An unsupervised and probabilistic approach to Pavlov's dog experiment with OxRAM devices

In this work, a potential basis for implementing unsupervised associative learning in two or more memristors within neuromorphic architectures is proposed. The experimental demonstration is carried out by means of emulating the Pavlov's dog classical conditioning experiment with two OxRAM devic...

Full description

Saved in:
Bibliographic Details
Published inMicroelectronic engineering Vol. 215; p. 111024
Main Authors Pedro, M., Martin-Martinez, J., Rodriguez, R., Gonzalez, M.B., Campabadal, F., Nafria, M.
Format Journal Article
LanguageEnglish
Published Amsterdam Elsevier B.V 15.07.2019
Elsevier BV
Subjects
Associative learning
Dependence
Dogs
Learning
Memristors
Microelectronics
Neuromorphic
OxRAM
Pulse amplitude
Random access memory
Statistical analysis
Unsupervised learning
Associative learning
Neuromorphic
OxRAM
Memristors
Unsupervised learning
Online AccessGet full text

Cover

More Information
Summary:In this work, a potential basis for implementing unsupervised associative learning in two or more memristors within neuromorphic architectures is proposed. The experimental demonstration is carried out by means of emulating the Pavlov's dog classical conditioning experiment with two OxRAM devices, in which the dependence of the probability of association on test parameters, such as the pulse amplitude, is studied. [Display omitted] •Associative learning implemented in OxRAM synapses permits to recall data by its content, instead of by its location.•The associative process can take place between many electronic synapses sharing one of the neurons they are connected to.•The associative process has to be thought as a voltage-dependent probabilistic event, analogously to biological learning.
ISSN:0167-9317
1873-5568
DOI:10.1016/j.mee.2019.111024