This page collects numerous recordings of webinars on various HD/VSA topics. 

Please also check the page with the videos.

Please let us know if some webinars are currently missing and should be added to this page. We will take care of updating the page. 

Compositional Vector Semantics in Spiking Neural Networks

Modelling Neural Probabilistic Computation Using Vector Symbolic Architectures

Brain-Inspired Hyperdimensional Computing in the Wild: Lightweight Symbolic Learning for Sensorimotor Controls of Wheeled Robots

Speaker: Yeseong Kim

Date: December 11, 2023

HW/SW Codesign for Brain-Inspired Hyperdimensional In-Memory Computing

Capacity Analysis of Vector Symbolic Architectures

A Tour Through Learning with High-Dimensional Representations: VSAs, Kernel Methods, and Randomized Embeddings 

Speaker: Anthony Thomas

Date: October 30, 2023

SupportHDC: Hyperdimensional Computing with Scalable Hypervector Sparsity

Hardware-Aware Static Optimization of Hyperdimensional Computations

Local Prediction-learning in High-dimensional Spaces Enables Neural Networks to Plan

Mappings Between Lower Dimensional and Hyperdimensional Embedding Spaces

Speaker: Tony Plate

Date: September 11, 2023

Panel: HD/VSA as a Scientific & Engineering Discipline

Date: June 15, 2023

Efficient Decoding of Compositional Structure in Holistic Representations

Hyper-Dimensional Function Encoding: Enable Neural Network to Process Continuous Objects

In-memory Factorization of Holographic Perceptual Representations

A Neuro-vector-symbolic Architecture for Solving Raven’s Progressive Matrices

Vector Symbolic Finite State Machines in Attractor Neural Networks

Hyperdimensional Computing with Applications

Speaker: Tajana Simunic Rosing

Date: March 20, 2023

Papers: Please see the slides

Unpaired Image Translation via Vector Symbolic Architectures

Hyperdimensional Feature Fusion for Out-Of-Distribution Detection

Vector Algebras on Loihi 2

Speaker: E. Paxon Frady

Date: February 6, 2023

Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations

Panel: Work-in-Progress and Future Perspective Directions in HD/VSA

Date: December 19, 2022

Hashing: A Robust and Efficient Dynamic Hash Table

Graph Embeddings via Tensor Products and Approximately Orthonormal Codes

HDC-MiniROCKET: Explicit Time Encoding in Time Series Classification with Hyperdimensional Computing

Recasting Self-Attention with Holographic Reduced Representations

Torchhd: An Open-Source Python Library to Support Hyperdimensional Computing Research

VSA-based Few-shot Continual Learning with a Demonstration on In-memory Computing Hardware

Attention Approximates Sparse Distributed Memory

Hyperdimensional Computing using Time-to-Spike Neuromorphic Circuits

Bridging Neural and Symbolic Representation for Simultaneous Localization and Mapping

Understanding Hyperdimensional Computing for Parallel Single-Pass Learning

Orthogonal Matrices for MBAT Vector Symbolic Architectures, and a "Soft" VSA Representation for JSON

Fractional Binding in Vector Symbolic Representations for Efficient Mutual Information Exploration

Linguistic Semantics and Geometry

Speaker: Jussi Karlgren

Date: March 28, 2022

Paper: Semantics in High-Dimensional Space

Similarity-Based Attention for Vector-Symbolic Architectures

Speaker: Wilkie Olin-Ammentorp

Date: March 14, 2022

Large-scale Systems Optimization: From Oscillatory Physics to High-dimensional Vector Memories

Speaker: Cristian Axenie

Date: February 14, 2022

Ontology as Manifold: Towards Symbolic and Numerical Artificial Embedding

Reiterating on Main Postulates of VSA with Hyperseed: What is English of Sweden?

Computing on Functions Using Randomized Vector Representations

Near-channel Classifier: Symbiotic Communication and Classification in High-dimensional Space

Generalized Learning Vector Quantization for Classification in Randomized Neural Networks and Hyperdimensional  Computing

Functional representations in VSA

Learning and compressing Tensor Product Representations for large-scale AI problems

Robust High-dimensional Memory-augmented Neural Networks

Boundary and Normal States of Consciousness

Quantum Mathematics in Artificial Intelligence

Combining Vector Symbolic Architecture and Semiotic Approach to Solve Visual Question Answering Task

Sequence Structure in the Human Brain: Vector Symbolic Architectures as a Neurocomputational Lingua Franca

Compressing Many Subject-specific Brain-Computer Interface Models into One Model by Hyperdimensional Superposition

Hyperdimensional Computing for Efficient and Robust Learning

Speaker: Mohsen Imani

Date: December 14, 2020

HDM: Hyper-Dimensional Modulation for Reliable Wireless Communication

Vector-Symbolic Approach to In-memory Realization of Kohonen’s Self-Organizing Maps

Speaker: Evgeny Osipov

Date: November 18, 2020

Comparison of Vector Symbolic Architectures

Speaker: Kenny Schlegel

Date: November 16, 2020

Preprint: A comparison of Vector Symbolic Architectures

A Neural-Network-Like Mechanism for Learning with Hyperdimensional Vectors

In-memory Hyperdimensional Computing

Word Similarity Estimation with Vector Symbolic Architectures

Vector Representations + Addition + Multiplication = Conceptual Reasoning

Speaker: Tony Plate

Date: July 13, 2020

Indirect Associations in Learning Semantic and Syntactic Lexical Relationships

Dynamic Distributed Orchestration of Node-RED IoT Workflows Using a Vector Symbolic Architecture

Speaker: Graham Bent

Date: June 29, 2020

Hyperdimensional Computing in Robotics and Comparison of VSAs

Towards a Holographic Model of Working Memory

Speaker: Stefan Reimann

Date: June 1, 2020

Vector Symbolic Architectures and Density Encoding as Enablers for Resource-Efficient Randomly Connected Neural Networks

Logic and Images with a VSA

Speaker: Hedda R. Schmidtke

Date: May 18, 2020

VSA, Analogy, and Dynamic Similarity

Speaker: Ross W. Gayler

Date: May 18, 2020

The Squinting Linguist Meets Hyperdimensional Computing