkaz:
http://arxiv.org/abs/2209.02000
Autor:
Renner, Alpha, Supic, Lazar, Danielescu, Andreea, Indiveri, Giacomo, Olshausen, Bruno A., Sandamirskaya, Yulia, Sommer, Friedrich T., Frady, E. Paxon
Publikováno v:
Nature Machine Intelligence 6 (2024)
Analyzing a visual scene by inferring the configuration of a generative model is widely considered the most flexible and generalizable approach to scene understanding. Yet, one major problem is the computational challenge of the inference procedure,
Externí odkaz:
http://arxiv.org/abs/2208.12880
An open problem in neuroscience is to explain the functional role of oscillations in neural networks, contributing, for example, to perception, attention, and memory. Cross-frequency coupling (CFC) is associated with information integration across po
Externí odkaz:
http://arxiv.org/abs/2204.07163
Spiking Neural Networks (SNNs) have attracted the attention of the deep learning community for use in low-latency, low-power neuromorphic hardware, as well as models for understanding neuroscience. In this paper, we introduce Spiking Phasor Neural Ne
Externí odkaz:
http://arxiv.org/abs/2204.00507
Autor:
Kleyko, Denis, Bybee, Connor, Kymn, Christopher J., Olshausen, Bruno A., Khosrowshahi, Amir, Nikonov, Dmitri E., Sommer, Friedrich T., Frady, E. Paxon
Publikováno v:
NICE 2022: Neuro-Inspired Computational Elements Conference
In this paper, we present an approach to integer factorization using distributed representations formed with Vector Symbolic Architectures. The approach formulates integer factorization in a manner such that it can be solved using neural networks and
Externí odkaz:
http://arxiv.org/abs/2203.00920