Zhaocheng Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhaocheng Liu has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Wenshan Cai
Georgia Institute of Technology
7 shared publications Dayu Zhu
School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332, United States
3 shared publicationsLakshmi Raju
School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332, United States
3 shared publications- Kexin Yang
School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, USA
2 shared publications - Linda Milor
Georgia Institute of Technology, Atlanta, GA, USA
2 shared publications - Rui Zhang
Cadence Design Systems, Inc., San Jose, CA, USA
2 shared publications
Latest Publications
- 20 July 2023
- Published by Optica Publishing Group in Optics Express
- Vol. 31 (16) , 26054-26068
Metalens enhanced ray optics: an end-to-end wave-ray co-optimization framework
We present a fully differentiable framework for seamlessly integrating wave optical components with geometrical lenses, offering an approach to enhance the performance of large-scale end-to-end optical systems. In this study, we focus on the integration of a metalens, a geometrical lens, and image data. Through the use of gradient-based optimization techniques, we demonstrate the design of nonparaxial imaging systems and the correction of aberrations inherent in geometrical optics. Our framework enables efficient and effective optimization of the entire optical system, leading to improved overall performance. & COPY; 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement
- 20 July 2023
- Published by Optica Publishing Group in Optics Express
- Vol. 31 (16) , 26054-26068
Metalens enhanced ray optics: an end-to-end wave-ray co-optimization framework
We present a fully differentiable framework for seamlessly integrating wave optical components with geometrical lenses, offering an approach to enhance the performance of large-scale end-to-end optical systems. In this study, we focus on the integration of a metalens, a geometrical lens, and image data. Through the use of gradient-based optimization techniques, we demonstrate the design of nonparaxial imaging systems and the correction of aberrations inherent in geometrical optics. Our framework enables efficient and effective optimization of the entire optical system, leading to improved overall performance. & COPY; 2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement
- 14 February 2022
- Published by American Chemical Society (ACS) in ACS Nano
- Vol. 16 (3) , 3926-3933
Maximized Frequency Doubling through the Inverse Design of Nonlinear Metamaterials
The conventional process for developing an optimal design for nonlinear optical responses is based on a trial-and-error approach that is largely inefficient and does not necessarily lead to an ideal result. Deep learning can automate this process and widen the realm of nonlinear geometries and devices. This research illustrates a deep learning framework used to create an optimal plasmonic design for a nonlinear metamaterial. The algorithm produces a plasmonic pattern that can maximize the second-order nonlinear effect of a nonlinear metamaterial. A nanolaminate metamaterial is used as a nonlinear material, and plasmonic patterns are fabricated on the prepared nanolaminate to demonstrate the validity and efficacy of the deep learning algorithm. The optimal pattern produced yielded second-harmonic generation from the nanolaminate with normal incident fundamental light. The deep learning architecture applied in this research can be expanded to other optical responses and light–matter interaction processes.
- 14 February 2022
- Published by American Chemical Society (ACS) in ACS Nano
- Vol. 16 (3) , 3926-3933
Maximized Frequency Doubling through the Inverse Design of Nonlinear Metamaterials
The conventional process for developing an optimal design for nonlinear optical responses is based on a trial-and-error approach that is largely inefficient and does not necessarily lead to an ideal result. Deep learning can automate this process and widen the realm of nonlinear geometries and devices. This research illustrates a deep learning framework used to create an optimal plasmonic design for a nonlinear metamaterial. The algorithm produces a plasmonic pattern that can maximize the second-order nonlinear effect of a nonlinear metamaterial. A nanolaminate metamaterial is used as a nonlinear material, and plasmonic patterns are fabricated on the prepared nanolaminate to demonstrate the validity and efficacy of the deep learning algorithm. The optimal pattern produced yielded second-harmonic generation from the nanolaminate with normal incident fundamental light. The deep learning architecture applied in this research can be expanded to other optical responses and light–matter interaction processes.
