scholarly journals A cyclical deep learning based framework for simultaneous inverse and forward design of nanophotonic metasurfaces

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Abhishek Mall ◽  
Abhijeet Patil ◽  
Amit Sethi ◽  
Anshuman Kumar
Keyword(s):  
Genetic Algorithm ◽  
Deep Learning ◽  
Design Space ◽  
Optical Response ◽  
Inverse Design ◽  
Electromagnetic Response ◽  
Design And Optimization ◽  
Half Wave ◽  
Wide Range ◽  
Optimization Mechanism

Abstract The conventional approach to nanophotonic metasurface design and optimization for a targeted electromagnetic response involves exploring large geometry and material spaces. This is a highly iterative process based on trial and error, which is computationally costly and time consuming. Moreover, the non-uniqueness of structural designs and high non-linearity between electromagnetic response and design makes this problem challenging. To model this unintuitive relationship between electromagnetic response and metasurface structural design as a probability distribution in the design space, we introduce a framework for inverse design of nanophotonic metasurfaces based on cyclical deep learning (DL). The proposed framework performs inverse design and optimization mechanism for the generation of meta-atoms and meta-molecules as metasurface units based on DL models and genetic algorithm. The framework includes consecutive DL models that emulate both numerical electromagnetic simulation and iterative processes of optimization, and generate optimized structural designs while simultaneously performing forward and inverse design tasks. A selection and evaluation of generated structural designs is performed by the genetic algorithm to construct a desired optical response and design space that mimics real world responses. Importantly, our cyclical generation framework also explores the space of new metasurface topologies. As an example application of the utility of our proposed architecture, we demonstrate the inverse design of gap-plasmon based half-wave plate metasurface for user-defined optical response. Our proposed technique can be easily generalized for designing nanophtonic metasurfaces for a wide range of targeted optical response.

scholarly journals Implementation of integrated design space exploration of scheduling, allocation and binding in high level synthesis using multi structure genetic algorithm

2021 ◽  
Author(s):  
Michael Gebremariam
Keyword(s):  
Genetic Algorithm ◽  
Design Space Exploration ◽  
Design Space ◽  
Space Exploration ◽  
Integrated Design ◽  
High Level Synthesis ◽  
C Language ◽  
Low Level ◽  
Wide Range ◽  
High Level

The objective of this project is to develop a software tool which assists in comparison of a work known as "M-GenESys: Multi Structure Genetic Algorithm based Design Space Exploration System for Integrated Scheduling, Allocation and Binding in High Level Synthesis" with another well established GA approach known as "A Generic Algorithm for the Design Space Exploration of Data paths During High-Level Synthesis". Two sets of software are developed based on both approaches using Microsoft Visual 2005 C# language. The C# language is an object-oriented language that is aimed at enabling programmers to quickly develop a wide range of applications on the Microsoft .NET platform. The goal of C# and the .NET platform is to shorten development time by freeing the developer from worrying about several low level plumbing issues such as memory equipment, type safety issues, building low level libraries, array bound checking, etc., thus allowing developers to actually spend their time and energy working on the application and business logic.

scholarly journals Acoustic Structure Inverse Design and Optimization Using Deep Learning

2021 ◽  
Author(s):  
Xuecong Sun ◽  
Han Jia ◽  
Yuzhen Yang ◽  
Han Zhao ◽  
Yafeng Bi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Acoustic Waves ◽  
Design Method ◽  
Helmholtz Resonator ◽  
Structure Design ◽  
Acoustic Structure ◽  
Design And Optimization ◽  
Wide Range ◽  
Potential Applications ◽  
Coupling Parameters

Abstract From ancient to modern times, acoustic structures have been used to control the propagation of acoustic waves. However, the design of acoustic structures has remained a time-consuming and computational resource-consuming iterative process. In recent years, deep learning has attracted unprecedented attention for its ability to tackle hard problems with large datasets, achieving state-of-the-art results in various tasks. In this work, an acoustic structure design method is proposed based on deep learning. Taking the design of multiorder Helmholtz resonator as an example, we experimentally demonstrate the effectiveness of the proposed method. Our method is not only able to give a very accurate prediction of the geometry of acoustic structures with multiple strong-coupling parameters, but also capable of improving the performance of evolutionary approaches in optimization for a desired property. Compared with the conventional numerical methods, our method is more efficient, universal and automatic, and it has a wide range of potential applications, such as speech enhancement, sound absorption and insulation.

