Results 231 to 240 of about 16,849 (282)

Approximate Computing for ML

Proceedings of the 26th Asia and South Pacific Design Automation Conference, 2021
In this paper, we present our state-of-the-art approximate techniques that cover the main pillars of approximate computing research. Our analysis considers both static and reconfigurable approximation techniques as well as operation-specific approximate components (e.g., multipliers) and generalized approximate high-level synthesis approaches.
Zervakis, Georgios, Saadat, H., Mrouch, H., Gerstlauer, A., Parameswaran, S., Henkel, Jörg   +5 more
openaire   +2 more sources

Approximations to joint-ML and ML symbol-channel estimators in MUD CDMA

Global Telecommunications Conference, 2002. GLOBECOM '02. IEEE, 2003
In this contribution we conceptually derive two symbol-channel estimators, the joint-ML and the ML, both having exponential complexity. Pragmatically we derive three approximations with polynomial complexity, one to the joint-ML: the pseudo-joint-ML; two to the ML: the naive-ML and the linear-response-ML. We assess the resulting average bit error rates
T. Fabricius, O. Norklit
openaire   +1 more source

Weighted MLS-SVM for approximation of directional derivatives

SPIE Proceedings, 2005
Based on statistical learning theory, support vector machine (SVM) is a novel type of learning machine, and it contains polynomial, neural network and radial basis function (RBF) as special cases. The mapped least squares support vector machine (MLS-SVM) is a special least square SVM (LS-SVM), which extends the application of the SVM to the image ...
Sheng Zheng, Jin Wen Tian, Jian Liu
openaire   +1 more source

MLS based local approximation in numerical manifold method

Engineering Computations, 2018
Purpose The purpose of this paper is to propose a new three-node triangular element in the framework of the numerical manifold method (NMM), which is designated by Trig3-MLScns. Design/methodology/approach The formulation uses the improved parametric shape functions of classical triangular elements (Trig3-0) to construct the partition of unity (PU ...
Yuanqiang Chen, H. Zheng, Wei Li, Shan Lin   +3 more
openaire   +1 more source

Approximate ML Detection Based on MMSE for MIMO Systems

PIERS Online, 2007
We derive two types of approximate maximum likelihood (ML) detection based on minimum mean squared error (MMSE), MMSE-CML (conditional ML) detection and MMSE- CLML (conditional local ML) detection, for MIMO communication system. A simple reliability judge rule to judge the estimate of the transmit symbols is also given.
Fan Wang, Yong Xiong, Xuemei Yang
openaire   +1 more source

Efficient approximate ML decoding units for polar list decoders

2015 IEEE Workshop on Signal Processing Systems (SiPS), 2015
Polar codes are of great interest since they are the first provably capacity-achieving forward error correction codes. To improve throughput of polar decoders, maximum likelihood (ML) decoding units are used by successive cancellation list (SCL) decoders as well as successive cancellation (SC) decoders.
Chenrong Xiong, Jun Lin, Zhiyuan Yan
openaire   +1 more source

Design of Majority Logic (ML) Based Approximate Full Adders

2018 IEEE International Symposium on Circuits and Systems (ISCAS), 2018
As a new paradigm in the nanoscale technologies, approximate computing enables error tolerance in the computational process; it has also emerged as a low power design methodology for arithmetic circuits. Majority logic (ML) is applicable to many emerging technologies and its basic building block (the 3-input majority voter) has been extensively used in
Zhang, Tingting, Liu, Weiqiang, McLarnon, Emma, O'Neill, Maire, Lombardi, Fabrizio   +4 more
openaire   +2 more sources

Approximate ML-estimates of random processes

Proceedings of 1994 IEEE International Symposium on Information Theory, 2002
Computationally feasible versions of maximum likelihood estimations (MLEs), called approximate MLEs (AMLEs), are introduced. Estimation models with all, some, or no AMLEs consistent are presented. >
openaire   +1 more source