- 19 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 29 (5) , 857-870
A Comprehensive Framework for Analysis of Time-Dependent Performance-Reliability Degradation of SRAM Cache Memory
This article describes a comprehensive framework for analysis of time-dependent performance-reliability degradation of an SRAM cache, considering cache configurations, process parameters and their variations, supply voltage, and aging. The framework consists of three parts: microprocessor emulation, activity extraction, and evaluation of performance-reliability metrics. Evaluation of performance-reliability metrics is implemented with a prediction engine involving regression models for the metrics, which evaluates degradation due to various wearout mechanisms, including bias temperature instability (BTI), hot carrier injection (HCI), and random telegraph noise (RTN). The regression models not only enable more than$100\times $ faster computation compared with SPICE simulations but also protect intellectual property. This framework has been applied to study how SRAM instruction cache (I-Cache) configurations, cell structure, inclusion of RTN and gate length variation, voltage scaling, and stress time affect the performance and reliability parameters, such as access time, leakage power, critical charge ($Q_{\mathrm {crit}}$ ), and static noise margin (SNM). We have also studied the impact of configuration parameters on the soft error rate (SER) and the hit rate of the I-Cache, and the impact of single error correction and double error detection (SECDED) error correcting codes (ECCs).- 19 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 29 (5) , 857-870
A Comprehensive Framework for Analysis of Time-Dependent Performance-Reliability Degradation of SRAM Cache Memory
This article describes a comprehensive framework for analysis of time-dependent performance-reliability degradation of an SRAM cache, considering cache configurations, process parameters and their variations, supply voltage, and aging. The framework consists of three parts: microprocessor emulation, activity extraction, and evaluation of performance-reliability metrics. Evaluation of performance-reliability metrics is implemented with a prediction engine involving regression models for the metrics, which evaluates degradation due to various wearout mechanisms, including bias temperature instability (BTI), hot carrier injection (HCI), and random telegraph noise (RTN). The regression models not only enable more than$100\times $ faster computation compared with SPICE simulations but also protect intellectual property. This framework has been applied to study how SRAM instruction cache (I-Cache) configurations, cell structure, inclusion of RTN and gate length variation, voltage scaling, and stress time affect the performance and reliability parameters, such as access time, leakage power, critical charge ($Q_{\mathrm {crit}}$ ), and static noise margin (SNM). We have also studied the impact of configuration parameters on the soft error rate (SER) and the hit rate of the I-Cache, and the impact of single error correction and double error detection (SECDED) error correcting codes (ECCs).- 8 January 2021
- Published by American Chemical Society (ACS) in ACS Nano
- Vol. 15 (2) , 2318-2326
Building Multifunctional Metasystems via Algorithmic Construction
Flat optics foresees a promising route to ultracompact optical devices, where metasurfaces serve as the foundation. Conventional designs of metasurfaces start with a certain structure as the prototype, followed by extensive parametric sweeps to accommodate the requirements of phase and amplitude of the emerging light. Regardless of how computation consuming the process is, a predefined structure can hardly realize the independent control over polarization, frequency, and spatial channels, which hinders the potential of metasurfaces to be multifunctional. Besides, achieving complicated and multiple functions calls for designing metasystems with multiple cascading layers of metasurfaces, which introduces exponential complexity. In this work, we present a hybrid deep learning framework for designing multilayer metasystems with multifunctional capabilities. We demonstrate examples of a polarization-multiplexed dual-functional beam generator, a second-order differentiator for all-optical computing, and a space-polarization-wavelength multiplexed hologram. These examples are barely achievable by single-layer metasurfaces and unattainable by traditional design processes.
- 8 January 2021
- Published by American Chemical Society (ACS) in ACS Nano
- Vol. 15 (2) , 2318-2326
Building Multifunctional Metasystems via Algorithmic Construction
Flat optics foresees a promising route to ultracompact optical devices, where metasurfaces serve as the foundation. Conventional designs of metasurfaces start with a certain structure as the prototype, followed by extensive parametric sweeps to accommodate the requirements of phase and amplitude of the emerging light. Regardless of how computation consuming the process is, a predefined structure can hardly realize the independent control over polarization, frequency, and spatial channels, which hinders the potential of metasurfaces to be multifunctional. Besides, achieving complicated and multiple functions calls for designing metasystems with multiple cascading layers of metasurfaces, which introduces exponential complexity. In this work, we present a hybrid deep learning framework for designing multilayer metasystems with multifunctional capabilities. We demonstrate examples of a polarization-multiplexed dual-functional beam generator, a second-order differentiator for all-optical computing, and a space-polarization-wavelength multiplexed hologram. These examples are barely achievable by single-layer metasurfaces and unattainable by traditional design processes.
- Top Cited PapersOpen Access
- 7 January 2021
- Published by Wiley in Advanced Science
- Vol. 8 (5)
Tackling Photonic Inverse Design with Machine Learning
Machine learning, as a study of algorithms that automate prediction and decision‐making based on complex data, has become one of the most effective tools in the study of artificial intelligence. In recent years, scientific communities have been gradually merging data‐driven approaches with research, enabling dramatic progress in revealing underlying mechanisms, predicting essential properties, and discovering unconventional phenomena. It is becoming an indispensable tool in the fields of, for instance, quantum physics, organic chemistry, and medical imaging. Very recently, machine learning has been adopted in the research of photonics and optics as an alternative approach to address the inverse design problem. In this report, the fast advances of machine‐learning‐enabled photonic design strategies in the past few years are summarized. In particular, deep learning methods, a subset of machine learning algorithms, dealing with intractable high degrees‐of‐freedom structure design are focused upon.
