Edward Paxon Frady

Edward Paxon Frady

Auto-generated profile, based on publicly available information

Edward Paxon Frady

Neuromorphic Computing Lab, Intel Labs, Santa Clara, USA

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 June 2024 in Nature Machine Intelligence
Verified
Journal Article
Closed access
PDF file
ARAlpha Renner
Alpha Renner
LSLazar Supic
Lazar Supic
ADAndreea Danielescu
Andreea Danielescu
GIGiacomo Indiveri
Giacomo Indiveri
BOBruno A. Olshausen
Bruno A. Olshausen
EFE. Paxon Frady
E. Paxon Frady

26 May 2022 in Journal of Signal Processing Systems
Verified
Journal Article
Closed access
PDF file
EFE. Paxon Frady
E. Paxon Frady
SSSophia Sanborn
Sophia Sanborn
SSSumit Bam Shrestha
Sumit Bam Shrestha
DRDaniel Ben Dayan Rubin
Daniel Ben Dayan Rubin
GOGarrick Orchard
Garrick Orchard
MDMike Davies
Mike Davies

12 June 2023 in Neural Computation
Verified
Journal Article
Closed access
PDF file
DKDenis Kleyko
Denis Kleyko
CBConnor Bybee
Connor Bybee
PHPing-Chen Huang
Ping-Chen Huang
CKChristopher J. Kymn
Christopher J. Kymn
BOBruno A. Olshausen
Bruno A. Olshausen
FSFriedrich Sommer
Friedrich Sommer
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 an overview of the decoding techniques that can be used to approach the retrieval task. The techniques are categorized into four groups. We then evaluate the considered techniques in several settings that involve, for example, inclusion of external noise and storage elements with reduced precision. In particular, we find that the decoding techniques from the sparse coding and compressed sensing literature (rarely used for hyperdimensional computing/vector symbolic architectures) are also well suited for decoding information from the compositional distributed representations. Combining these decoding techniques with interference cancellation ideas from communications improves previously reported bounds (Hersche et al., 2021) of the information rate of the distributed representations from 1.20 to 1.40 bits per dimension for smaller codebooks and from 0.60 to 1.26 bits per dimension for larger codebooks.

27 June 2024 in Nature Machine Intelligence
Verified
Journal Article
Closed access
PDF file
ARAlpha Renner
Alpha Renner
LSLazar Supic
Lazar Supic
ADAndreea Danielescu
Andreea Danielescu
GIGiacomo Indiveri
Giacomo Indiveri
EFE. Paxon Frady
E. Paxon Frady
YSYulia Sandamirskaya
Yulia Sandamirskaya

12 December 2024 in Neural Computation
Verified
Journal Article
Closed access
PDF file
CKChristopher J. Kymn
Christopher J. Kymn
DKDenis Kleyko
Denis Kleyko
EFE. Paxon Frady
E. Paxon Frady
CBConnor Bybee
Connor Bybee
PKPentti Kanerva
Pentti Kanerva
BOBruno A. Olshausen
Bruno A. Olshausen
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 manner that allows algebraic operations to be performed with component-wise, parallelizable operations on the vector elements. The resulting framework, when combined with an efficient method for factorizing high-dimensional vectors, can represent and operate on numerical values over a large dynamic range using resources that scale only logarithmically with the range, a vast improvement over previous methods. It also exhibits impressive robustness to noise. We demonstrate the potential for this framework to solve computationally difficult problems in visual perception and combinatorial optimization, showing improvement over baseline methods. More broadly, the framework provides a possible account for the computational operations of grid cells in the brain, and it suggests new machine learning architectures for representing and manipulating numerical data.

20 July 2023 in arXiv
Verified
Preprint
Open access
PDF file
DKDenis Kleyko
Denis Kleyko
MDMike Davies
Mike Davies
EFE. Paxon Frady
E. Paxon Frady
PKPentti Kanerva
Pentti Kanerva
SKSpencer J. Kent
Spencer J. Kent
FSFriedrich Sommer
Friedrich Sommer
This article reviews recent progress in the development of the computing framework vector symbolic architectures (VSA) (also known as hyperdimensional computing). This framework is well suited for implementation in stochastic, emerging hardware, and it naturally expresses the types of cognitive operations required for artificial intelligence (AI). We demonstrate in this article that the field-like algebraic structure of VSA offers simple but powerful operations on high-dimensional vectors that can support all data structures and manipulations relevant to modern computing. In addition, we illustrate the distinguishing feature of VSA, "computing in superposition," which sets it apart from conventional computing. It also opens the door to efficient solutions to the difficult combinatorial search problems inherent in AI applications. We sketch ways of demonstrating that VSA are computationally universal. We see them acting as a framework for computing with distributed representations that can play a role of an abstraction layer for emerging computing hardware. This article serves as a reference for computer architects by illustrating the philosophy behind VSA, techniques of distributed computing with them, and their relevance to emerging computing hardware, such as neuromorphic computing.