Nonlinear retinal response modeling for future neuromorphic instrumentation

Eshraghian, Jason K.; Baek, Seungbum; Levi, Timothée; Kohno, Takashi; Al-Sarawi, Said F.; Leong, Philip H. W.; Cho, Kyoung-Rok; Abbott, Derek; Kavehei, Omid

doi:10.1109/mim.2020.8979519

Cited by 15 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the smallest measured time step of dt = 10 −6 s in the dual path (i.e., rod and cone cells are connected via electrical synapses) the method implemented is over 50% times faster than the benchmark. Similar speed improvements were noted in the C++ implementation [18].…”

Section: Resultssupporting

confidence: 73%

Prosthesis Control Using Spike Rate Coding in the Retina Photoreceptor Cells

Arrow

Baek

et al. 2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

Self Cite

View full text Add to dashboard Cite

Volitional control of prostheses is most commonly achieved by myoelectric signalling. The electromyograph (EMG) is detected and processed by a controller, that decodes and relates the signal to the corresponding position of the prosthetic. Myoelectric signalling is limited in users by two factors: lack of nerve endings corresponding to the position of the amputation, and neurological damage resulting in poor signal control. Improved prosthesis control has been demonstrated by the addition of feedback sensors based on computer vision and inertial measurement units. Computer vision requires a significant level of processing, resulting in a high latency and high power usage. In this paper, we propose a means of overcoming this limitation by use of in-vivo retinal signalling to complement EMG for improved control. This is demonstrated using a real-time conductancebased simulator as the sole method of control for an upper-limb prosthesis. Input image streams are received by a camera and used to activate the combined rod and cone photoreceptor cell responses. This in turn generates a spike train which is counted and averaged over time, and passed to an Arduino-based control system which modulates the behavior of the prosthesis. We seek to use this system to lower the experimental barriers of in-vivo ganglion electrical signalling by presenting a way to use retina emulation. A link to the simulator is provided.

show abstract

Section: Resultssupporting

confidence: 73%

Prosthesis Control Using Spike Rate Coding in the Retina Photoreceptor Cells

Arrow

Baek

et al. 2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Neurons can respond to sensory stimuli over an enormous dynamic range. In the retina, neurons can detect individual photons to an influx of millions of photons [96], [97], [98], [99], [100]. To handle such widely varying stimuli, sensory transduction systems likely compress stimulus intensity with a logarithmic dependency.…”

Section: Input Data To An Snn May Be Converted Into a Firing Rate A F...mentioning

confidence: 99%

Training Spiking Neural Networks Using Lessons From Deep Learning

Eshraghian,

Ward,

Neftci

et al. 2023

Proc. IEEE

Self Cite

210

View full text Add to dashboard Cite

show abstract

“…UtilizationUse of event-based cameras for tactile sensing applications provides a much higher sampling rate as well as significant reduction of power consumption. Neuromorphic vision sensors have become significantly popular recently and introduce a paradigm in computer vision applications for instrumentation and measurements [29,30]. The Dynamic Vision Sensor (DVS) that is used in this paper is one of the well-known neuromorphic cameras.…”

Section: Neuromorphic Vision-based Tactile Sensormentioning

confidence: 99%

Dynamic-Vision-Based Force Measurements Using Convolutional Recurrent Neural Networks

Naeini

Makris

Gan

et al. 2020

Sensors

View full text Add to dashboard Cite

In this paper, a novel dynamic Vision-Based Measurement method is proposed to measure contact force independent of the object sizes. A neuromorphic camera (Dynamic Vision Sensor) is utilizused to observe intensity changes within the silicone membrane where the object is in contact. Three deep Long Short-Term Memory neural networks combined with convolutional layers are developed and implemented to estimate the contact force from intensity changes over time. Thirty-five experiments are conducted using three objects with different sizes to validate the proposed approach. We demonstrate that the networks with memory gates are robust against variable contact sizes as the networks learn object sizes in the early stage of a grasp. Moreover, spatial and temporal features enable the sensor to estimate the contact force every 10 ms accurately. The results are promising with Mean Squared Error of less than 0.1 N for grasping and holding contact force using leave-one-out cross-validation method.

show abstract

Nonlinear retinal response modeling for future neuromorphic instrumentation

Cited by 15 publications

References 16 publications

Prosthesis Control Using Spike Rate Coding in the Retina Photoreceptor Cells

Prosthesis Control Using Spike Rate Coding in the Retina Photoreceptor Cells

Training Spiking Neural Networks Using Lessons From Deep Learning

Dynamic-Vision-Based Force Measurements Using Convolutional Recurrent Neural Networks

Contact Info

Product

Resources

About