Memristive Stochastic Computing for Deep Learning Parameter Optimization

  title={Memristive Stochastic Computing for Deep Learning Parameter Optimization},
  author={Corey Lammie and Jason Kamran Eshraghian and Wei D. Lu and Mostafa Rahimi Azghadi},
  journal={IEEE Transactions on Circuits and Systems II: Express Briefs},
Stochastic Computing (SC) is a computing paradigm that allows for the low-cost and low-power computation of various arithmetic operations using stochastic bit streams and digital logic. In contrast to conventional representation schemes used within the binary domain, the sequence of bit streams in the stochastic domain is inconsequential, and computation is usually non-deterministic. In this brief, we exploit the stochasticity during switching of probabilistic Conductive Bridging RAM (CBRAM… Expand
2 Citations

Figures and Tables from this paper

Overleaf Example
The brain is the perfect place to look for inspiration to develop more efficient neural networks. The inner workings of our synapses and neurons provide a glimpse at what the future of deep learningExpand
Training Spiking Neural Networks Using Lessons From Deep Learning
The delicate interplay between encoding data as spikes and the learning process; the challenges and solutions of applying gradient-based learning to spiking neural networks; the subtle link between temporal backpropagation and spike timing dependent plasticity; and how deep learning might move towards biologically plausible online learning are explored. Expand


Memristors—From In‐Memory Computing, Deep Learning Acceleration, and Spiking Neural Networks to the Future of Neuromorphic and Bio‐Inspired Computing
The case for a novel beyond‐complementary metal–oxide–semiconductor (CMOS) technology—memristors)—as a potential solution for the implementation of power‐efficient in‐memory computing, DL accelerators, and spiking neural networks is reviewed. Expand
A Native Stochastic Computing Architecture Enabled by Memristors
This work simulates a memristor-based stochastic processor for gradient descent optimization, and k-means clustering, and demonstrates key advantages in energy and speed in compute-intensive, data- intensive, and probabilistic applications. Expand
Stochastic Memristive Devices for Computing and Neuromorphic Applications
This work demonstrates memristor-based stochastic bitstreams in both time and space domains, and shows that an array of binary memristors can act as a multi-level "analog" device for neuromorphic applications. Expand
A novel true random number generator based on a stochastic diffusive memristor
A novel true random number generator utilizing the stochastic delay time of threshold switching in a Ag:SiO2 diffusive memristor, which exhibits evident advantages in scalability, circuit complexity, and power consumption. Expand
Complementary Metal‐Oxide Semiconductor and Memristive Hardware for Neuromorphic Computing
It is shown that the CMOS and memristive devices are assembled in different neuromorphic learning platforms to perform simple cognitive tasks such as classification of spike rate‐based patterns or handwritten digits. Expand
Memristor networks for real-time neural activity analysis
A memristor-based reservoir computing (RC) system that can potentially analyze neural signals in real-time and can be directly driven by emulated neural spikes, where the Memristor state reflects temporal features in the neural spike train. Expand
Exploring the viability of stochastic computing
The results show that even for 3 bits, the SM consumes more energy to finish one multiplication than an SOP based regular binary multiplier (RM), and this energy consumption grows exponentially as the number of bits increases. Expand
Stochasticity Modeling in Memristors
The model proposed is generic and could be incorporated into variants of threshold-based memristor models in which apparent variations in the output hysteresis convey the switching threshold shift, and paves the way for novel approaches in the fields of neuromorphic engineering circuits design. Expand
High-speed true random number generation based on paired memristors for security electronics.
This work demonstrates a TRNG using intrinsic variation of memristors as a natural source of entropy that is otherwise undesirable in most applications and holds great promise for physically-implemented random number generation. Expand
A Survey of ReRAM-Based Architectures for Processing-In-Memory and Neural Networks
This paper presents a survey of techniques for designing ReRAM-based PIM and NN architectures and underscores their similarities and differences by classifying the techniques based on key parameters. Expand