171 Hits in 5.2 sec

NAIS: Neural Architecture and Implementation Search and its Applications in Autonomous Driving [article]

Cong Hao, Yao Chen, Xinheng Liu, Atif Sarwari, Daryl Sew, Ashutosh Dhar, Bryan Wu, Dongdong Fu, Jinjun Xiong, Wen-mei Hwu, Junli Gu, Deming Chen
2019 arXiv   pre-print
In this position paper, we argue that a simultaneous DNN/implementation co-design methodology, named Neural Architecture and Implementation Search (NAIS), deserves more research attention to boost the  ...  We take autonomous driving as a key use case as it is one of the most demanding areas for high quality AI algorithms and accelerators.  ...  ACKNOWLEDGEMENT This work is supported in part by, Semiconductor Research Corporation (SRC), the IBM-Illinois Center for Cognitive Computing System Research (C3SR) and Advanced Digital Sciences  ... 
arXiv:1911.07446v1 fatcat:5daaueicx5agrfrvfocmigvqba

Software/Hardware Co-design for Multi-modal Multi-task Learning in Autonomous Systems [article]

Cong Hao, Deming Chen
2021 arXiv   pre-print
While MMMT learning has been attracting intensive research interests, its applications in autonomous systems are still underexplored.  ...  We advocate for further explorations of MMMT in autonomous systems and software/hardware co-design solutions.  ...  NAIS [51] and EDD [52] are two existing automated neural architecture and implementation co-search frameworks.  ... 
arXiv:2104.04000v1 fatcat:vf673pujtvhg7nyqrlppmsk2fa

Effective Algorithm-Accelerator Co-design for AI Solutions on Edge Devices [article]

Cong Hao, Yao Chen, Xiaofan Zhang, Yuhong Li, Jinjun Xiong, Wen-mei Hwu, Deming Chen
2020 arXiv   pre-print
; 3) a differentiable and efficient DNN and accelerator co-search method.  ...  High quality AI solutions require joint optimization of AI algorithms, such as deep neural networks (DNNs), and their hardware accelerators.  ...  Excellence and Technological Enterprise (CREATE) programme in Singapore.  ... 
arXiv:2010.07185v2 fatcat:erfoyh536rgmlklbr4pvrfuds4


Nai-Hsin Pan, Ching-Hsiang Tsai, Kuei-Yuan Chen, Jessie Sung
2020 Journal of Civil Engineering and Management  
The inspection results in using this method are affected by the factors of subjectivity, safety and cost.  ...  This proposed method implements Forward Looking Infrared (FLIR) technology and high-resolution photographic equipment on Unmanned Aerial Vehicle (UAV) which can improve the image recording of the detection  ...  Nai-Hsin Pan and Jessie Sung are supervisors. Disclosure statement Nothing to declare.  ... 
doi:10.3846/jcem.2020.11925 fatcat:v2z7h6as6rhnjnc3whytldmgfa

Efficient Machine Learning, Compilers, and Optimizations for Embedded Systems [article]

Xiaofan Zhang, Yao Chen, Cong Hao, Sitao Huang, Yuhong Li, Deming Chen
2022 arXiv   pre-print
Deep Neural Networks (DNNs) have achieved great success in a massive number of artificial intelligence (AI) applications by delivering high-quality computer vision, natural language processing, and virtual  ...  To address these challenges, we will introduce a series of effective design methods in this book chapter to enable efficient algorithms, compilers, and various optimizations for embedded systems.  ...  neural architecture and implementation co-search, targeting arbitrary hardware platforms.  ... 
arXiv:2206.03326v1 fatcat:th66tbqxibez7hmctl2ytdiroa

Generalization of Agent Behavior through Explicit Representation of Context [article]

Cem C Tutum, Suhaib Abdulquddos, Risto Miikkulainen
2021 arXiv   pre-print
The approach is evaluated in the Flappy Bird and LunarLander video games, as well as in the CARLA autonomous driving simulation.  ...  Such a principled generalization ability is essential in deploying autonomous agents in real-world tasks, and can serve as a foundation for continual adaptation as well.  ...  Remarkably, whereas in sentence processing the standardization was implemented by a hand-designed architecture, in Context+Skill it is automatically discovered by evolution.  ... 
arXiv:2006.11305v2 fatcat:zqi5ksor5veazk43zt445qez54

Intelligent Edge-Embedded Technologies for Digitising Industry [chapter]

Ovidiu Vermesan, Mario Diaz Nava
2022 Intelligent Edge-Embedded Technologies for Digitising Industry  
Topics range from the theory and use of systems involving all terminals, computers, and information processors to wired and wireless networks and network layouts, protocols, architectures, and implementations  ...  The "River Publishers Series in Communications and Networking" is a series of comprehensive academic and professional books which focus on communication and network systems.  ...  This work reflects only the author's view, JU, EU and BMBF are not responsible for any use that may be made of the information it contains.  ... 
doi:10.13052/rp-9788770226103 fatcat:mgz277pmkbetvbpoaomoktzgzi

Design and Implementation of a Radioactive Source Intelligent Search Robot Based on Artificial Intelligence Edge Computing

