Neuro-Inspired Quantization

This paper presents a novel neuro-inspired quantization model which is the extension of the recently released perfect-Leaky Integrate and Fire (LIF) model. We propose that the LIF, which is a very efficient neuromathematical model that describes the spike generation neural mechanism, can lead to a g...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings - International Conference on Image Processing s. 689 - 693
Hlavní autoři: Doutsi, Effrosyni, Fillatre, Lionel, Antonini, Marc, Gaulmin, Julien
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.10.2018
Témata:
Decoding
Delays
Image coding
Image reconstruction
Leaky Integrate and Fire (LIF) model
Neuron
Neurons
Nickel
Quantization (signal)
Uniform Deadzone Quantization (UDQ)
Visual system
ISSN:2381-8549
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This paper presents a novel neuro-inspired quantization model which is the extension of the recently released perfect-Leaky Integrate and Fire (LIF) model. We propose that the LIF, which is a very efficient neuromathematical model that describes the spike generation neural mechanism, can lead to a groundbreaking and above all dynamic compression algorithm which is called LIF encoder/decoder. We also prove that under some assumptions, there is a link between the novel LIF encoder/decoder and the conventional Uniform Deadzone Quantizer (UDQ).
ISSN:2381-8549
DOI:10.1109/ICIP.2018.8451793