scholarly journals Real-time multi-task diffractive deep neural networks via hardware-software co-design

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Yingjie Li ◽  
Ruiyang Chen ◽  
Berardi Sensale-Rodriguez ◽  
Weilu Gao ◽  
Cunxi Yu
Keyword(s):  
Neural Networks ◽  
Real Time ◽  
Power Efficiency ◽  
Deep Neural Networks ◽  
Design Method ◽  
Optical Computing ◽  
Domain Specific ◽  
Constrained Environments ◽  
Task Architecture ◽  
Hardware Efficiency

AbstractDeep neural networks (DNNs) have substantial computational requirements, which greatly limit their performance in resource-constrained environments. Recently, there are increasing efforts on optical neural networks and optical computing based DNNs hardware, which bring significant advantages for deep learning systems in terms of their power efficiency, parallelism and computational speed. Among them, free-space diffractive deep neural networks (D2NNs) based on the light diffraction, feature millions of neurons in each layer interconnected with neurons in neighboring layers. However, due to the challenge of implementing reconfigurability, deploying different DNNs algorithms requires re-building and duplicating the physical diffractive systems, which significantly degrades the hardware efficiency in practical application scenarios. Thus, this work proposes a novel hardware-software co-design method that enables first-of-its-like real-time multi-task learning in D22NNs that automatically recognizes which task is being deployed in real-time. Our experimental results demonstrate significant improvements in versatility, hardware efficiency, and also demonstrate and quantify the robustness of proposed multi-task D2NN architecture under wide noise ranges of all system components. In addition, we propose a domain-specific regularization algorithm for training the proposed multi-task architecture, which can be used to flexibly adjust the desired performance for each task.

scholarly journals Assurance monitoring of learning-enabled cyber-physical systems using inductive conformal prediction based on distance learning

2021 ◽  
Vol 35 (2) ◽  
pp. 251-264
Author(s):  
Dimitrios Boursinos ◽  
Xenofon Koutsoukos
Keyword(s):  
Neural Networks ◽  
Distance Learning ◽  
Real Time ◽  
Speaker Recognition ◽  
Deep Neural Networks ◽  
Cyber Physical Systems ◽  
Error Rates ◽  
Traffic Sign ◽  
Conformal Prediction ◽  
Physical Systems

AbstractMachine learning components such as deep neural networks are used extensively in cyber-physical systems (CPS). However, such components may introduce new types of hazards that can have disastrous consequences and need to be addressed for engineering trustworthy systems. Although deep neural networks offer advanced capabilities, they must be complemented by engineering methods and practices that allow effective integration in CPS. In this paper, we proposed an approach for assurance monitoring of learning-enabled CPS based on the conformal prediction framework. In order to allow real-time assurance monitoring, the approach employs distance learning to transform high-dimensional inputs into lower size embedding representations. By leveraging conformal prediction, the approach provides well-calibrated confidence and ensures a bounded small error rate while limiting the number of inputs for which an accurate prediction cannot be made. We demonstrate the approach using three datasets of mobile robot following a wall, speaker recognition, and traffic sign recognition. The experimental results demonstrate that the error rates are well-calibrated while the number of alarms is very small. Furthermore, the method is computationally efficient and allows real-time assurance monitoring of CPS.

scholarly journals Diagnostic data integration using deep neural networks for real-time plasma analysis

2021 ◽  
pp. 1-1
Author(s):  
A. Rigoni Garola ◽  
R. Cavazzana ◽  
M. Gobbin ◽  
R.S. Delogu ◽  
G. Manduchi ◽  
...  
Keyword(s):  
Neural Networks ◽  
Data Integration ◽  
Real Time ◽  
Deep Neural Networks ◽  
Plasma Analysis ◽  
Diagnostic Data

scholarly journals A Power Efficiency Enhancements of a Multi-Bit Accelerator for Memory Prohibitive Deep Neural Networks

2021 ◽  
Vol 2 ◽  
pp. 156-169
Author(s):  
Suhas Shivapakash ◽  
Hardik Jain ◽  
Olaf Hellwich ◽  
Friedel Gerfers
Keyword(s):  
Neural Networks ◽  
Power Efficiency ◽  
Deep Neural Networks

scholarly journals Synthesizing Action Sequences for Modifying Model Decisions

2020 ◽  
Vol 34 (04) ◽  
pp. 5462-5469
Author(s):  
Goutham Ramakrishnan ◽  
Yun Chan Lee ◽  
Aws Albarghouthi
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Program Synthesis ◽  
Test Time ◽  
Domain Specific ◽  
Action Sequences

When a model makes a consequential decision, e.g., denying someone a loan, it needs to additionally generate actionable, realistic feedback on what the person can do to favorably change the decision. We cast this problem through the lens of program synthesis, in which our goal is to synthesize an optimal (realistically cheapest or simplest) sequence of actions that if a person executes successfully can change their classification. We present a novel and general approach that combines search-based program synthesis and test-time adversarial attacks to construct action sequences over a domain-specific set of actions. We demonstrate the effectiveness of our approach on a number of deep neural networks.

Real-time strawberry detection using deep neural networks on embedded system (rtsd-net): An edge AI application

2022 ◽  
Vol 192 ◽  
pp. 106586
Author(s):  
Yanchao Zhang ◽  
Jiya Yu ◽  
Yang Chen ◽  
Wen Yang ◽  
Wenbo Zhang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Embedded System ◽  
Real Time ◽  
Deep Neural Networks

Real-Time Downhole Geosteering Data Processing Using Deep Neural Networks On FPGA

2021 ◽  
Author(s):  
Qiyu Wan ◽  
Yuchen Jin ◽  
Xuqing Wu ◽  
Jiefu Chen ◽  
Xin Fu
Keyword(s):  
Neural Networks ◽  
Data Processing ◽  
Real Time ◽  
Deep Neural Networks

scholarly journals Latent Multi-Task Architecture Learning

2019 ◽  
Vol 33 ◽  
pp. 4822-4829 ◽  
Author(s):  
Sebastian Ruder ◽  
Joachim Bingel ◽  
Isabelle Augenstein ◽  
Anders Søgaard
Keyword(s):  
Neural Networks ◽  
Recent Work ◽  
Deep Neural Networks ◽  
Synthetic Data ◽  
Approaches To Learning ◽  
Average Error ◽  
Task Learning ◽  
Task Architecture ◽  
Parameter Sharing

Multi-task learning (MTL) allows deep neural networks to learn from related tasks by sharing parameters with other networks. In practice, however, MTL involves searching an enormous space of possible parameter sharing architectures to find (a) the layers or subspaces that benefit from sharing, (b) the appropriate amount of sharing, and (c) the appropriate relative weights of the different task losses. Recent work has addressed each of the above problems in isolation. In this work we present an approach that learns a latent multi-task architecture that jointly addresses (a)–(c). We present experiments on synthetic data and data from OntoNotes 5.0, including four different tasks and seven different domains. Our extension consistently outperforms previous approaches to learning latent architectures for multi-task problems and achieves up to 15% average error reductions over common approaches to MTL.

Sign in / Sign up

Export Citation Format

Share Document