Vector Symbolic Algebras and Neural Computation

Join Dr. Michael Furlong to explore Vector Symbolic Algebras (VSAs), how they unify symbolic reasoning with connectionist models, and their computational benefits.

Vector Symbolic Algebras (VSAs) are a family of frameworks developed to unify symbolic reasoning and connectionist models. In this way, they provide a rigorous way to talk about neural computation. While VSAs may appear a niche interest at first blush, they have ties to other well-established models of computation.

In this talk, Dr. Michael Furlong will highlight the connections between different computing models and underscore some of the computational benefits that can be gained by adopting VSAs as a computing model.

About the Speaker

Michael Furlong

Michael Furlong

Dr. Michael Furlong is a research officer at the National Research Council of Canada / University of Waterloo Collaboration Centre, focusing on probabilistic models of neural computation.

Event Production & Support

Social share preview for Vector Symbolic Algebras and Neural Computation

Upcoming Workshops

No workshops are currently scheduled. Check back soon for new events!

Are you an expert in a neuromorphic topic? We invite you to share your knowledge with our community.

Inspired? Share your work.

Share your expertise with the community by speaking at a workshop, student talk, or hacking hour. It’s a great way to get feedback and help others learn.

Related Workshops

Tonic: Building the PyTorch Vision of Neuromorphic Data Loading

Tonic: Building the PyTorch Vision of Neuromorphic Data Loading

The Tonic library standardizes event-based data loading and transformation, providing a PyTorch-compatible pipeline that accelerates SNN model training.

Low-power Spiking Neural Network Processing Systems for Extreme-Edge Applications

Low-power Spiking Neural Network Processing Systems for Extreme-Edge Applications

The Microbrain architecture combines asynchronous processing and Forward Propagation Through Time (FPTT) to train 6.2-million-neuron SNNs.

Hands-On with snnTorch

Hands-On with snnTorch

snnTorch applies surrogate gradients to overcome the non-differentiability of spikes, enabling SNN training and quantization using standard PyTorch pipelines.