Neuromorphic Computing Using Emerging Synaptic Devices: A Retrospective Summary and an Outlook

Park, Jaeyoung

doi:10.3390/electronics9091414

Cited by 43 publications

(23 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Electrical control of resistance states in two-terminal devices is currently a potentially disruptive trend in information technology. The nonvolatile resistance states with analog distribution of memristors enable hardware neuromorphic computation systems that challenge von Neumann architectures, mainly in terms of efficiency [20,21]. Note, that training a software neural network for natural language processing running on a conventional computer architecture can produce five times as much carbon dioxide as a car during its life time [22].…”

Section: Introductionmentioning

confidence: 99%

Reversible Barrier Switching of ZnO/RuO2 Schottky Diodes

et al. 2021

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Reversible Barrier Switching of ZnO/RuO2 Schottky Diodes

et al. 2021

View full text Add to dashboard Cite

show abstract

“…One of the major advantages of converting CNNs to spiking-CNNs is that it allows to use SNNs' sparse computing and perform similar computation with less energy. With this, SNNs can achieve ×38.7 times better energy efficiency than ANNs without any significant loss in accuracy [9].…”

Section: Why Current Models Are Not Whatmentioning

confidence: 97%

From Convolutions towards Spikes: The Environmental Metric that the Community currently Misses

Chharia¹,

Chauhan²,

Upadhyay³

et al. 2021

Preprint

View full text Add to dashboard Cite

Today, the AI community is obsessed with 'state-of-the-art' scores (80% papers in NeurIPS) as the major performance metrics, due to which an important parameter, i.e., the environmental metric, remains unreported. Computational capabilities were a limiting factor a decade ago; however, in foreseeable future circumstances, the challenge will be to develop environment-friendly and power-efficient algorithms. The human brain, which has been optimizing itself for almost a million years, consumes the same amount of power as a typical laptop. Therefore, developing nature-inspired algorithms is one solution to it. In this study, we show that currently used ANNs are not what we find in nature, and why, although having lower performance, spiking neural networks, which mirror the mammalian visual cortex, have attracted much interest. We further highlight the hardware gaps restricting the researchers from using spike-based computation for developing neuromorphic energy-efficient microchips on a large scale. Using neuromorphic processors instead of traditional GPUs might be more environment friendly and efficient. These processors will turn SNNs into an ideal solution for the problem. This paper presents in-depth attention highlighting the current gaps, the lack of comparative research, while proposing new research directions at the intersection of two fields-neuroscience and deep learning. Further, we define a new evaluation metric 'NATURE' for reporting the carbon footprint of AI models.

show abstract

“…, M, is the k-th total readout current. 0-conductance elements are realized with cells in RESET-state, and non-null conductance elements with cells in a SET-state programmed to have a specified conductance value [16]. Furthermore, PCM cells are characterized by a maximum conductance G MAX , which is reached in their full-SET state.…”

Section: Introductionmentioning

confidence: 99%

Characterization and Programming Algorithm of Phase Change Memory Cells for Analog In-Memory Computing

et al. 2021

View full text Add to dashboard Cite

In this paper, a thorough characterization of phase-change memory (PCM) cells was carried out, aimed at evaluating and optimizing their performance as enabling devices for analog in-memory computing (AIMC) applications. Exploiting the features of programming pulses, we discuss strategies to reduce undesired phenomena that afflict PCM cells and are particularly harmful in analog computations, such as low-frequency noise, time drift, and cell-to-cell variability of the conductance. The test vehicle is an embedded PCM (ePCM) provided by STMicroelectronics and designed in 90-nm smart power BCD technology with a Ge-rich Ge-Sb-Te (GST) alloy for automotive applications. On the basis of the results of the characterization of a large number of cells, we propose an iterative algorithm to allow multi-level cell conductance programming, and its performances for AIMC applications are discussed. Results for a group of 512 cells programmed with four different conductance levels are presented, showing an initial conductance spread under 6%, relative current noise less than 9% in most cases, and a relative conductance drift of 15% in the worst case after 14 h from the application of the programming sequence.

show abstract

Neuromorphic Computing Using Emerging Synaptic Devices: A Retrospective Summary and an Outlook

Cited by 43 publications

References 71 publications

Reversible Barrier Switching of ZnO/RuO2 Schottky Diodes

Reversible Barrier Switching of ZnO/RuO2 Schottky Diodes

From Convolutions towards Spikes: The Environmental Metric that the Community currently Misses

Characterization and Programming Algorithm of Phase Change Memory Cells for Analog In-Memory Computing

Contact Info

Product

Resources

About