Open Access. Powered by Scholars. Published by Universities.®

Computer Sciences Commons™

Open Access. Powered by Scholars. Published by Universities.®

Optimization

Discipline
Institution
Publication Year
Publication
Publication Type
File Type

Articles 121 - 150 of 352

Full-Text Articles in Computer Sciences

Adaptive Operating Hours For Improved Performance Of Taxi Fleets, Rajiv Ranjan Kumar, Pradeep Varakantham, Shih-Fen Cheng May 2021

Adaptive Operating Hours For Improved Performance Of Taxi Fleets, Rajiv Ranjan Kumar, Pradeep Varakantham, Shih-Fen Cheng

Research Collection School Of Computing and Information Systems

Taxi fleets and car aggregation systems are an important component of the urban public transportation system. Taxis and cars in taxi fleets and car aggregation systems (e.g., Uber) are dependent on a large number of self-controlled and profit-driven taxi drivers, which introduces inefficiencies in the system. There are two ways in which taxi fleet performance can be optimized: (i) Operational decision making: improve assignment of taxis/cars to customers, while accounting for future demand; (ii) strategic decision making: optimize operating hours of (taxi and car) drivers. Existing research has primarily focused on the operational decisions in (i) and we focus on …

Go to article

Deep Learning And Optimization In Visual Target Tracking, Mohammadreza Javanmardi May 2021

Deep Learning And Optimization In Visual Target Tracking, Mohammadreza Javanmardi

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Visual tracking is the process of estimating states of a moving object in a dynamic frame sequence. It has been considered as one of the most paramount and challenging topics in computer vision. Although numerous tracking methods have been introduced, developing a robust algorithm that can handle different challenges still remains unsolved. In this dissertation, we introduce four different trackers and evaluate their performance in terms of tracking accuracy on challenging frame sequences. Each of these trackers aims to address the drawbacks of their peers. The first developed method is called a structured multi-task multi-view tracking (SMTMVT) method, which exploits …

Go to article

Unified Multi-Objective Genetic Algorithm For Energy Efficient Job Shop Scheduling, Hongjong Wei, Shaobo Li, Huageng Quan, Dacheng Liu, Shu Rao, Chuanjiang Li, Jianjun Hu Apr 2021

Unified Multi-Objective Genetic Algorithm For Energy Efficient Job Shop Scheduling, Hongjong Wei, Shaobo Li, Huageng Quan, Dacheng Liu, Shu Rao, Chuanjiang Li, Jianjun Hu

Faculty Publications

In recent years, people have paid more and more attention to traditional manufacturing’s environmental impact, especially in terms of energy consumption and related emissions of carbon dioxide. Except for adopting new equipment, production scheduling could play an important role in reducing the total energy consumption of a manufacturing plant. Machine tools waste a considerable amount of energy because of their underutilization. Consequently, energy saving can be achieved by switching machines to standby or off when they lay idle for a comparatively long period. Herein, we first introduce the objectives of minimizing non-processing energy consumption, total weighted tardiness and earliness, and …

Go to article

Learning To Fuse Asymmetric Feature Maps In Siamese Trackers, Wencheng Han, Xingping Dong, Fahad Shahbaz Khan, Ling Shao, Jianbing Shen Mar 2021

Learning To Fuse Asymmetric Feature Maps In Siamese Trackers, Wencheng Han, Xingping Dong, Fahad Shahbaz Khan, Ling Shao, Jianbing Shen

Computer Vision Faculty Publications

Recently, Siamese-based trackers have achieved promising performance in visual tracking. Most recent Siamese-based trackers typically employ a depth-wise cross-correlation (DW-XCorr) to obtain multi-channel correlation information from the two feature maps (target and search region). However, DW-XCorr has several limitations within Siamese-based tracking: it can easily be fooled by distractors, has fewer activated channels and provides weak discrimination of object boundaries. Further, DW-XCorr is a handcrafted parameter-free module and cannot fully benefit from offline learning on large-scale data. We propose a learnable module, called the asymmetric convolution (ACM), which learns to better capture the semantic correlation information in offline training on …

Go to article

A Survey Of Edge Computing Resource Allocation And Task Scheduling Optimization, Wang Ling, Chuge Wu, Wenhui Fan Mar 2021

A Survey Of Edge Computing Resource Allocation And Task Scheduling Optimization, Wang Ling, Chuge Wu, Wenhui Fan

