Neural Power Units
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00347207" target="_blank" >RIV/68407700:21230/20:00347207 - isvavai.cz</a>
Result on the web
<a href="https://proceedings.neurips.cc/paper/2020/hash/48e59000d7dfcf6c1d96ce4a603ed738-Abstract.html" target="_blank" >https://proceedings.neurips.cc/paper/2020/hash/48e59000d7dfcf6c1d96ce4a603ed738-Abstract.html</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Neural Power Units
Original language description
Conventional Neural Networks can approximate simple arithmetic operations, but fail to generalize beyond the range of numbers that were seen during training. Neural Arithmetic Units aim to overcome this difficulty, but current arithmetic units are either limited to operate on positive numbers or can only represent a subset of arithmetic operations. We introduce the Neural Power Unit (NPU) that operates on the full domain of real numbers and is capable of learning arbitrary power functions in a single layer. The NPU thus fixes the shortcomings of existing arithmetic units and extends their expressivity. We achieve this by using complex arithmetic without requiring a conversion of the network to complex numbers. A simplification of the unit to the RealNPU yields a highly transparent model. We show that the NPUs outperform their competitors in terms of accuracy and sparsity on artificial arithmetic datasets, and that the RealNPU can discover the governing equations of a dynamical system only from data.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Advances in Neural Information Processing Systems 33 (NeurIPS 2020)
ISBN
—
ISSN
1049-5258
e-ISSN
1049-5258
Number of pages
11
Pages from-to
—
Publisher name
Neural Information Processing Society
Place of publication
Montreal
Event location
Vancouver
Event date
Dec 6, 2020
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—