1,606 Hits in 6.2 sec

Compilation and Optimizations for Efficient Machine Learning on Embedded Systems [article]

Xiaofan Zhang, Yao Chen, Cong Hao, Sitao Huang, Yuhong Li, Deming Chen
2022 arXiv   pre-print
to enable efficient ML applications on embedded systems.  ...  However, DNN-based ML applications also bring much increased computational and storage requirements, which are particularly challenging for embedded systems with limited compute/storage resources, tight  ...  Search algorithm Sampling-based Reinforcement learning, evolutionary algorithm, Bayesian optimization, random search...  ... 
arXiv:2206.03326v2 fatcat:gh6acseycjdejf6oij6nmclepa

A Review of Complex Systems Approaches to Cancer Networks [article]

Abicumaran Uthamacumaran
2020 arXiv   pre-print
Herein, a tumor and its heterogeneous phenotypes are discussed as dynamical systems having multiple, strange attractors.  ...  The emerging field of complex systems has redefined cancer networks as a computational system with intractable algorithmic complexity.  ...  A Galilean-invariance embedded, DNN network architecture (Tensor Basis Neural Network) underwent training on various turbulent flow datasets followed by the Bayesian optimization for the neural network's  ... 
arXiv:2009.12693v2 fatcat:kt3e4bqaufgwlbhx2wbgzftnpe

A Survey of Machine Learning for Computer Architecture and Systems [article]

Nan Wu, Yuan Xie
2021 arXiv   pre-print
It has been a long time that computer architecture and systems are optimized to enable efficient execution of machine learning (ML) algorithms or models.  ...  For ML-based design methodology, we follow a bottom-up path to review current work, with a scope of (micro-)architecture design (memory, branch prediction, NoC), coordination between architecture/system  ...  In heterogeneous systems with CPUs and GPUs, device placement refers to the process of mapping nodes in computational graphs of neural networks onto proper hardware devices.  ... 
arXiv:2102.07952v1 fatcat:vzj776a6abesljetqobakoc3dq

Using meta-heuristics and machine learning for software optimization of parallel computing systems: a systematic literature review

Suejb Memeti, Sabri Pllana, Alécio Binotto, Joanna Kołodziej, Ivona Brandic
2018 Computing  
Determining the optimal set of parameters in a given execution context is a complex task, and therefore to address this issue researchers have proposed different approaches that use heuristic search or  ...  In this paper, we undertake a systematic literature review to aggregate, analyze and classify the existing software optimization methods for parallel computing systems.  ..., which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a  ... 
doi:10.1007/s00607-018-0614-9 fatcat:da2rfxqlcjen5frzfxreimtngm

2020 Index IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems Vol. 39

2020 IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems  
., +, TCAD Nov. 2020 3373-3384 Modular Design and Optimization of Biomedical Applications for Ultralow Power Heterogeneous Platforms.  ...  ., +, TCAD Feb. 2020 520-532 FUZYE: A Fuzzy c-Means Analog IC Yield Optimization Using Evolutionary-Based Algorithms.  ... 
doi:10.1109/tcad.2021.3054536 fatcat:wsw3olpxzbeclenhex3f73qlw4

Hybrid Application Mapping for Composable Many-Core Systems: Overview and Future Perspective

Behnaz Pourmohseni, Michael Glaß, Jörg Henkel, Heba Khdr, Martin Rapp, Valentina Richthammer, Tobias Schwarzer, Fedor Smirnov, Jan Spieck, Jürgen Teich, Andreas Weichslgartner, Stefan Wildermann
2020 Journal of Low Power Electronics and Applications  
is divided into (i) a design-time Design Space Exploration (DSE) step per application to obtain a set of high-quality mapping options and (ii) a run-time system management step in which applications are  ...  Many-core platforms are rapidly expanding in various embedded areas as they provide the scalable computational power required to meet the ever-growing performance demands of embedded applications and systems  ...  The design problem of heterogeneous embedded systems, including the many-core application mapping problem, is typically represented using a graph-based system model, referred to as a specification which  ... 
doi:10.3390/jlpea10040038 fatcat:3pde6c5gmvcchifub3xnxpcm7u

Efficient Mapping of Dimensionality Reduction Designs onto Heterogeneous FPGAs

Christos-S Bouganis, Iosifina Pournara, Peter Y.K. Cheung
2007 15th Annual IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM 2007)  
In this paper, we propose a novel approach that couples the calculation of the linear projection basis, the area optimization problem, and the heterogeneity exploration of modern FPGAs under a probabilistic  ...  Currently, the optimization of such a design, in terms of area usage and efficient allocation of the embedded multipliers that exist in modern FPGAs, is considered as a separate problem to the basis calculation  ...  The proposed approach couples the problem of data approximation using a small set of variables, the problem of area design optimization, and the problem of heterogeneity exploration of modern FPGAs under  ... 
doi:10.1109/fccm.2007.50 dblp:conf/fccm/BouganisPC07 fatcat:brycqkkoujh63k3zhujogwl5sq

A Comprehensive Survey on Electronic Design Automation and Graph Neural Networks: Theory and Applications

Daniela Sánchez Lopera, Lorenzo Servadei, Gamze Naz Kiprit, Robert Wille, Wolfgang Ecker
2022 ACM Transactions on Design Automation of Electronic Systems  
We map those works to a design pipeline by defining graphs, tasks, and model types. Furthermore, we analyze their practical implications and outcomes.  ...  However, EDA approaches are time and resource-demanding, and they often do not guarantee optimal solutions.  ...  For instance, in [35] , the graph embeddings are the inputs to a Bayesian optimizer leveraging dropout to predict the uncertainty of the predictions.  ... 
doi:10.1145/3543853 fatcat:halhg7zwgvdpjkzf7g7ctxzuby