Journal of System Simulation

Abstract: With the rapid development of Internet of Things (IoT) and mobile terminals, the concept of edge computing arises. By moving the computation and storage capacity to the edge of network, edge computing is able to deal with a large amount of data produced by IoT devices and the responsive request from IoT application. To improve the utility of edge resource, the quality of service and quality of user experience, resource allocation and task scheduling optimization problems under edge computing attract wide attention. It becomes more difficult due to the geographic separated and heterogeneous features of edge computing resource as …

Go to article

Optimizing A Bank Of Kalman Filters For Navigation Integrity, Luis E. Sepulveda Mar 2021

Optimizing A Bank Of Kalman Filters For Navigation Integrity, Luis E. Sepulveda

Theses and Dissertations

Alternative navigation is an area of research which employs a variety of sensor technologies to provide a navigation solution in Global Navigation Satellite System degraded or denied environments. The Autonomy and Navigation Technology Center at the Air Force Institute of Technology has recently developed the Autonomous and Resilient Management of All-source Sensors (ARMAS) navigation framework which utilizes an array of Kalman Filters to provide a navigation solution resilient to sensor failures. The Kalman Filter array size increases exponentially as system sensors and detectable faults are scaled up, which in turn increases the computational power required to run ARMAS in areal-world …

Go to article

Waste Collection Routing Problem: A Mini-Review Of Recent Heuristic Approaches And Applications, Yun-Chia Liang, Vanny Minanda, Aldy Gunawan Mar 2021

Waste Collection Routing Problem: A Mini-Review Of Recent Heuristic Approaches And Applications, Yun-Chia Liang, Vanny Minanda, Aldy Gunawan

Research Collection School Of Computing and Information Systems

The waste collection routing problem (WCRP) can be defined as a problem of designing a route to serve all of the customers (represented as nodes) with the least total traveling time or distance, served by the least number of vehicles under specific constraints, such as vehicle capacity. The relevance of WCRP is rising due to its increased waste generation and all the challenges involved in its efficient disposal. This research provides a mini-review of the latest approaches and its application in the collection and routing of waste. Several metaheuristic algorithms are reviewed, such as ant colony optimization, simulated annealing, genetic …

Go to article

Machine Learning Morphisms: A Framework For Designing And Analyzing Machine Learning Work Ows, Applied To Separability, Error Bounds, And 30-Day Hospital Readmissions, Eric Zenon Cawi Jan 2021

Machine Learning Morphisms: A Framework For Designing And Analyzing Machine Learning Work Ows, Applied To Separability, Error Bounds, And 30-Day Hospital Readmissions, Eric Zenon Cawi

McKelvey School of Engineering Graduate Student Theses & Dissertations

A machine learning workflow is the sequence of tasks necessary to implement a machine learning application, including data collection, preprocessing, feature engineering, exploratory analysis, and model training/selection. In this dissertation we propose the Machine Learning Morphism (MLM) as a mathematical framework to describe the tasks in a workflow. The MLM is a tuple consisting of: Input Space, Output Space, Learning Morphism, Parameter Prior, Empirical Risk Function. This contains the information necessary to learn the parameters of the learning morphism, which represents a workflow task. In chapter 1, we give a short review of typical tasks present in a workflow, as …

Go to article

Molecule Optimization By Explainable Evolution, Binghong Chen, Tianzhe Wang, Chengtao Li, Hanjun Dai, Le Song Jan 2021

Molecule Optimization By Explainable Evolution, Binghong Chen, Tianzhe Wang, Chengtao Li, Hanjun Dai, Le Song

Machine Learning Faculty Publications

Optimizing molecules for desired properties is a fundamental yet challenging task in chemistry, material science, and drug discovery. This paper develops a novel algorithm for optimizing molecular properties via an Expectation-Maximization (EM) like explainable evolutionary process. The algorithm is designed to mimic human experts in the process of searching for desirable molecules and alternate between two stages: the first stage on explainable local search which identifies rationales, i.e., critical subgraph patterns accounting for desired molecular properties, and the second stage on molecule completion which explores the larger space of molecules containing good rationales. We test our approach against various baselines …

Go to article

A Linear Programming Approach To Multiple Instance Learning, Emel Şeyma Küçükaşci, Mustafa Gökçe Baydoğan, Zeki̇ Caner Taşkin Jan 2021

A Linear Programming Approach To Multiple Instance Learning, Emel Şeyma Küçükaşci, Mustafa Gökçe Baydoğan, Zeki̇ Caner Taşkin

