The explicit kernel transformation of input data vectors to their distributed high-dimensional representations has recently been receiving increasing attention in the field of hyperdimensional computing (HDC). The main argument is that such representations endow simpler last-leg classification models, often referred to as HDC classifiers. HDC models have obvious advantages over resource-intensive deep learning models for use cases requiring fast, energy-efficient computations both for model training and deploying. Recent approaches to training HDC classifiers have primarily focused on various methods for selecting individual learning rates for incorrectly classified samples. In contrast to these methods, we propose an alternative strategy where the decision to learn is based on a margin applied to the classifier scores. This approach ensures that even correctly classified samples within the specified margin are utilized in training the model. This leads to improved test performances while maintaining a basic learning rule with a fixed (unit) learning rate. We propose and empirically evaluate two such strategies, incorporating either an additive or multiplicative margin, on the standard subset of the UCI collection, consisting of 121 datasets. Our approach demonstrates superior mean accuracy compared to other HDC classifiers with iterative error-correcting training.

Hyperdimensional computing (HDC) is a powerful algorithmic framework at the intersection of symbolic and neural network Artificial Intelligence. In particular, HDC has received significant attention as a suitable candidate for low-resource machine learning tasks, exemplified by wearable Internet of Things. To solve classification tasks, HDC transforms input data to a high-dimensional space and uses simple component-wise vector operations to create, train, and operate the classification model. While the classical centroid model has been often used in HDC, iterative updating of centroids with wrongly classified samples improves the classification performance. In this paper, using a large and variable collection of 121 UCI datasets, we explore how confidence-driven training of centroids formed from HDC representations further improves the classification accuracy Keywords: centroid, linear classifier, non-linear data transformation, hyperdimensional computing, vector symbolic architecture.

The proliferation of Artificial Neural Networks (ANNs) has led to increased energy consumption, raising concerns about their sustainability. Spiking Neural Networks (SNNs), which are inspired by biological neural systems and operate using sparse, event-driven spikes to communicate information between neurons, offer a potential solution due to their lower energy requirements. An alternative technique for reducing a neural network's footprint is quantization, which compresses weight representations to decrease memory usage and energy consumption. In this study, we present Twin Network Augmentation (TNA), a novel training framework aimed at improving the performance of SNNs while also facilitating an enhanced compression through low-precision quantization of weights. TNA involves co-training an SNN with a twin network, optimizing both networks to minimize their cross-entropy losses and the mean squared error between their output logits. We demonstrate that TNA significantly enhances classification performance across various vision datasets and in addition is particularly effective when applied when reducing SNNs to ternary weight precision. Notably, during inference , only the ternary SNN is retained, significantly reducing the network in number of neurons, connectivity and weight size representation. Our results show that TNA outperforms traditional knowledge distillation methods and achieves state-of-the-art performance for the evaluated network architecture on benchmark datasets, including CIFAR-10, CIFAR-100, and CIFAR-10-DVS. This paper underscores the effectiveness of TNA in bridging the performance gap between SNNs and ANNs and suggests further exploration into the application of TNA in different network architectures and datasets.