Automatic Unsupervised Outlier Model Selection

Yue Zhao, Ryan A. Rossi, Leman Akoglu
2021 Neural Information Processing Systems  
In this work, we tackle the unsupervised outlier model selection (UOMS) problem, and propose METAOD, a principled, data-driven approach to UOMS based on meta-learning.  ...  Given an unsupervised outlier detection task on a new dataset, how can we automatically select a good outlier detection algorithm and its hyperparameter(s) (collectively called a model)?  ...  onto the latent features.We simplify by learning a regression function f : R k → R k that maps the (lower dimensional) embedding features φ(M) (which are also used to initialize U) onto the final optimized  ... 
dblp:conf/nips/ZhaoRA21 fatcat:p5nkkvxhpnhyvep2vsmxbwoabe

Accelerating data mining workloads: current approaches and future challenges in system architecture design

Alok N. Choudhary, Daniel Honbo, Prabhat Kumar, Berkin Ozisikyilmaz, Sanchit Misra, Gokhan Memik
2011 Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery  
Experiments have shown that heterogeneous architectures employing GPUs or FPGAs can result in significant application speedups over homogenous CPU-based systems, while increasing performance per watt.  ...  Conventional systems based on general-purpose processors cannot keep pace with the exponential increase in the generation and collection of data.  ...  The GPU implementation of the summation function follows a tree-based approach. In this approach, the datapoints are summed in pairs at the root node.  ... 
doi:10.1002/widm.9 fatcat:ierjg2bucnbljiknyoqlomam2a

Enabling development of OpenCL applications on FPGA platforms

Kavya Shagrithaya, Krzysztof Kepa, Peter Athanas
2013 2013 IEEE 24th International Conference on Application-Specific Systems, Architectures and Processors  
Enabling Development of OpenCL Applications on FPGA platforms Kavya S Shagrithaya (ABSTRACT) FPGAs can potentially deliver tremendous acceleration in high-performance server and embedded computing applications  ...  In this thesis, a compilation flow to generate customized application-specific hardware descriptions from OpenCL computation kernels is presented.  ...  Impulse-C Co-developer tools include a C-to-FPGA compiler and platform support packages for a wide range of FPGA based embedded systems and high performance computing platforms.  ... 
doi:10.1109/asap.2013.6567546 dblp:conf/asap/ShagrithayaKA13 fatcat:5cb6mpbe35htjax7vn5skzbrwa

Gen: a general-purpose probabilistic programming system with programmable inference

Marco F. Cusumano-Towner, Feras A. Saad, Alexander K. Lew, Vikash K. Mansinghka
2019 Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation - PLDI 2019  
This Work We introduce Gen, a probabilistic programming system that uses a novel approach in which (i) users define probabilistic models in one or more embedded probabilistic DSLs and (ii) users implement  ...  Most languages provide automatic "black box" inference mechanisms based on Monte Carlo, gradient-based optimization, or neural networks.  ...  We give three examples of combinators: map, unfold, and recurse (Section 4). • Gen, a system implementing this approach with three interoperable probabilistic DSLs (Section 5). • An empirical evaluation  ... 
doi:10.1145/3314221.3314642 dblp:conf/pldi/Cusumano-Towner19 fatcat:bmjwmh7jhjf33gg6dywrdjop7y

A Unified Programmable Edge Matrix Processor for Deep Neural Networks and Matrix Algebra

Biji George, Om ji Omer, Ziaul Choudhury, Anoop V, Sreenivas Subramoney
2022 ACM Transactions on Embedded Computing Systems  
We submit MxCore as the generalized approach to facilitate the flexible acceleration of multiple Matrix Algebra and Deep-learning applications across a range of sparsity levels.  ...  However, constrained Edge systems requiring multiple applications and diverse matrix operations to be efficiently supported, cannot afford numerous custom accelerators.  ...  Having the flexibility to map both classical and Deep learning approaches in a hardware solution enables a broad range of AI applications. FigFig. 5 . 5 Fig. 4.  ... 
doi:10.1145/3524453 fatcat:miqhwzep3fey5admehib4md5ly

BISTRO: Berkeley Integrated System for Transportation Optimization [article]

Sidney A. Feygin, Jessica R. Lazarus, Edward H. Forscher, Valentine Golfier-Vetterli, Jonathan W. Lee, Abhishek Gupta, Rashid A. Waraich, Colin J.R. Sheppard, Alexandre M. Bayen
2020 arXiv   pre-print
This article introduces BISTRO, a new open source transportation planning decision support system that uses an agent-based simulation and optimization approach to anticipate and develop adaptive plans  ...  On the other hand, a follow-on study aimed to fix the objective function, served to demonstrate BISTRO's utility as a human-in-the-loop cyberphysical system: one that uses scenario-based optimization algorithms  ...  An example of such an approach is "freeze-thaw Bayesian Optimization" [48] .  ... 
arXiv:1908.03821v2 fatcat:upxxxx5tbvbmdaxojyr3abjwca

Scanning the Issue

Azim Eskandarian
2022 IEEE transactions on intelligent transportation systems (Print)  
In total, 90 subjects from China, South Korea, and the USA assume a pedestrian's role in a virtual reality-based pedestrian simulator and experience three encounter scenarios with an automated vehicle.  ...  This article investigates the influence of an external humanmachine interface (eHMI) for automated vehicles on pedestrian behavior in a parking lot.  ...  Furthermore, a selfadapting lane detection algorithm based solely on accelerometer readings is added on top of the map matching algorithm.  ... 
doi:10.1109/tits.2022.3160062 fatcat:4gklzaonfzcehnvps6oge35fwe
« Previous Showing results 1 — 15 out of 1,606 results