Hardware Design for Machine Learning

Jawandhiya, Pooja

doi:10.5121/ijaia.2018.9105

Cited by 20 publications

(17 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tensor or vector data that resides in memory is retrieved and sent to the processor, which performs MAC operations (a ← a + (w × x)) and some other nonlinear functions (encompassed in f {x}) before the result is sent back to memory and stored. Although MACs constitute the majority of operations in AI, in practice, most of the energy is lost data movement [14], [15]. Activations must be shuttled to and from various memory caches and buffers to the matrix multiplication units and back.…”

Section: Multiply-accumulate Operationsmentioning

confidence: 99%

“…switching charge for gain cascadability (15) where η = η L η wg η d is laser efficiency, photonic link efficiency, and photodetector efficiency, respectively; V s is the inverse slope of the modulator's voltage-to-transmission curve T (V ); and C mod , C PD are the joint capacitances of the photodetetor and modulator. In a typical foundry-model where V s (C mod + C PD ) ∼ 70 fC and η ∼ .06 (which includes the passive losses through the weight banks, which can be made quite small [116]), even with ρ = N in fixed point systems, we arrive at a floor of approximately E MAC ≥ 30 fJ/MAC.…”

Section: Neural Network Hardware Comparisonmentioning

confidence: 99%

See 1 more Smart Citation

Photonic Multiply-Accumulate Operations for Neural Networks

Nahmias

Lima

Tait

et al. 2020

IEEE J. Select. Topics Quantum Electron.

237

133

View full text Add to dashboard Cite

It has long been known that photonic communication can alleviate the data movement bottlenecks that plague conventional microelectronic processors. More recently, there has also been interest in its capabilities to implement low precision linear operations, such as matrix multiplications, fast and efficiently. We characterize the performance of photonic and electronic hardware underlying neural network models using multiply-accumulate operations. First, we investigate the limits of analog electronic crossbar arrays and on-chip photonic linear computing systems. Photonic processors are shown to have advantages in the limit of large processor sizes (>100 µm), large vector sizes (N > 500), and low noise precision (≤4 bits). We discuss several proposed tunable photonic MAC systems, and provide a concrete comparison between deep learning and photonic hardware using several empiricallyvalidated device and system models. We show significant potential improvements over digital electronics in energy (>10 2), speed (>10 3), and compute density (>10 2). Index Terms-Artificial intelligence, neural networks, analog computers, analog processing circuits, optical computing. I. INTRODUCTION P HOTONICS has been well studied for its role in communication systems. Fiber optic links currently form the backbone of the world's telecommunications infrastructure, vastly overshadowing the best electronic communication standards in information capacity. Light signals have many advantageous properties for the transfer of information. For one, a photonic waveguide, with diameters ranging from those in fiber (∼80 μm) to those fabricated on-chip (∼500 nm), can carry information at enormous bandwidth densities-i.e., terabits per secondwith an energy efficiency that scales nearly independent of distance. This density is possible thanks to signal parallelization in photonic waveguides, in which hundreds of high speed, multiplexed channels can be independently modulated and detected. Photonic channels also experience less distortion, jitter,

show abstract

Section: Multiply-accumulate Operationsmentioning

confidence: 99%

Section: Neural Network Hardware Comparisonmentioning

confidence: 99%

Photonic Multiply-Accumulate Operations for Neural Networks

Nahmias

Lima

Tait

et al. 2020

IEEE J. Select. Topics Quantum Electron.

