HyperSeed: Unsupervised Learning with Vector Symbolic Architectures

Osipov, Evgeny; Kahawala, Sachin; Haputhanthri, Dilantha; Kempitiya, Thimal; Silva, Daswin De; Alahakoon, Damminda; Kleyko, Denis

doi:10.48550/arxiv.2110.08343

Cited by 1 publication

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the Clintox dataset, it includes D-MPNN 17,18 , MoleHD 19 and 2 methods, Random Forest(RF) and Graph Convolutional Networks (GCN) from "MoleculeNet of deepchem" 20,21 . For the language recognition task, it includes Random Indexing 22 , Robust and Energy-Efficient Classifier (REEC) 23 , HyperSeed 24 and SOMs 25 .…”

Section: Training Settingsmentioning

confidence: 99%

See 1 more Smart Citation

Automated Architecture Search for Brain-inspired Hyperdimensional Computing

Yang¹,

Sangbong²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper represents the first effort to explore an automated architecture search for hyperdimensional computing (HDC), a type of brain-inspired neural network. Currently, HDC design is largely carried out in an application-specific ad-hoc manner, which significantly limits its application. Furthermore, the approach leads to inferior accuracy and efficiency, which suggests that HDC cannot perform competitively against deep neural networks. Herein, we present a thorough study to formulate an HDC architecture search space. On top of the search space, we apply reinforcement-learning to automatically explore the HDC architectures. The searched HDC architectures show competitive performance on case studies involving a drug discovery dataset and a language recognition task. On the Clintox dataset, which tries to learn features from developed drugs that passed/failed clinical trials for toxicity reasons, the searched HDC architecture obtains the state-of-the-art ROC-AUC scores, which are 0.80% higher than the manually designed HDC and 9.75% higher than conventional neural networks. Similar results are achieved on the language recognition task, with 1.27% higher performance than conventional methods.

show abstract

Section: Training Settingsmentioning

confidence: 99%

“…For the language recognition task, we still use the accuracy, which is the percentage of samples in the test (validation) set that are identified correctly. -97.80% REEC 23 -97.10% HyperSeed 24 -91.00% SOMs 25 -95.70%…”

Section: /8mentioning

confidence: 99%