Multiplexing the aperture of a metasurface: inverse design via deep-learning-forward genetic algorithm

2020 ◽  
Vol 53 (45) ◽  
pp. 455002
Author(s):  
Ruichao Zhu ◽  
Tianshuo Qiu ◽  
Jiafu Wang ◽  
Sai Sui ◽  
Yongfeng Li ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Deep Learning ◽  
Inverse Design ◽  
Learning Forward

scholarly journals Multiplexed supercell metasurface design and optimization with tandem residual networks

Nanophotonics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 1133-1143
Author(s):  
Christopher Yeung ◽  
Ju-Ming Tsai ◽  
Brian King ◽  
Benjamin Pham ◽  
David Ho ◽  
...  
Keyword(s):  
Inverse Design ◽  
Training Dataset ◽  
Structure Property ◽  
Broadband Absorption ◽  
Design And Optimization ◽  
Optical Responses ◽  
Wide Range ◽  
Metal Insulator Metal ◽  
Material Choice ◽  
Nanophotonic Structures

Abstract Complex nanophotonic structures hold the potential to deliver exquisitely tailored optical responses for a range of applications. Metal–insulator–metal (MIM) metasurfaces arranged in supercells, for instance, can be tailored by geometry and material choice to exhibit a variety of absorption properties and resonant wavelengths. With this flexibility, however, comes a vast space of design possibilities that classical design paradigms struggle to effectively navigate. To overcome this challenge, here, we demonstrate a tandem residual network approach to efficiently generate multiplexed supercells through inverse design. By using a training dataset with several thousand full-wave electromagnetic simulations in a design space of over three trillion possible designs, the deep learning model can accurately generate a wide range of complex supercell designs given a spectral target. Beyond inverse design, the presented approach can also be used to explore the structure–property relationships of broadband absorption and emission in such supercell configurations. Thus, this study demonstrates the feasibility of high-dimensional supercell inverse design with deep neural networks, which is applicable to complex nanophotonic structures composed of multiple subunit elements that exhibit coupling.

scholarly journals GPU implementation of restricted Boltzmann machines with application to view classification in sports videos

2021 ◽  
Author(s):  
Andreas Fred Bernitzke
Keyword(s):  
Genetic Algorithm ◽  
Design Space Exploration ◽  
Design Space ◽  
Space Exploration ◽  
High Level Synthesis ◽  
Restricted Boltzmann Machines ◽  
C Language ◽  
Low Level ◽  
Wide Range ◽  
High Level

The objective of this project is to develop a software tool which assists in comparison of a work known as "M-GenESys: Multi Structure Genetic Algorithm based Design Space Exploration System for Integrated Scheduling, Allocation and Binding in High Level Synthesis" with another well established GA approach known as "A Genetic Algorithm for the Design Space Exploration of Data paths During High-Level Synthesis". Two sets of Software are developed based on both approaches using Microsoft visual 2005,C# language. The C# language is an object-oriented language that is aimed at enabling programmers to quickly develop a wide range of applications on the Microsoft .NET platform. The goal of C# and the .NET platform is to shorten development time by freeing the developer from worrying about several low level plumbing issues such as memory management, type safety issues, building low level libraries, array bounds checking, etc. thus allowing developers to actually spend their time and energy working on the application and business logic.

scholarly journals Implementation of integrated design space exploration of scheduling, allocation and binding in high level synthesis using multi structure genetic algorithm

2021 ◽  
Author(s):  
Michael Gebremariam
Keyword(s):  
Genetic Algorithm ◽  
Design Space Exploration ◽  
Design Space ◽  
Space Exploration ◽  
Integrated Design ◽  
High Level Synthesis ◽  
C Language ◽  
Low Level ◽  
Wide Range ◽  
High Level

The objective of this project is to develop a software tool which assists in comparison of a work known as "M-GenESys: Multi Structure Genetic Algorithm based Design Space Exploration System for Integrated Scheduling, Allocation and Binding in High Level Synthesis" with another well established GA approach known as "A Generic Algorithm for the Design Space Exploration of Data paths During High-Level Synthesis". Two sets of software are developed based on both approaches using Microsoft Visual 2005 C# language. The C# language is an object-oriented language that is aimed at enabling programmers to quickly develop a wide range of applications on the Microsoft .NET platform. The goal of C# and the .NET platform is to shorten development time by freeing the developer from worrying about several low level plumbing issues such as memory equipment, type safety issues, building low level libraries, array bound checking, etc., thus allowing developers to actually spend their time and energy working on the application and business logic.

scholarly journals GPU implementation of restricted Boltzmann machines with application to view classification in sports videos

2021 ◽  
Author(s):  
Andreas Fred Bernitzke
Keyword(s):  
Genetic Algorithm ◽  
Design Space Exploration ◽  
Design Space ◽  
Space Exploration ◽  
High Level Synthesis ◽  
Restricted Boltzmann Machines ◽  
C Language ◽  
Low Level ◽  
Wide Range ◽  
High Level

The objective of this project is to develop a software tool which assists in comparison of a work known as "M-GenESys: Multi Structure Genetic Algorithm based Design Space Exploration System for Integrated Scheduling, Allocation and Binding in High Level Synthesis" with another well established GA approach known as "A Genetic Algorithm for the Design Space Exploration of Data paths During High-Level Synthesis". Two sets of Software are developed based on both approaches using Microsoft visual 2005,C# language. The C# language is an object-oriented language that is aimed at enabling programmers to quickly develop a wide range of applications on the Microsoft .NET platform. The goal of C# and the .NET platform is to shorten development time by freeing the developer from worrying about several low level plumbing issues such as memory management, type safety issues, building low level libraries, array bounds checking, etc. thus allowing developers to actually spend their time and energy working on the application and business logic.

