Acoustic analog computing based on a reflective metasurface with decoupled modulation of phase and amplitude

Analog computing from recycling principle for next circular economy scenario has been studied with an iron oxide-coupled graphite/Fe–Si steel structure which was built using recycled waste materials, such as lead pencil and 3% Si steel (Fe–Si steel) foils. Proximity phenomena, such as disordered structure of iron oxide and magnetostriction-induced conduction, inside graphite lattice resulted in functional properties to advance analog architectures. Thermal oxidation was the synthesis route to produce iron oxide as coating film on Fe–Si steel foil, whose structure properties were validated by Raman spectroscopy where phase formation of hematite, α-Fe2O3, resulted as iron oxide thin-film. Three graphite layers with different compositions were also analyzed by Raman spectroscopy and used for studying electrical conduction in Fe–Si steel/α-Fe2O3/graphite structure from current–voltage plots at room temperature.

Download Full-text

Acoustic Analog Signal Processing for 20 MeV - 200 MeV Proton Sound Detectors

IEEE Transactions on Radiation and Plasma Medical Sciences ◽

10.1109/trpms.2021.3073803 ◽

2021 ◽

pp. 1-1

Author(s):

Marcello De Matteis ◽

Andrea Baschirotto ◽

Elia Vallicelli

Keyword(s):

Signal Processing ◽

Analog Signal Processing ◽

Analog Signal ◽

Acoustic Analog

Download Full-text

A Neural Network Decomposition Algorithm for Mapping on Crossbar-Based Computing Systems

Electronics ◽

10.3390/electronics9091526 ◽

2020 ◽

Vol 9 (9) ◽

pp. 1526 ◽

Cited By ~ 1

Author(s):

Choongmin Kim ◽

Jacob A. Abraham ◽

Woochul Kang ◽

Jaeyong Chung

Keyword(s):

Neural Network ◽

Neural Networks ◽

Predictive Performance ◽

Fixed Number ◽

Decomposition Algorithm ◽

Computing Systems ◽

Network Decomposition ◽

Von Neumann ◽

Analog Computing ◽

The Neural Network

Crossbar-based neuromorphic computing to accelerate neural networks is a popular alternative to conventional von Neumann computing systems. It is also referred as processing-in-memory and in-situ analog computing. The crossbars have a fixed number of synapses per neuron and it is necessary to decompose neurons to map networks onto the crossbars. This paper proposes the k-spare decomposition algorithm that can trade off the predictive performance against the neuron usage during the mapping. The proposed algorithm performs a two-level hierarchical decomposition. In the first global decomposition, it decomposes the neural network such that each crossbar has k spare neurons. These neurons are used to improve the accuracy of the partially mapped network in the subsequent local decomposition. Our experimental results using modern convolutional neural networks show that the proposed method can improve the accuracy substantially within about 10% extra neurons.

Download Full-text