- 7 January 2021
- Published by Wiley in Advanced Science
- Vol. 8 (5)
Top Cited PapersOpen AccessTackling Photonic Inverse Design with Machine Learning
Machine learning, as a study of algorithms that automate prediction and decision‐making based on complex data, has become one of the most effective tools in the study of artificial intelligence. In recent years, scientific communities have been gradually merging data‐driven approaches with research, enabling dramatic progress in revealing underlying mechanisms, predicting essential properties, and discovering unconventional phenomena. It is becoming an indispensable tool in the fields of, for instance, quantum physics, organic chemistry, and medical imaging. Very recently, machine learning has been adopted in the research of photonics and optics as an alternative approach to address the inverse design problem. In this report, the fast advances of machine‐learning‐enabled photonic design strategies in the past few years are summarized. In particular, deep learning methods, a subset of machine learning algorithms, dealing with intractable high degrees‐of‐freedom structure design are focused upon.
- Open Access
- 19 October 2020
- Published by Association for Computing Machinery (ACM)
- p. 2285-2288
Deep Interaction Machine
Click-Through Rate (CTR) prediction is a crucial task for various online applications, such as recommendation and online advertising. The task of CTR prediction is to predict the probability of users' clicking behaviors, with high-dimensional input features. To avoid heavy handcrafted feature engineering, the core topic of CTR prediction is the automatic interactions of the input features. Factorization Machine (FM) is an effective approach for modeling second-order feature interactions. Recently, FM has been extended for modeling higher-order feature interactions, such as xDeepFM and Higher-Order Factorization Machine (HOFM). However, these approaches are with either high complexity or iterative computation consuming much time and space. To overcome above problems, we express arbitrary-order FM in the form of power sums according to Newton's identities. Accordingly, we propose a novel Interaction Machine (IM) model. IM is an efficient and exact implementation of high-order FM, whose time complexity linearly grows with the order of interactions and the number of feature fields. Via IM, we can conduct arbitrary-order feature interactions in a very simple way. Moreover, we perform IM together with deep neural networks, and the resulted DeepIM model is more efficient than xDeepFM with comparable or even better performance. We conduct experiments on two real-world datasets, in which effectiveness and efficiency of both IM and DeepIM are strongly verified.
- 19 October 2020
- Published by Association for Computing Machinery (ACM)
- p. 2285-2288
Open AccessDeep Interaction Machine
Click-Through Rate (CTR) prediction is a crucial task for various online applications, such as recommendation and online advertising. The task of CTR prediction is to predict the probability of users' clicking behaviors, with high-dimensional input features. To avoid heavy handcrafted feature engineering, the core topic of CTR prediction is the automatic interactions of the input features. Factorization Machine (FM) is an effective approach for modeling second-order feature interactions. Recently, FM has been extended for modeling higher-order feature interactions, such as xDeepFM and Higher-Order Factorization Machine (HOFM). However, these approaches are with either high complexity or iterative computation consuming much time and space. To overcome above problems, we express arbitrary-order FM in the form of power sums according to Newton's identities. Accordingly, we propose a novel Interaction Machine (IM) model. IM is an efficient and exact implementation of high-order FM, whose time complexity linearly grows with the order of interactions and the number of feature fields. Via IM, we can conduct arbitrary-order feature interactions in a very simple way. Moreover, we perform IM together with deep neural networks, and the resulted DeepIM model is more efficient than xDeepFM with comparable or even better performance. We conduct experiments on two real-world datasets, in which effectiveness and efficiency of both IM and DeepIM are strongly verified.
- Top Cited Papers
- 5 October 2020
- Published by Springer Nature in Nature Photonics
- Vol. 15 (2) , 77-90
Deep learning for the design of photonic structures
- 5 October 2020
- Published by Springer Nature in Nature Photonics
- Vol. 15 (2) , 77-90
Top Cited PapersDeep learning for the design of photonic structures
- 5 February 2020
- Published by Optica Publishing Group in Optics Express
- Vol. 28 (4) , 4825-4835
Topological encoding method for data-driven photonics inverse design
Data-driven approaches have been proposed as effective strategies for the inverse design and optimization of photonic structures in recent years. In order to assist data-driven methods for the design of topology of photonic devices, we propose a topological encoding method that transforms photonic structures represented by binary images to a continuous sparse representation. This sparse representation can be utilized for dimensionality reduction and dataset generation, enabling effective analysis and optimization of photonic topologies with data-driven approaches. As a proof of principle, we leverage our encoding method for the design of two dimensional non-paraxial diffractive optical elements with various diffraction intensity distributions. We proved that our encoding method is able to assist machine-learning-based inverse design approaches for accurate and global optimization.