Control of Thin Film Growth in Chemical Vapor Deposition Manufacturing Systems: A Feasibility Study

2002 ◽  
Vol 124 (3) ◽  
pp. 715-724 ◽  
Author(s):  
Wilson K. S. Chiu ◽  
Yogesh Jaluria ◽  
Nick G. Glumac
Keyword(s):  
Thin Film ◽  
Chemical Vapor Deposition ◽  
Vapor Deposition ◽  
Design Space ◽  
Chemical Vapor ◽  
Film Deposition ◽  
Operating Conditions ◽  
Design And Optimization ◽  
Wide Range ◽  
Computer Aided

A study is carried out to design and optimize Chemical Vapor Deposition (CVD) systems for material fabrication. Design and optimization of the CVD process is necessary to satisfying strong global demand and ever increasing quality requirements for thin film production. Advantages of computer aided optimization include high design turnaround time, flexibility to explore a larger design space and the development and adaptation of automation techniques for design and optimization. A CVD reactor consisting of a vertical impinging jet at atmospheric pressure, for growing titanium nitride films, is studied for thin film deposition. Numerical modeling and simulation are used to determine the rate of deposition and film uniformity over a wide range of design variables and operating conditions. These results are used for system design and optimization. The optimization procedure employs an objective function characterizing film quality, productivity and operational costs based on reactor gas flow rate, susceptor temperature and precursor concentration. Parameter space mappings are used to determine the design space, while a minimization algorithm, such as the steepest descent method, is used to determine optimal operating conditions for the system. The main features of computer aided design and optimization, using these techniques, are discussed in detail.

scholarly journals Computational Design of Modular Robots Based on Genetic Algorithm and Reinforcement Learning

Symmetry ◽  
2021 ◽  
Vol 13 (3) ◽  
pp. 471
Author(s):  
Jai Hoon Park ◽  
Kang Hoon Lee
Keyword(s):  
Genetic Algorithm ◽  
Reinforcement Learning ◽  
Design Space ◽  
Learning Algorithm ◽  
Computational Design ◽  
Computational Method ◽  
Learning Ability ◽  
Modular Robots ◽  
Control Mechanisms ◽  
Candidate Structure

Designing novel robots that can cope with a specific task is a challenging problem because of the enormous design space that involves both morphological structures and control mechanisms. To this end, we present a computational method for automating the design of modular robots. Our method employs a genetic algorithm to evolve robotic structures as an outer optimization, and it applies a reinforcement learning algorithm to each candidate structure to train its behavior and evaluate its potential learning ability as an inner optimization. The size of the design space is reduced significantly by evolving only the robotic structure and by performing behavioral optimization using a separate training algorithm compared to that when both the structure and behavior are evolved simultaneously. Mutual dependence between evolution and learning is achieved by regarding the mean cumulative rewards of a candidate structure in the reinforcement learning as its fitness in the genetic algorithm. Therefore, our method searches for prospective robotic structures that can potentially lead to near-optimal behaviors if trained sufficiently. We demonstrate the usefulness of our method through several effective design results that were automatically generated in the process of experimenting with actual modular robotics kit.

scholarly journals A Generalization Performance Study Using Deep Learning Networks in Embedded Systems

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1031
Author(s):  
Joseba Gorospe ◽  
Rubén Mulero ◽  
Olatz Arbelaitz ◽  
Javier Muguerza ◽  
Miguel Ángel Antón
Keyword(s):  
Deep Learning ◽  
Embedded Systems ◽  
Embedded System ◽  
General Purpose ◽  
Learning Networks ◽  
Performance Study ◽  
Learning Techniques ◽  
Wide Range ◽  
Learning Architectures

Deep learning techniques are being increasingly used in the scientific community as a consequence of the high computational capacity of current systems and the increase in the amount of data available as a result of the digitalisation of society in general and the industrial world in particular. In addition, the immersion of the field of edge computing, which focuses on integrating artificial intelligence as close as possible to the client, makes it possible to implement systems that act in real time without the need to transfer all of the data to centralised servers. The combination of these two concepts can lead to systems with the capacity to make correct decisions and act based on them immediately and in situ. Despite this, the low capacity of embedded systems greatly hinders this integration, so the possibility of being able to integrate them into a wide range of micro-controllers can be a great advantage. This paper contributes with the generation of an environment based on Mbed OS and TensorFlow Lite to be embedded in any general purpose embedded system, allowing the introduction of deep learning architectures. The experiments herein prove that the proposed system is competitive if compared to other commercial systems.

Sign in / Sign up

Export Citation Format

Share Document