237

133

View full text Add to dashboard Cite

show abstract

“…f Pulses = 1 T Pulses (12) where τ denotes the delay, and the analog cutoff frequency f 0 is given by…”

Section: Sctn-based Phase Shiftingmentioning

confidence: 99%

“…The close resemblance between SN and a biological neuron justifies the evaluation of the substitution of the classical NN model with the SN model. The implementation of SN can be carried out using both analog and digital circuits [ 12 ]. Various kinds of SNN-based models and neuromorphic circuits have been recently proposed to support the processing of vast streams of information in real-time [ 13 , 14 ].…”

Section: Introductionmentioning

confidence: 99%

Using a Low-Power Spiking Continuous Time Neuron (SCTN) for Sound Signal Processing

Bensimon

Greenberg

Haiut³

2021

Sensors

View full text Add to dashboard Cite

This work presents a new approach based on a spiking neural network for sound preprocessing and classification. The proposed approach is biologically inspired by the biological neuron’s characteristic using spiking neurons, and Spike-Timing-Dependent Plasticity (STDP)-based learning rule. We propose a biologically plausible sound classification framework that uses a Spiking Neural Network (SNN) for detecting the embedded frequencies contained within an acoustic signal. This work also demonstrates an efficient hardware implementation of the SNN network based on the low-power Spike Continuous Time Neuron (SCTN). The proposed sound classification framework suggests direct Pulse Density Modulation (PDM) interfacing of the acoustic sensor with the SCTN-based network avoiding the usage of costly digital-to-analog conversions. This paper presents a new connectivity approach applied to Spiking Neuron (SN)-based neural networks. We suggest considering the SCTN neuron as a basic building block in the design of programmable analog electronics circuits. Usually, a neuron is used as a repeated modular element in any neural network structure, and the connectivity between the neurons located at different layers is well defined. Thus, generating a modular Neural Network structure composed of several layers with full or partial connectivity. The proposed approach suggests controlling the behavior of the spiking neurons, and applying smart connectivity to enable the design of simple analog circuits based on SNN. Unlike existing NN-based solutions for which the preprocessing phase is carried out using analog circuits and analog-to-digital conversion, we suggest integrating the preprocessing phase into the network. This approach allows referring to the basic SCTN as an analog module enabling the design of simple analog circuits based on SNN with unique inter-connections between the neurons. The efficiency of the proposed approach is demonstrated by implementing SCTN-based resonators for sound feature extraction and classification. The proposed SCTN-based sound classification approach demonstrates a classification accuracy of 98.73% using the Real-World Computing Partnership (RWCP) database.

show abstract

“…The proposed procedure can be adopted in different applications involving healthcare [23] and for mapping industrial processes [24]. The ANN could be implemented by means of a tailored architecture [25].…”

Section: Second Test Oriented On Predictive Maintenancementioning

confidence: 99%

ESB Platform Integrating Knime Data Mining Tool Oriented on Industry 4.0 Based on Artificial Neural Network Predictive Maintenance

Massaro¹,

Maritati²,

Galiano³

et al. 2018

IJAIA

View full text Add to dashboard Cite

In this paper are discussed some results related to an industrial project oriented on the integration of data mining tools into Enterprise Service Bus (ESB) platform. WSO2 ESB has been implemented for data transaction and to interface a client web service connected to a KNIME workflow behaving as a flexible data mining engine. In order to validate the implementation two test have been performed: the first one is related to the data management of two relational database management system (RDBMS) merged into one database whose data have been processed by KNIME dashboard statistical tool thus proving the data transfer of the prototype system; the second one is related to a simulation of two sensor data belonging to two distinct production lines connected to the same ESB. Specifically in the second example has been developed a practical case by processing by a Multilayered Perceptron (MLP) neural networks the temperatures of two milk production lines and by providing information about predictive maintenance. The platform prototype system is suitable for data automatism and Internet of Thing (IoT) related to Industry 4.0, and it is suitable for innovative hybrid system embedding different hardware and software technologies integrated with ESB, data mining engine and client web-services.

show abstract

Hardware Design for Machine Learning

Abstract: ABSTRACT

Cited by 20 publications

References 43 publications

Photonic Multiply-Accumulate Operations for Neural Networks

Photonic Multiply-Accumulate Operations for Neural Networks

Using a Low-Power Spiking Continuous Time Neuron (SCTN) for Sound Signal Processing

ESB Platform Integrating Knime Data Mining Tool Oriented on Industry 4.0 Based on Artificial Neural Network Predictive Maintenance

Contact Info

Product

Resources

About