One Analog Neuron Cannot Recognize Deterministic Context-Free Languages
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F19%3A00505945" target="_blank" >RIV/67985807:_____/19:00505945 - isvavai.cz</a>
Výsledek na webu
<a href="https://www.springer.com/gp/book/9783030367176" target="_blank" >https://www.springer.com/gp/book/9783030367176</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-030-36718-3_7" target="_blank" >10.1007/978-3-030-36718-3_7</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
One Analog Neuron Cannot Recognize Deterministic Context-Free Languages
Popis výsledku v původním jazyce
We analyze the computational power of discrete-time recurrent neural networks (NNs) with the saturated-linear activation function within the Chomsky hierarchy. This model restricted to integer weights coincides with binary-state NNs with the Heaviside activation function, which are equivalent to finite automata (Chomsky level 3), while rational weights make this model Turing complete even for three analog-state units (Chomsky level 0). For an intermediate model alphaANN of a binary-state NN that is extended with alpha>=0 extra analog-state neurons with rational weights, we have established the analog neuron hierarchy 0ANNs subset 1ANNs subset 2ANNs subseteq 3ANNs. The separation 1ANNs subsetneq 2ANNs has been witnessed by the deterministic context-free language (DCFL) L_#={0^n1^n|n>=1} which cannot be recognized by any 1ANN even with real weights, while any DCFL (Chomsky level 2) is accepted by a 2ANN with rational weights. In this paper, we generalize this result by showing that any non-regular DCFL cannot be recognized by 1ANNs with real weights, which means (DCFLs-REG) subset (2ANNs-1ANNs), implying 0ANNs = 1ANNs cap DCFLs. For this purpose, we show that L_# is the simplest non-regular DCFL by reducing L_# to any language in this class, which is by itself an interesting achievement in computability theory.
Název v anglickém jazyce
One Analog Neuron Cannot Recognize Deterministic Context-Free Languages
Popis výsledku anglicky
We analyze the computational power of discrete-time recurrent neural networks (NNs) with the saturated-linear activation function within the Chomsky hierarchy. This model restricted to integer weights coincides with binary-state NNs with the Heaviside activation function, which are equivalent to finite automata (Chomsky level 3), while rational weights make this model Turing complete even for three analog-state units (Chomsky level 0). For an intermediate model alphaANN of a binary-state NN that is extended with alpha>=0 extra analog-state neurons with rational weights, we have established the analog neuron hierarchy 0ANNs subset 1ANNs subset 2ANNs subseteq 3ANNs. The separation 1ANNs subsetneq 2ANNs has been witnessed by the deterministic context-free language (DCFL) L_#={0^n1^n|n>=1} which cannot be recognized by any 1ANN even with real weights, while any DCFL (Chomsky level 2) is accepted by a 2ANN with rational weights. In this paper, we generalize this result by showing that any non-regular DCFL cannot be recognized by 1ANNs with real weights, which means (DCFLs-REG) subset (2ANNs-1ANNs), implying 0ANNs = 1ANNs cap DCFLs. For this purpose, we show that L_# is the simplest non-regular DCFL by reducing L_# to any language in this class, which is by itself an interesting achievement in computability theory.
Klasifikace
Druh
D - Stať ve sborníku
CEP obor
—
OECD FORD obor
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Návaznosti výsledku
Projekt
<a href="/cs/project/GA19-05704S" target="_blank" >GA19-05704S: FoNeCo: Analytické základy neurovýpočtů</a><br>
Návaznosti
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Ostatní
Rok uplatnění
2019
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
Neural Information Processing. Proceedings, Part III
ISBN
978-3-030-36717-6
ISSN
—
e-ISSN
—
Počet stran výsledku
13
Strana od-do
77-89
Název nakladatele
Springer
Místo vydání
Heidelberg
Místo konání akce
Sydney
Datum konání akce
12. 12. 2019
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
—