A curated list of papers in Hyperdimensional Computing / Vector Symbolic Architectures (HD/VSA).
If you have any papers to add or suggestions for improvement, please feel free to open an issue or submit a pull request.
| Title | Authors | Publication | Summary | Link |
|---|---|---|---|---|
| Hyperdimensional Computing: An Introduction to Computing in Distributed Representation with High-Dimensional Random Vectors | Pentti Kanerva | Cognitive Computation, 2009 | This paper introduces the concept of hyperdimensional computing, explaining how high-dimensional random vectors can be used for distributed representation and computation. | Paper |
| Fully Distributed Representation | Pentti Kanerva | Real World Computing Symposium, 1997 | This paper introduces Binary Spatter Codes (BSC), a model of HD/VSA that uses binary vectors and bitwise operations. | Paper |
| A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations & Part II: Applications, Cognitive Models, and Challenges | Denis Kleyko, Dmitri A. Rachkovskij, Evgeny Osipov, Abbas Rahimi | ACM Computing Surveys, 2022 & 2023 | This 2-part survey paper provides a comprehensive overview of the field of HD/VSA. | Part I, Part II |
| Title | Authors | Publication | Summary | Link |
|---|---|---|---|---|
| OnlineHD: Robust, Efficient, and Single-Pass Online Learning Using Hyperdimensional System | Alejandro Hernández-Cano, Namiko Matsumoto, Eric Ping, Mohsen Imani | DATE, 2021 | This paper presents OnlineHD, an adaptive learning algorithm for hyperdimensional computing that achieves higher classification accuracy than single-pass models. After a single-pass training, OnlineHD iteratively updates the model memory based on the similarity score. | Paper |
| LeHDC: Learning-Based Hyperdimensional Computing Classifier | Shijin Duan, Yejia Liu, Shaolei Ren, Xiaolin Xu | DAC, 2022 | This paper introduces LeHDC, which replaces the label prediction stage in the HD classification pipeline with a binary neural network and uses a neural network's training strategy to minimize loss. | Paper |
| A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devices | Shijin Duan, Xiaolin Xu, Shaolei Ren | TinyML, 2022 | LDC uses low-dimensional vectors to achieve high accuracy by mapping its operations to an equivalent neural network and using a principled training approach. | Paper |
| HyperCam: Low-Power Onboard Computer Vision for IoT Cameras | Chae Young Lee, Pu (Luke) Yi, Maxwell Fite, Tejus Rao, Sara Achour, Zerina Kapetanovic | ArXiv, 2025 | This paper introduces HyperCam, an onboard HD classifier for low-power IoT cameras. For real-time inference, HyperCam uses novel encoding methods that aggressively reduce memory consumption and latency. | Paper |
| Title | Authors | Publication | Summary | Link |
|---|---|---|---|---|
| Resonator Networks, 1: : An Efficient Solution for Factoring High-Dimensional, Distributed Representations of Data Structures | E. Paxon Frady, Spencer J. Kent, Bruno A. Olshausen, Friedrich T. Sommer | Neural Computation, 2020 | Resonar Networks represents a class-class relation in an attempt to solve the factorization problem in the VSA framework. | Paper |
- VSAOnline: a bi-weekly webinar on HD/VSA, featuring most up-to-date work