Pin Wang, Zhijian Gao, Yimin Li, Lingyu Zeng, Hongmei Zhong
2022 Wireless Communications and Mobile Computing  
In this paper, a research method for the design and implementation of a radioactive source intelligent search robot based on artificial intelligence edge computing is proposed, including intelligent edge  ...  This paper mainly introduces the design and implementation of a radioactive source intelligent search robot based on artificial intelligence edge computing, aiming to provide some ideas and directions  ...  as NaI (Tl).  ... 
doi:10.1155/2022/3940348 doaj:a7e53e512a7e4d0993b812931852d9b6 fatcat:gubo36giffbvdndwbn6i6xkz74

Deep Learning and Reinforcement Learning for Autonomous Unmanned Aerial Systems: Roadmap for Theory to Deployment [article]

Jithin Jagannath, Anu Jagannath, Sean Furman, Tyler Gwin
2020 arXiv   pre-print
The exponential increase in computing resources and the availability of large amount of data in this digital era has led to the resurgence of machine learning from its last winter.  ...  Therefore, in this chapter, we discuss how some of the advances in machine learning, specifically deep learning and reinforcement learning can be leveraged to develop next-generation autonomous UAS.  ...  These characteristics of reinforcement learning have led to many research efforts on its application to autonomous UAS applications.  ... 
arXiv:2009.03349v2 fatcat:5ylreoukrfcrtorzzp44mntjum

From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence [article]

Nicholas Roy, Ingmar Posner, Tim Barfoot, Philippe Beaudoin, Yoshua Bengio, Jeannette Bohg, Oliver Brock, Isabelle Depatie, Dieter Fox, Dan Koditschek, Tomas Lozano-Perez, Vikash Mansinghka (+8 others)
2021 arXiv   pre-print
Contrary to viewing embodied intelligence as another application domain for machine learning, here we argue that it is in fact a key driver for the advancement of machine learning technology.  ...  Machine learning has long since become a keystone technology, accelerating science and applications in a broad range of domains.  ...  Leslie Kaelbling assisted with several ideas in this paper, and her considerable time and help is also very gratefully acknowledged.  ... 
arXiv:2110.15245v1 fatcat:juxc4tai2jbklpul55loccnp7e

Scanning the Issue

Azim Eskandarian
2022 IEEE transactions on intelligent transportation systems (Print)  
practical applications, including traffic management, safety, and energy efficiency.  ...  This article first presents the state-of-the-art communication technologies, standards, and protocols in vehicular networks (either inter-vehicle networking or in-vehicle networking) along with several  ...  For rough search, it proposes an improved A* algorithm implemented in the discrete time layer to find out the suboptimal states efficiently.  ... 
doi:10.1109/tits.2022.3141513 fatcat:gvywr655cvgolg7rfjrqmt33b4


2020 2020 IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)  
Secondly, we adopt a train model based on Tensorflow and Keras architecture, and utilize neural network to implement PM2.5 feature extraction and detection.  ...  In this paper, two common architectures of passive and active capacitive fingerprint sensors are introduced which are implemented by VIS 0.18μm process.  ...  The circuit architecture has been implemented to drive a 100-pF capacitor in parallel with a 1-K ohm resistor load.  ... 
doi:10.1109/icce-taiwan49838.2020.9258230 fatcat:g25vw7mzvradxna2grlzp6kgiq

Clinical applications of artificial intelligence and machine learning in cancer diagnosis: looking into the future

Muhammad Javed Iqbal, Zeeshan Javed, Haleema Sadia, Ijaz A. Qureshi, Asma Irshad, Rais Ahmed, Kausar Malik, Shahid Raza, Asif Abbas, Raffaele Pezzani, Javad Sharifi-Rad
2021 Cancer Cell International  
Clinical applications of AI and Machine Learning (ML) in cancer diagnosis and treatment are the future of medical guidance towards faster mapping of a new treatment for every individual.  ...  In this review, we focused to present game-changing technology of the future in clinics, by connecting biology with Artificial Intelligence and explain how AI-based assistance help oncologist for precise  ...  Acknowledgements Not applicable.  ... 
doi:10.1186/s12935-021-01981-1 pmid:34020642 fatcat:2q6aeg4jobdlplcjhemadavez4

Deep Reinforcement Learning Overview of the state of the Art

Youssef Fenjiro, Houda Benbrahim
2018 Journal of Automation, Mobile Robotics & Intelligent Systems  
The adoption of DL neural networks in RL, in the first decade of the 21 century, led to an end-toend framework allowing a great advance in human-level agents and autonomous systems, called deep reinforcement  ...  , giving an outline of current challenges and real-world applications, along with the hardware and frameworks used.  ...  many use cases and applications, but it often fails in areas where the feedback is sparse.  ... 
doi:10.14313/jamris_3-2018/15 fatcat:wn5i7y7tgfhvnhz3u5xkqlgvpe

Human-in-the-Loop Methods for Data-Driven and Reinforcement Learning Systems [article]

Vinicius G. Goecks
2020 arXiv   pre-print
metrics in real-time and in real world scenarios.  ...  Recent successes combine reinforcement learning algorithms and deep neural networks, despite reinforcement learning not being widely applied to robotics and real world scenarios.  ...  . • How: Advances in the fields of Neural Architecture Search (NAS) and Neural Network Compression can be leverage to find smaller architectures with similar accuracy that can increase inference speed  ... 
arXiv:2008.13221v1 fatcat:aofoenmwcvckvagbttrkskevty
« Previous Showing results 1 — 15 out of 171 results