More Like this

1. All-optical ultrafast ReLU function for energy-efficient nanophotonic deep learning

   https://doi.org/10.1515/nanoph-2022-0137  

   Li, Gordon H.Y. ; Sekine, Ryoto ; Nehra, Rajveer ; Gray, Robert M. ; Ledezma, Luis ; Guo, Qiushi ; Marandi, Alireza ( May 2022 , Nanophotonics)

   Abstract In recent years, the computational demands of deep learning applications have necessitated the introduction of energy-efficient hardware accelerators. Optical neural networks are a promising option; however, thus far they have been largely limited by the lack of energy-efficient nonlinear optical functions. Here, we experimentally demonstrate an all-optical Rectified Linear Unit (ReLU), which is the most widely used nonlinear activation function for deep learning, using a periodically-poled thin-film lithium niobate nanophotonic waveguide and achieve ultra-low energies in the regime of femtojoules per activation with near-instantaneous operation. Our results provide a clear and practical path towards truly all-optical, energy-efficient nanophotonic deep learning. 

   more » « less
2. Adaptive Particle Filtering for Fault Detection in Partially-Observed Boolean Dynamical Systems

   https://doi.org/10.1109/TCBB.2018.2880234  

   Bahadorinejad, Arghavan ; Imani, Mahdi ; Braga-Neto, Ulisses ( November 2018 , IEEE/ACM Transactions on Computational Biology and Bioinformatics)

   We propose a novel methodology for fault detection and diagnosis in partially-observed Boolean dynamical systems (POBDS). These are stochastic, highly nonlinear, and derivative- less systems, rendering difficult the application of classical fault detection and diagnosis methods. The methodology comprises two main approaches. The first addresses the case when the normal mode of operation is known but not the fault modes. It applies an innovations filter (IF) to detect deviations from the nominal normal mode of operation. The second approach is applicable when the set of possible fault models is finite and known, in which case we employ a multiple model adaptive estimation (MMAE) approach based on a likelihood-ratio (LR) statistic. Unknown system parameters are estimated by an adaptive expectation- maximization (EM) algorithm. Particle filtering techniques are used to reduce the computational complexity in the case of systems with large state-spaces. The efficacy of the proposed methodology is demonstrated by numerical experiments with a large gene regulatory network (GRN) with stuck-at faults observed through a single noisy time series of RNA-seq gene expression measurements. 

   more » « less
3. Constant Coefficient Multipliers Using Self-Similarity-Based Hybrid Binary-Unary Computing

   https://doi.org/10.1109/ICCAD57390.2023.10323844  

   Khataei, Alireza ; Bazargan, Kia ( October 2023 , 2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD))

   Constant coefficient multipliers are widely used in digital signal processing and machine learning architectures. Researchers have proposed HBU-CCM (hybrid binary-unary constant coefficient multiplier), which is an approximate method that outperforms conventional binary and FloPoCo-KCM (table-based real multiplier) methods in terms of hardware cost at the expense of accuracy due to aliasing issues. SimBU (self-similarity-based hybrid binary-unary) is another method that was recently proposed to implement general nonlinear functions using self-similarities leading to few hardware resources. In this work, we use a simplified version of the SimBU algorithm to address the aliasing issues of HBU-CCM and improve accuracy. We also implement a convolution kernel for a Gaussian blurring filter to evaluate our method and compare it to previous works. Our method outperforms conventional binary and FloPoCo-KCM methods in terms of hardware cost with desired accuracy and with no aliasing error as opposed to HBU-CCM. 

   more » « less
4. Closure Learning for Nonlinear Model Reduction Using Deep Residual Neural Network

   https://doi.org/10.3390/fluids5010039  

   Xie, Xuping ; Webster, Clayton ; Iliescu, Traian ( March 2020 , Fluids)

   null (Ed.)

   Developing accurate, efficient, and robust closure models is essential in the construction of reduced order models (ROMs) for realistic nonlinear systems, which generally require drastic ROM mode truncations. We propose a deep residual neural network (ResNet) closure learning framework for ROMs of nonlinear systems. The novel ResNet-ROM framework consists of two steps: (i) In the first step, we use ROM projection to filter the given nonlinear system and construct a spatially filtered ROM. This filtered ROM is low-dimensional, but is not closed. (ii) In the second step, we use ResNet to close the filtered ROM, i.e., to model the interaction between the resolved and unresolved ROM modes. We emphasize that in the new ResNet-ROM framework, data is used only to complement classical physical modeling (i.e., only in the closure modeling component), not to completely replace it. We also note that the new ResNet-ROM is built on general ideas of spatial filtering and deep learning and is independent of (restrictive) phenomenological arguments, e.g., of eddy viscosity type. The numerical experiments for the 1D Burgers equation show that the ResNet-ROM is significantly more accurate than the standard projection ROM. The new ResNet-ROM is also more accurate and significantly more efficient than other modern ROM closure models. 

   more » « less
5. Security for safety: a path toward building trusted autonomous vehicles

   https://doi.org/10.1145/3240765.3243496  

   Dutta, Raj Gautam ; Yu, Feng ; Zhang, Teng ; Hu, Yaodan ; Jin, Yier ( November 2018 , Proceedings of the International Conference on Computer-Aided Design)

   Automotive systems have always been designed with safety in mind. In this regard, the functional safety standard, ISO 26262, was drafted with the intention of minimizing risk due to random hardware faults or systematic failure in design of electrical and electronic components of an automobile. However, growing complexity of a modern car has added another potential point of failure in the form of cyber or sensor attacks. Recently, researchers have demonstrated that vulnerability in vehicle's software or sensing units could enable them to remotely alter the intended operation of the vehicle. As such, in addition to safety, security should be considered as an important design goal. However, designing security solutions without the consideration of safety objectives could result in potential hazards. Consequently, in this paper we propose the notion of security for safety and show that by integrating safety conditions with our system-level security solution, which comprises of a modified Kalman filter and a Chi-squared detector, we can prevent potential hazards that could occur due to violation of safety objectives during an attack. Furthermore, with the help of a car-following case study, where the follower car is equipped with an adaptive-cruise control unit, we show that our proposed system-level security solution preserves the safety constraints and prevent collision between vehicle while under sensor attack. 

   more » « less