Implementation Study of an Analog Spiking Neural Network for Assisting Cardiac Delay Prediction in a Cardiac Resynchronization Therapy Device

Sun, Qing; Schwartz, François; Michel, J.; Hervé, Y.; Dalmolin, Renzo

doi:10.1109/tnn.2011.2125986

Cited by 19 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It integrates the STT stochastic behavior at the sub volume regime with a low critical current and high thermal stability. When the applied current is larger than the critical current, the switching duration changes randomly around the average duration (τ) calculated by ( 5) and (6). Figure 12(a) shows a schematic for stochastic switching of the MTJ, and demonstrates the switching probability as a function of the bias voltage and pulse width.…”

Section: Behavior Of Mtj As a Sigmoid Functionmentioning

confidence: 98%

“…The development in this area of study aims to find effective and biologically stable circuit designs for its hardware implementation. The hardware implementations presented in the literature use analog [6][7][8], digital [9,10] and also mixed signal circuits [11,12], but they rarely consider the probabilistic nature of communication in real biological systems. Hardware-based neural networks never accomplished enough development for largescale applications, because most of them were analog, making them costly and hardly reconfigurable.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Implementation of an efficient magnetic tunnel junction-based stochastic neural network with application to iris data classification

Nisar¹,

Khanday²,

Kaushik³

2020

Nanotechnology

View full text Add to dashboard Cite

Stochastic neuromorphic computation (SNC) has the potential to enable a low power, error tolerant and scalable computing platform in comparison to its deterministic counterparts. However, the hardware implementation of complementary metal oxide semiconductor (CMOS)-based stochastic circuits involves conversion blocks that cost more than the actual processing circuits. The realization of the activation function for SNCs also requires a complicated circuit that results in a significant amount of power dissipation and area overhead. The inherent probabilistic switching behavior of nanomagnets provides an advantage to overcome these complexity issues for the realization of low power and area efficient SNC systems. This paper presents magnetic tunnel junction (MTJ)-based stochastic computing methodology for the implementation of a neural network. The stochastic switching behavior of the MTJ has been exploited to design a binary to stochastic converter to mitigate the complexity of the CMOS-based design. The paper also presents the technique for realizing stochastic sigmoid activation function using an MTJ. Such circuits are simpler than existing ones and use considerably less power. An image classification system employing the proposed circuits has been implemented to verify the effectiveness of the technique. The MTJ-based SNC system shows area and energy reduction by a factor of 13.5 and 2.5, respectively, while the prediction accuracy is 86.66%. Furthermore, this paper investigates how crucial parameters, such as stochastic bitstream length, number of hidden layers and number of nodes in a hidden layer, need to be set precisely to realize an efficient MTJ-based stochastic neural network (SNN). The proposed methodology can prove a promising alternative for highly efficient digital stochastic computing applications.

show abstract

Section: Behavior Of Mtj As a Sigmoid Functionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Implementation of an efficient magnetic tunnel junction-based stochastic neural network with application to iris data classification

Nisar¹,

Khanday²,

Kaushik³

2020

Nanotechnology

View full text Add to dashboard Cite

show abstract

“…Neuromorphic hardware uses dedicated processing units to implement neuronal connections and firing behavior directly on a physical chip, rather than simulating them mathematically. Analog neuromorphic hardware has been shown to be more power efficient than traditional digital computation hardware, and does not suffer from the same bottleneck as Von Neuman computing [35][36][37][38][39][40][41][42]. Some designs take advantage of sub-threshold operation for ultra-low power neurons [43,44].…”

Section: Neuromorphic Hardwarementioning

confidence: 99%

Towards Low-Power Machine Learning Architectures Inspired by Brain Neuromodulatory Signalling

Barton

Rogers

et al. 2022

JLPEA

View full text Add to dashboard Cite

We present a transfer learning method inspired by modulatory neurotransmitter mechanisms in biological brains and explore applications for neuromorphic hardware. In this method, the pre-trained weights of an artificial neural network are held constant and a new, similar task is learned by manipulating the firing sensitivity of each neuron via a supplemental bias input. We refer to this as neuromodulatory tuning (NT). We demonstrate empirically that neuromodulatory tuning produces results comparable with traditional fine-tuning (TFT) methods in the domain of image recognition in both feed-forward deep learning and spiking neural network architectures. In our tests, NT reduced the number of parameters to be trained by four orders of magnitude as compared with traditional fine-tuning methods. We further demonstrate that neuromodulatory tuning can be implemented in analog hardware as a current source with a variable supply voltage. Our analog neuron design implements the leaky integrate-and-fire model with three bi-directional binary-scaled current sources comprising the synapse. Signals approximating modulatory neurotransmitter mechanisms are applied via adjustable power domains associated with each synapse. We validate the feasibility of the circuit design using high-fidelity simulation tools and propose an efficient implementation of neuromodulatory tuning using integrated analog circuits that consume significantly less power than digital hardware (GPU/CPU).

show abstract

“…Although most SNN circuits learn the patterns of the firing rate, this type of learning suffers from a tradeoff between accuracy and speed. Spiking neural networks have wide applications in data modeling [12], delay prediction [13], classification problems [14], pattern classification [15] and in many more data analysis crisis [16].…”

Section: Spiking Neural Networkmentioning

confidence: 99%

Hardware Implementation of E-Nose in Arm-7 Board through Neural Networks

Moorthilingam¹,

Bagavathi²

2013

IJCA

View full text Add to dashboard Cite

In the fast pacing world, it has becomes essential to so many gadgets that humans should take their effort to understand and use them. One such device is an Electronic Nose (E-Nose). There is still a long voyage ahead before artificial Electronic nose is developed completely. This work is a commendation for refining and enhancing current detection capabilities. Gas sensors used in electronic noses are based on broad selectivity profiles, mimicking the responses of olfactory receptors in the biological olfactory system. To identify a particular odour, the design is should be able to detect the odour which sufficient confidence and hence saving the humans for hazardous situation and false alarms.

show abstract

Implementation Study of an Analog Spiking Neural Network for Assisting Cardiac Delay Prediction in a Cardiac Resynchronization Therapy Device

Cited by 19 publications

References 16 publications

Implementation of an efficient magnetic tunnel junction-based stochastic neural network with application to iris data classification

Implementation of an efficient magnetic tunnel junction-based stochastic neural network with application to iris data classification

Towards Low-Power Machine Learning Architectures Inspired by Brain Neuromodulatory Signalling

Hardware Implementation of E-Nose in Arm-7 Board through Neural Networks

Contact Info

Product

Resources

About