An Encoding Framework for Binarized Images using HyperDimensional Computing

Abstract

Hyperdimensional Computing (HDC) is a brain-inspired and light-weight machine learning method. It has received significant attention in the literature as a candidate to be applied in the wearable internet of things, near-sensor artificial intelligence applications and on-device processing. HDC is computationally less complex than traditional deep learning algorithms and typically achieves moderate to good classification performance. A key aspect that determines the performance of HDC is the encoding of the input data to the hyperdimensional (HD) space. This article proposes a novel light-weight approach relying only on native HD arithmetic vector operations to encode binarized images that preserves similarity of patterns at nearby locations by using point of interest selection and local linear mapping. The method reaches an accuracy of 97.35% on the test set for the MNIST data set and 84.12% for the Fashion-MNIST data set. These results outperform other studies using baseline HDC with different encoding approaches and are on par with more complex hybrid HDC models. The proposed encoding approach also demonstrates a higher robustness to noise and blur compared to the baseline encoding.

References in corpus (19)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• BinaryConnect: Training Deep Neural Networks with binary weights during propagations
• FINN: A Framework for Fast, Scalable Binarized Neural Network Inference
• A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations
• BS4NN: Binarized Spiking Neural Networks with Temporal Coding and Learning
• Embedded Binarized Neural Networks
• Holographic Graph Neuron: a Bio-Inspired Architecture for Pattern Processing
• MNIST-C: A Robustness Benchmark for Computer Vision
• Training Binary Multilayer Neural Networks for Image Classification using Expectation Backpropagation
• Training a HyperDimensional Computing Classifier using a Threshold on its Confidence
• Understanding Hyperdimensional Computing for Parallel Single-Pass Learning
• Adversarial Attacks on Brain-Inspired Hyperdimensional Computing-Based Classifiers
• A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devices
• Hyperdimensional Computing vs. Neural Networks: Comparing Architecture and Learning Process
• Memory-Efficient, Limb Position-Aware Hand Gesture Recognition using Hyperdimensional Computing
• HDC-MiniROCKET: Explicit Time Encoding in Time Series Classification with Hyperdimensional Computing
• LeHDC: Learning-Based Hyperdimensional Computing Classifier
• HDTest: Differential Fuzz Testing of Brain-Inspired Hyperdimensional Computing