Zhuowen Zou
YOU?
Author Swipe
View article: Lipschitz-based robustness estimation for hyperdimensional learning
Lipschitz-based robustness estimation for hyperdimensional learning Open
With the adoption of machine learning models in various practical domains, there is a growing need for evaluating and increasing model robustness. Hyperdimensional computing (HDC) is a neurosymbolic computational paradigm that represents s…
View article: Cognitive map formation under uncertainty via local prediction learning
Cognitive map formation under uncertainty via local prediction learning Open
Cognitive maps are internal world models that enable adaptive behaviour including spatial navigation and planning. The Cognitive Map Learner (CML) has been recently proposed as a model for cognitive map formation and planning. A CML learns…
View article: Configuration and Charge Dynamics of Defect‐Cluster‐Dipoles in CaTiO<sub>3</sub> for Enhanced Permittivity
Configuration and Charge Dynamics of Defect‐Cluster‐Dipoles in CaTiO<sub>3</sub> for Enhanced Permittivity Open
The wealth of complex defects induces attractive functionalities and structural variations in materials. This renders engineering defect states, as well as building up a defect‐property relationship, a central subject, but it remains highl…
View article: Hyperdimensional Quantum Factorization
Hyperdimensional Quantum Factorization Open
This paper presents a quantum algorithm for efficiently decoding hypervectors, a crucial process in extracting atomic elements from hypervectors - an essential task in Hyperdimensional Computing (HDC) models for interpretable learning and …
View article: NetHD: Neurally Inspired Integration of Communication and Learning in Hyperspace
NetHD: Neurally Inspired Integration of Communication and Learning in Hyperspace Open
The 6G network, the next‐generation communication system, is envisaged to provide unprecedented experience through hyperconnectivity involving everything. The communication should hold artificial intelligence‐centric network infrastructure…
View article: Generalized Holographic Reduced Representations
Generalized Holographic Reduced Representations Open
Deep learning has achieved remarkable success in recent years. Central to its success is its ability to learn representations that preserve task-relevant structure. However, massive energy, compute, and data costs are required to learn gen…
View article: Efficient event-based robotic grasping perception using hyperdimensional computing
Efficient event-based robotic grasping perception using hyperdimensional computing Open
Grasping is fundamental in various robotic applications, particularly within industrial contexts. Accurate inference of object properties is a crucial step toward enhancing grasping quality. Dynamic and Active Vision Sensors (DAVIS), incre…
View article: Hyperdimensional computing with holographic and adaptive encoder
Hyperdimensional computing with holographic and adaptive encoder Open
Introduction Brain-inspired computing has become an emerging field, where a growing number of works focus on developing algorithms that bring machine learning closer to human brains at the functional level. As one of the promising directio…
View article: HDReason: Algorithm-Hardware Codesign for Hyperdimensional Knowledge Graph Reasoning
HDReason: Algorithm-Hardware Codesign for Hyperdimensional Knowledge Graph Reasoning Open
In recent times, a plethora of hardware accelerators have been put forth for graph learning applications such as vertex classification and graph classification. However, previous works have paid little attention to Knowledge Graph Completi…
View article: Conjunctive block coding for hyperdimensional graph representation
Conjunctive block coding for hyperdimensional graph representation Open
Knowledge Graphs (KGs) have become a pivotal knowledge representation tool in machine learning, not only providing access to existing knowledge but also enabling the discovery of new knowledge through advanced applications. Among the scala…
View article: HEAL: Brain-inspired Hyperdimensional Efficient Active Learning
HEAL: Brain-inspired Hyperdimensional Efficient Active Learning Open
Drawing inspiration from the outstanding learning capability of our human brains, Hyperdimensional Computing (HDC) emerges as a novel computing paradigm, and it leverages high-dimensional vector presentation and operations for brain-like l…
View article: Optimal decoding of neural dynamics occurs at mesoscale spatial and temporal resolutions
Optimal decoding of neural dynamics occurs at mesoscale spatial and temporal resolutions Open
Introduction Understanding the neural code has been one of the central aims of neuroscience research for decades. Spikes are commonly referred to as the units of information transfer, but multi-unit activity (MUA) recordings are routinely …
View article: Efficient Event-Based Robotic Grasping Perception using Hyperdimensional Computing
Efficient Event-Based Robotic Grasping Perception using Hyperdimensional Computing Open
Grasping is Fundamental in various robotic applications, particularly within industrial contexts. Accurate inference of object properties is a crucial step toward enhancing grasping quality. Dynamic and Active Vision Sensors (DAVIS), incre…
View article: Optimal Decoding of Neural Dynamics Occurs at Mesoscale Spatial and Temporal Resolutions
Optimal Decoding of Neural Dynamics Occurs at Mesoscale Spatial and Temporal Resolutions Open
Introduction Understanding the neural code has been one of the central aims of neuroscience research for decades. Spikes are commonly referred to as the units of information transfer, but multi-unit activity (MUA) recordings are routinely …
View article: EventHD: Robust and efficient hyperdimensional learning with neuromorphic sensor
EventHD: Robust and efficient hyperdimensional learning with neuromorphic sensor Open
Brain-inspired computing models have shown great potential to outperform today's deep learning solutions in terms of robustness and energy efficiency. Particularly, Hyper-Dimensional Computing (HDC) has shown promising results in enabling …
View article: BioHD
BioHD Open
In this paper, we propose BioHD, a novel genomic sequence searching platform based on Hyper-Dimensional Computing (HDC) for hardware-friendly computation. BioHD transforms inherent sequential processes of genome matching to highly-parallel…
View article: Memory-inspired spiking hyperdimensional network for robust online learning
Memory-inspired spiking hyperdimensional network for robust online learning Open
Recently, brain-inspired computing models have shown great potential to outperform today’s deep learning solutions in terms of robustness and energy efficiency. Particularly, Spiking Neural Networks (SNNs) and HyperDimensional Computing (H…
View article: Scalable edge-based hyperdimensional learning system with brain-like neural adaptation
Scalable edge-based hyperdimensional learning system with brain-like neural adaptation Open
In the Internet of Things (IoT) domain, many applications are running machine learning algorithms to assimilate the data collected in the swarm of devices. Sending all data to the powerful computing environment, e.g., cloud, poses signific…
View article: Spiking Hyperdimensional Network: Neuromorphic Models Integrated with Memory-Inspired Framework
Spiking Hyperdimensional Network: Neuromorphic Models Integrated with Memory-Inspired Framework Open
Recently, brain-inspired computing models have shown great potential to outperform today's deep learning solutions in terms of robustness and energy efficiency. Particularly, Spiking Neural Networks (SNNs) and HyperDimensional Computing (H…
View article: MIMHD: Accurate and Efficient Hyperdimensional Inference Using Multi-Bit In-Memory Computing
MIMHD: Accurate and Efficient Hyperdimensional Inference Using Multi-Bit In-Memory Computing Open
Hyperdimensional Computing (HDC) is an emerging computational framework that mimics important brain functions by operating over high-dimensional vectors, called hypervectors (HVs). In-memory computing implementations of HDC are desirable s…