Neuromorphic Vision Hybrid Rramcmos Architecture

• doi: 10.1109/TVLSI.2018.2829918
• title: Neuromorphic Vision Hybrid RRAM-CMOS Architecture
• publisher: IEEE
• isbn:
• issn: 1557-9999
• rank: 3101
• access_type: LOCKED
• content_type: Journals
• abstract: The development of a bioinspired image sensor, which can match the functionality of the vertebrate retina, has provided new opportunities for vision systems and processing through the realization of new architectures. Research in both retinal cellular systems and nanodriven memristive technology has made a challenging arena more accessible to emulate features of the retina that are closer to biological systems. This paper synthesizes the signal flow path of photocurrent throughout a retina in a scalable 180-nm CMOS technology, which initiates at a 128 × 128 active pixel image sensor, and converges to a 16 × 16 array, where each node emits a spike train synonymous to the function of the retinal ganglionic output cell. This signal can be sent to the visual cortex for image interpretation as part of an artificial vision system. Layers of memristive networks are used to emulate the functions of horizontal and amacrine cells in the retina, which average and converge signals. The resulting image matches biologically verified results within an error margin of 6% and exhibits the following features of the retina: lateral inhibition, asynchronous adaptation, and a low-dynamic-range integration active pixel sensor to perceive a high-dynamic-range scene.
• article_number: 8355733
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8355733
• html_url: https://ieeexplore.ieee.org/document/8355733/
• abstract_url: https://ieeexplore.ieee.org/document/8355733/
• publication_title: IEEE Transactions on Very Large Scale Integration (VLSI) Systems
• conference_location:
• conference_dates:
• publication_number: 92
• is_number: 8554317
• publication_year: 2018
• publication_date: Dec. 2018
• start_page: 2816
• end_page: 2829
• citing_paper_count: 44
• citing_patent_count: 0
• download_count: 1797
• insert_date: 20180507
• index_terms:
  • ieee_terms:
    • Computer architecture
    • Microprocessors
    • Retina
    • Photoreceptors
    • Ganglia
    • Memristors
    • Neuromorphics
  • author_terms:
    • Artificial retina
    • memristor
    • neuromorphic vision
    • sensor systems
    • silicon retina
  • dynamic_index_terms:
    • Neuromorphic Vision
    • Visual System
    • Retinal Cells
    • Ganglion Cells
    • Image Sensor
    • Camera Sensor
    • Flow Signal
    • Spike Trains
    • Lateral Inhibition
    • Surround Suppression
    • CMOS Technology
    • Amacrine Cells
    • Impedance
    • Resistivity
    • Hexagonal
    • Current Flow
    • Pupil Size
    • Pupil Dilation
    • Mydriasis
    • Transient Response
    • Total Resistance
    • Photoreceptor Cells
    • Photoreception
    • Cone Photoreceptors
    • Cone Cells
    • Bipolar Cells
    • Inner Plexiform Layer
    • Rod Outer Segment
    • Rod Cells
    • Low Light Levels
    • Bipolar Signals
    • Transient Cell
    • Outer Plexiform Layer
    • External Plexiform Layer
    • Piecewise Linear Function
    • Piecewise-linear Function
    • Retinal Network
    • Photocurrent Response
    • Photoreceptor Layer
• authors:
  • Author Name: Jason Kamran Eshraghian
    Affiliation: School of Electrical, Electronic and Computer Engineering, The University of Western Australia, Crawley, WA, Australia
    Author URL: https://ieeexplore.ieee.org/author/37085814242
    ID: 37085814242
    Order: 1
    Author Affiliations:
    • School of Electrical, Electronic and Computer Engineering, The University of Western Australia, Crawley, WA, Australia
  • Author Name: Kyoungrok Cho
    Affiliation: School of Electrical, Electronic and Computer Engineering, The University of Western Australia, Crawley, WA, Australia
    Author URL: https://ieeexplore.ieee.org/author/37279029100
    ID: 37279029100
    Order: 2
    Author Affiliations:
    • School of Electrical, Electronic and Computer Engineering, The University of Western Australia, Crawley, WA, Australia
  • Author Name: Ciyan Zheng
    Affiliation: School of Electrical, Electronic and Computer Engineering, The University of Western Australia, Crawley, WA, Australia
    Author URL: https://ieeexplore.ieee.org/author/37085579861
    ID: 37085579861
    Order: 3
    Author Affiliations:
    • School of Electrical, Electronic and Computer Engineering, The University of Western Australia, Crawley, WA, Australia
  • Author Name: Minho Nam
    Affiliation: College of Electrical and Computer Engineering, Chungbuk National University, Cheongju, South Korea
    Author URL: https://ieeexplore.ieee.org/author/37085566477
    ID: 37085566477
    Order: 4
    Author Affiliations:
    • College of Electrical and Computer Engineering, Chungbuk National University, Cheongju, South Korea
  • Author Name: Herbert Ho-Ching Iu
    Affiliation: School of Electrical, Electronic and Computer Engineering, The University of Western Australia, Crawley, WA, Australia
    Author URL: https://ieeexplore.ieee.org/author/37278163000
    ID: 37278163000
    Order: 5
    Author Affiliations:
    • School of Electrical, Electronic and Computer Engineering, The University of Western Australia, Crawley, WA, Australia
  • Author Name: Wen Lei
    Affiliation: School of Electrical, Electronic and Computer Engineering, The University of Western Australia, Crawley, WA, Australia
    Author URL: https://ieeexplore.ieee.org/author/37085447555
    ID: 37085447555
    Order: 6
    Author Affiliations:
    • School of Electrical, Electronic and Computer Engineering, The University of Western Australia, Crawley, WA, Australia
  • Author Name: Kamran Eshraghian
    Affiliation: School of Electrical, Electronic and Computer Engineering, The University of Western Australia, Crawley, WA, Australia
    Author URL: https://ieeexplore.ieee.org/author/37326970400
    ID: 37326970400
    Order: 7
    Author Affiliations:
    • School of Electrical, Electronic and Computer Engineering, The University of Western Australia, Crawley, WA, Australia

Image Sensor

• sensor_type: CMOS
• resolution: 128x128
• dynamic_range: High
• pixel_size: Not specified
• dark_current: Not specified

Optical Data

• focal_length: Not specified
• aperture: Not specified
• field_of_view: Not specified
• distortion: Not specified

Performance Metrics

• power_consumption: 7.8 μW for a single pathway from photoreceptor to ganglion cell; approx. 2 mW for the full network layout.
• noise: Stochastic nature of memristors leads to cycle-to-cycle variations.

Applications & Benefits

• cell_imaging: Application in artificial vision systems as part of retinal modeling.
• benefits: Low-power operation, adaptive response, mimics biological functions of the retina.

Supporting Organizations

• supported_by: National Research Foundation of Korea, DFAT Australia–Korea Foundation, iDataMap Corporation.

Manuscript Details

• publication_date: Dec. 2018

Relevancy Score

• score: 8
• missing_fields:
  • fill factor
  • quantum efficiency
  • readout speed
  • noise sources
  • microlenses
  • on-chip colour filters
  • global or rolling shutters
  • backside illumination

Processed JSON Filename

request_3f98ec47-f222-465e-82a1-84af965dfa85-neuromorphic_vision_hybrid_rramcmos_architecture.json