Vector symbolic architectures as a computing framework for emerging hardware
This article reviews recent progress in the development of the computing framework vector
symbolic architectures (VSA)(also known as hyperdimensional computing). This framework …
symbolic architectures (VSA)(also known as hyperdimensional computing). This framework …
Graphd: Graph-based hyperdimensional memorization for brain-like cognitive learning
Memorization is an essential functionality that enables today's machine learning algorithms
to provide a high quality of learning and reasoning for each prediction. Memorization gives …
to provide a high quality of learning and reasoning for each prediction. Memorization gives …
Biohd: an efficient genome sequence search platform using hyperdimensional memorization
In this paper, we propose BioHD, a novel genomic sequence searching platform based on
Hyper-Dimensional Computing (HDC) for hardware-friendly computation. BioHD transforms …
Hyper-Dimensional Computing (HDC) for hardware-friendly computation. BioHD transforms …
Neural computation for robust and holographic face detection
Face detection is an essential component of many tasks in computer vision with several
applications. However, existing deep learning solutions are significantly slow and inefficient …
applications. However, existing deep learning solutions are significantly slow and inefficient …
Hdpg: Hyperdimensional policy-based reinforcement learning for continuous control
Traditional robot control or more general continuous control tasks often rely on carefully
hand-crafted classic control methods. These models often lack the self-learning adaptability …
hand-crafted classic control methods. These models often lack the self-learning adaptability …
Hdnn-pim: Efficient in memory design of hyperdimensional computing with feature extraction
A Dutta, S Gupta, B Khaleghi… - Proceedings of the …, 2022 - dl.acm.org
Brain-inspired Hyperdimensional (HD) computing is a new machine learning approach that
leverages simple and highly parallelizable operations. Unfortunately, none of the published …
leverages simple and highly parallelizable operations. Unfortunately, none of the published …
Algorithm-hardware co-design for efficient brain-inspired hyperdimensional learning on edge
Machine learning methods have been widely utilized to provide high quality for many
cognitive tasks. Running sophisticated learning tasks requires high computational costs to …
cognitive tasks. Running sophisticated learning tasks requires high computational costs to …
Mathematical models of computation in superposition
Superposition--when a neural network represents more``features''than it has dimensions--
seems to pose a serious challenge to mechanistically interpreting current AI systems …
seems to pose a serious challenge to mechanistically interpreting current AI systems …
Adaptive neural recovery for highly robust brain-like representation
Today's machine learning platforms have major robustness issues dealing with insecure
and unreliable memory systems. In conventional data representation, bit flips due to noise or …
and unreliable memory systems. In conventional data representation, bit flips due to noise or …
Spatialhd: Spatial transformer fused with hyperdimensional computing for ai applications
Brain-inspired computing methods have shown remarkable efficiency and robustness
compared to deep neural networks (DNN). In particular, HyperDimensional Computing …
compared to deep neural networks (DNN). In particular, HyperDimensional Computing …