Rescuing memristor-based neuromorphic design with high defects

Memristor-based synaptic network has been widely investigated and applied to neuromorphic computing systems for the fast computation and low design cost. As memristors continue to mature and achieve higher density, bit failures within crossbar arrays can become a critical issue. These can degrade th...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2017 54th ACM/EDAC/IEEE Design Automation Conference (DAC) s. 1 - 6
Hlavní autoři: Chenchen Liu, Miao Hu, Strachan, John Paul, Hai Li
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2017
Témata:
Degradation
Hardware
Memristors
Neural networks
Neuromorphics
Redundancy
Training
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Memristor-based synaptic network has been widely investigated and applied to neuromorphic computing systems for the fast computation and low design cost. As memristors continue to mature and achieve higher density, bit failures within crossbar arrays can become a critical issue. These can degrade the computation accuracy significantly. In this work, we propose a defect rescuing design to restore the computation accuracy. In our proposed design, significant weights in a specified network are first identified and retraining and remapping algorithms are described. For a two layer neural network with 92.64% classification accuracy on MNIST digit recognition, our evaluation based on real device testing shows that our design can recover almost its full performance when 20% random defects are present.
DOI:10.1145/3061639.3062310