Analog architectures for neural network acceleration based on non-volatile memory

HIGHLIGHTS

• who: T. Patrick Xiao et al. from the Sandia National Laboratories, Albuquerque, New Mexico, USA have published the research: Analog architectures for neural network acceleration based on non-volatile memory, in the Journal: (JOURNAL)
• what: The authors explore and consolidate the various approaches that have been proposed to address the critical challenges faced by analog accelerators for both neural network inference and training and highlight the key design trade-offs underlying these techniques. Resistive crossbars have notably also been explored for accelerating several related computational kernels, such as solving linear systems10,11 and combinatorial optimization . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.