activity
20222026
most citedTorchhd: An Open Source Python Library to Support Research on Hyperdimensional Computing and Vector Symbolic Architectures

15 citations · 44 across the 12 of their papers we have counts for

collaborators

12 papers

cs.DS2026

Approximating Tensor Network Contraction with Sketches

Mike Heddes, Igor Nunes, Tony Givargis +1

Tensor network contraction is a fundamental mathematical operation that generalizes the dot product and matrix multiplication. It finds applications in numerous domains, such as da…

cs.LG2025

Advancing Intoxication Detection: A Smartwatch-Based Approach

Manuel Segura, Pere Vergés, Richard Ky +7

Excess alcohol consumption leads to serious health risks and severe consequences for both individuals and their communities. To advocate for healthier drinking habits, we introduce…

cs.LG2024★ 1 cited

Enhanced Detection of Transdermal Alcohol Levels Using Hyperdimensional Computing on Embedded Devices

Manuel E. Segura, Pere Verges, Justin Tian Jin Chen +6

Alcohol consumption has a significant impact on individuals' health, with even more pronounced consequences when consumption becomes excessive. One approach to promoting healthier…

cs.LG2024★ 2 cited

Molecular Classification Using Hyperdimensional Graph Classification

Pere Verges, Igor Nunes, Mike Heddes +2

Our work introduces an innovative approach to graph learning by leveraging Hyperdimensional Computing. Graphs serve as a widely embraced method for conveying information, and their…

cs.DB2024★ 5 cited

Convolution and Cross-Correlation of Count Sketches Enables Fast Cardinality Estimation of Multi-Join Queries

Mike Heddes, Igor Nunes, Tony Givargis +1

With the increasing rate of data generated by critical systems, estimating functions on streaming data has become essential. This demand has driven numerous advancements in algorit…

cs.LG2024

Always-Sparse Training by Growing Connections with Guided Stochastic Exploration

Mike Heddes, Narayan Srinivasa, Tony Givargis +1

The excessive computational requirements of modern artificial neural networks (ANNs) are posing limitations on the machines that can run them. Sparsification of ANNs is often motiv…