Gluing Neural Networks Symbolically Through Hyperdimensional Computing

TL;DR

This paper introduces a method to fuse multiple neural networks using hyperdimensional computing, enabling efficient, online, and lifelong learning by encoding network outputs as hypervectors and combining them through consensus summation.

Contribution

It presents a novel approach to symbolically fuse neural networks using hyperdimensional vectors, improving efficiency and enabling lifelong learning with minimal overhead.

Findings

Outperforms or matches state-of-the-art methods.

Supports online learning and model adaptation.

Enables lifelong learning through hypervector memory structures.

Abstract

Hyperdimensional Computing affords simple, yet powerful operations to create long Hyperdimensional Vectors (hypervectors) that can efficiently encode information, be used for learning, and are dynamic enough to be modified on the fly. In this paper, we explore the notion of using binary hypervectors to directly encode the final, classifying output signals of neural networks in order to fuse differing networks together at the symbolic level. This allows multiple neural networks to work together to solve a problem, with little additional overhead. Output signals just before classification are encoded as hypervectors and bundled together through consensus summation to train a classification hypervector. This process can be performed iteratively and even on single neural networks by instead making a consensus of multiple classification hypervectors. We find that this outperforms the state of the art, or is on a par with it, while using very little overhead, as hypervector operations are extremely fast and efficient in comparison to the neural networks. This consensus process can learn online and even grow or lose models in real time. Hypervectors act as memories that can be stored, and even further bundled together over time, affording life long learning capabilities. Additionally, this consensus structure inherits the benefits of Hyperdimensional Computing, without sacrificing the performance of modern Machine Learning. This technique can be extrapolated to virtually any neural model, and requires little modification to employ - one simply requires recording the output signals of networks when presented with a testing example.