» Authors » Friedrich T Sommer

Friedrich T Sommer

Explore the profile of Friedrich T Sommer including associated specialties, affiliations and a list of published articles. Areas
Snapshot
Articles 52
Citations 1071
Followers 0
Related Specialties
Top 10 Co-Authors
Published In
Affiliations
Soon will be listed here.
Recent Articles
1.
Kleyko D, Kymn C, Thomas A, Olshausen B, Sommer F, Frady E
Nat Commun . 2025 Jan; 16(1):640. PMID: 39809739
Reservoir computing advances the intriguing idea that a nonlinear recurrent neural circuit-the reservoir-can encode spatio-temporal input signals to enable efficient ways to perform tasks like classification or regression. However, recently...
2.
Kymn C, Kleyko D, Frady E, Bybee C, Kanerva P, Sommer F, et al.
Neural Comput . 2024 Nov; 37(1):1-37. PMID: 39556514
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...
3.
Kymn C, Mazelet S, Thomas A, Kleyko D, Frady E, Sommer F, et al.
ArXiv . 2024 Jul; PMID: 38979486
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...
4.
Agarwal G, Lustig B, Akera S, Pastalkova E, Lee A, Sommer F
bioRxiv . 2024 Jan; PMID: 38187593
Local field potentials (LFPs) reflect the collective dynamics of neural populations, yet their exact relationship to neural codes remains unknown. One notable exception is the theta rhythm of the rodent...
5.
Kymn C, Kleyko D, Frady E, Bybee C, Kanerva P, Sommer F, et al.
ArXiv . 2023 Nov; PMID: 37986727
We introduce , 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...
6.
Li Z, Chen Y, Sommer F
Entropy (Basel) . 2023 Oct; 25(10). PMID: 37895489
Energy-based models (EBMs) assign an unnormalized log probability to data samples. This functionality has a variety of applications, such as sample synthesis, data denoising, sample restoration, outlier detection, Bayesian reasoning...
7.
Kleyko D, Davies M, Frady E, Kanerva P, Kent S, Olshausen B, et al.
Proc IEEE Inst Electr Electron Eng . 2023 Oct; 110(10):1538-1571. PMID: 37868615
This article reviews recent progress in the development of the computing framework (also known as Hyperdimensional Computing). This framework is well suited for implementation in stochastic, emerging hardware and it...
8.
Bybee C, Kleyko D, Nikonov D, Khosrowshahi A, Olshausen B, Sommer F
Nat Commun . 2023 Sep; 14(1):6033. PMID: 37758716
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...
9.
Gorin A, Miao Y, Ahn S, Suresh V, Su Y, Ciftcioglu U, et al.
bioRxiv . 2023 Aug; PMID: 37609295
By influencing the type and quality of information that relay cells transmit, local interneurons in thalamus have a powerful impact on cortex. To define the sensory features that these inhibitory...
10.
Kleyko D, Bybee C, Huang P, Kymn C, Olshausen B, Frady E, et al.
Neural Comput . 2023 May; 35(7):1159-1186. PMID: 37187162
We investigate the task of retrieving information from compositional distributed representations formed by hyperdimensional computing/vector symbolic architectures and present novel techniques that achieve new information rate bounds. First, we provide...