- 5 February 2020
- Published by Optica Publishing Group in Optics Express
- Vol. 28 (4) , 4825-4835
Topological encoding method for data-driven photonics inverse design
Data-driven approaches have been proposed as effective strategies for the inverse design and optimization of photonic structures in recent years. In order to assist data-driven methods for the design of topology of photonic devices, we propose a topological encoding method that transforms photonic structures represented by binary images to a continuous sparse representation. This sparse representation can be utilized for dimensionality reduction and dataset generation, enabling effective analysis and optimization of photonic topologies with data-driven approaches. As a proof of principle, we leverage our encoding method for the design of two dimensional non-paraxial diffractive optical elements with various diffraction intensity distributions. We proved that our encoding method is able to assist machine-learning-based inverse design approaches for accurate and global optimization.
- 28 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- Vol. 10 (1) , 126-135
A Hybrid Strategy for the Discovery and Design of Photonic Structures
Metasurfaces and metamaterials are playing a growing role in the control of electromagnetic waves in the application of communication, display, and sensing technologies. However, designing photonic structures as the building blocks of these systems is typically a tedious trial-and-error process that requires extensive simulations with iterative sweeps in a multi-dimensional parameter space. To circumvent this conventional approach and substantially expedite the discovery and development of photonic structures, here we develop a framework leveraging both a deep generative model and a modified evolution strategy to automate the inverse design of engineered photonic materials and devices. The capacity of the proposed methodology is tested through the application to a case study, where metasurfaces in either continuous or discrete topologies are generated in response to customer-defined spectra at the input. Through a variational autoencoder, all potential patterns of unit structures are encoded into a continuous latent space. An evolution strategy is applied to vectors in the latent space to identify an optimized vector whose corresponding metasurface fulfills the design objective. The evaluation shows that over 95% accuracy can be achieved for all the unit patterns of the metasurfaces in the test dataset. Our scheme requires no prior knowledge of the geometry of the photonic structures, and, in principle, allows joint optimization of the dimensional parameters. As such, our work represents an efficient, on-demand, and automated approach for the inverse design of photonic structures with subwavelength features.
- 28 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- Vol. 10 (1) , 126-135
A Hybrid Strategy for the Discovery and Design of Photonic Structures
Metasurfaces and metamaterials are playing a growing role in the control of electromagnetic waves in the application of communication, display, and sensing technologies. However, designing photonic structures as the building blocks of these systems is typically a tedious trial-and-error process that requires extensive simulations with iterative sweeps in a multi-dimensional parameter space. To circumvent this conventional approach and substantially expedite the discovery and development of photonic structures, here we develop a framework leveraging both a deep generative model and a modified evolution strategy to automate the inverse design of engineered photonic materials and devices. The capacity of the proposed methodology is tested through the application to a case study, where metasurfaces in either continuous or discrete topologies are generated in response to customer-defined spectra at the input. Through a variational autoencoder, all potential patterns of unit structures are encoded into a continuous latent space. An evolution strategy is applied to vectors in the latent space to identify an optimized vector whose corresponding metasurface fulfills the design objective. The evaluation shows that over 95% accuracy can be achieved for all the unit patterns of the metasurfaces in the test dataset. Our scheme requires no prior knowledge of the geometry of the photonic structures, and, in principle, allows joint optimization of the dimensional parameters. As such, our work represents an efficient, on-demand, and automated approach for the inverse design of photonic structures with subwavelength features.
- Open Access
A topological encoding method for data-driven photonics inverse design
Data-driven approaches have been proposed as effective strategies for the inverse design and optimization of photonic structures in recent years. In order to assist data-driven methods for the design of topology of photonic devices, we propose a topological encoding method that transforms photonic structures represented by binary images to a continuous sparse representation. This sparse representation can be utilized for dimensionality reduction and dataset generation, enabling effective analysis and optimization of photonic topologies with data-driven approaches. As a proof of principle, we leverage our encoding method for the design of two dimensional non-paraxial diffractive optical elements with various diffraction intensity distributions. We proved that our encoding method is able to assist machine-learning-based inverse design approach for accurate and global optimization.
Open AccessA topological encoding method for data-driven photonics inverse design
Data-driven approaches have been proposed as effective strategies for the inverse design and optimization of photonic structures in recent years. In order to assist data-driven methods for the design of topology of photonic devices, we propose a topological encoding method that transforms photonic structures represented by binary images to a continuous sparse representation. This sparse representation can be utilized for dimensionality reduction and dataset generation, enabling effective analysis and optimization of photonic topologies with data-driven approaches. As a proof of principle, we leverage our encoding method for the design of two dimensional non-paraxial diffractive optical elements with various diffraction intensity distributions. We proved that our encoding method is able to assist machine-learning-based inverse design approach for accurate and global optimization.