Grounded HyperSymbolic Representations Learned through Gradient-Based Optimization
Ładowanie...
Data
2023
Tytuł czasopisma
ISSN czasopisma
Tytuł tomu
Wydawca
Wydawnictwo Politechniki Łódzkiej
Lodz University of Technology Press
Lodz University of Technology Press
Abstrakt
Hyperdimensional computing is a novel paradigm, capable of
processing complex data structures with simple operations. Its main limitations
lie in the conversion of real world data onto hyperdimensional space,
which due to lack of a universal translation scheme, oftentimes requires
application-specific methods. This work presents a novel method for unsupervised
hyperdimensional conversion of arbitrary image data. Additionally,
this method is augmented by the ability of creating HyperSymbols, or
class prototypes, provided that such class labels are available. The proposed
method achieves promising performance on MNIST dataset, both in translating
individual samples as well as producing HyperSymbols for downstream
classification task.
Opis
Słowa kluczowe
artificial intelligence, hyperdimensional computing, representation extraction, neuromorphic architectures, sztuczna inteligencja, obliczenia hiperwymiarowe, ekstrakcja reprezentacji, architektury neuromorficzne
Cytowanie
Łuczak P., Ślot K., Kucharski J., Grounded HyperSymbolic Representations Learned through Gradient-Based Optimization. W: Progress in Polish Artificial Intelligence Research 4, Wojciechowski A. (Ed.), Lipiński P. (Ed.)., Seria: Monografie Politechniki Łódzkiej Nr. 2437, Wydawnictwo Politechniki Łódzkiej, Łódź 2023, s. 319-324, ISBN 978-83-66741-92-8, doi: 10.34658/9788366741928.51.