Turkish Journal of Electrical Engineering and Computer Sciences

Multiple instance learning (MIL) aims to classify objects with complex structures and covers a wide range of real-world data mining applications. In MIL, objects are represented by a bag of instances instead of a single instance, and class labels are provided only for the bags. Some of the earlier MIL methods focus on solving MIL problem under the standard MIL assumption, which requires at least one positive instance in positive bags and all remaining instances are negative. This study proposes a linear programming framework to learn instance level contributions to bag label without emposing the standart assumption. Each instance of …

Go to article

Plant Species Identification In The Wild Based On Images Of Organs, Meghana Kovur Jan 2021

Plant Species Identification In The Wild Based On Images Of Organs, Meghana Kovur

Graduate Theses, Dissertations, and Problem Reports (ETD)

Image-based plant species identification in the wild is a difficult problem for several reasons. First, the input data is subject to a very high degree of variability because it is captured under fully unconstrained conditions. The same plant species may look very different in different images, while different species can often appear very similar, challenging even the recognition skills of human experts in the field. The large intra-class and small inter-class image variability makes this a fine-grained visual classification problem. One way to cope with this variability and to reduce image background noise is to predict species based on the …

Go to article

Green Underwater Wireless Communications Using Hybrid Optical-Acoustic Technologies, Kazi Y. Islam, Iftekhar Ahmad, Daryoush Habibi, M. Ishtiaque A. Zahed, Joarder Kamruzzaman Jan 2021

Green Underwater Wireless Communications Using Hybrid Optical-Acoustic Technologies, Kazi Y. Islam, Iftekhar Ahmad, Daryoush Habibi, M. Ishtiaque A. Zahed, Joarder Kamruzzaman

Research outputs 2014 to 2021

Underwater wireless communication is a rapidly growing field, especially with the recent emergence of technologies such as autonomous underwater vehicles (AUVs) and remotely operated vehicles (ROVs). To support the high-bandwidth applications using these technologies, underwater optics has attracted significant attention, alongside its complementary technology – underwater acoustics. In this paper, we propose a hybrid opto-acoustic underwater wireless communication model that reduces network power consumption and supports high-data rate underwater applications by selecting appropriate communication links in response to varying traffic loads and dynamic weather conditions. Underwater optics offers high data rates and consumes less power. However, due to the severe …

Go to article

Optimal Planning Dg And Bes Units In Distribution System Consideringuncertainty Of Power Generation And Time-Varying Load, Mansur Khasanov, Salah Kamel, Ayman Awad, Francisco Jurado Jan 2021

Optimal Planning Dg And Bes Units In Distribution System Consideringuncertainty Of Power Generation And Time-Varying Load, Mansur Khasanov, Salah Kamel, Ayman Awad, Francisco Jurado

Turkish Journal of Electrical Engineering and Computer Sciences

Global environmental problems associated with traditional energy generation have led to a rapid increasein the use of renewable energy sources (RES) in power systems. The integration of renewable energy technologiesis commercially available nowadays, and the most common of such RES technology is photovoltaic (PV). This paperproposes an application of hybrid teaching-learning and artificial bee colony (TLABC) technique for determining theoptimal allocation of PV based distributed generation (DG) and battery energy storage (BES) units in the distributionsystem (DS) with the aim of minimizing the total power losses. Besides, some potential nodes identified by the powerloss sensitivity factor (PLSF). Thereupon TLABC is …

Go to article

Structured Data Mining Networks, Time Series, And Time Series Of Networks, Lin Zhang Dec 2020

Structured Data Mining Networks, Time Series, And Time Series Of Networks, Lin Zhang

Legacy Theses & Dissertations (2009 - 2024)

The rate at which data is generated in modern applications has created an unprecedented demand for novel methods to effectively and efficiently extract insightful patterns. Methods aware of known domain-specific structure in the data tend to be advantageous. In particular, a joint temporal and networked view of observations offers a holistic lens to many real-world systems. Example domains abound: activity of social network users, gene interactions over time, a temporal load of infrastructure networks, and others. Existing analysis and mining approaches for such data exhibit limited quality and scalability due to their sensitivity to noise, missing observations, and the need …

Go to article

Micro Grid Control Optimization With Load And Solar Prediction, Shaju Saha Dec 2020

Micro Grid Control Optimization With Load And Solar Prediction, Shaju Saha

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

Using renewable energy can save money and keep the environment cleaner. Installing a solar PV system is a one-time cost but it can generate energy for a lifetime. Solar PV does not generate carbon emissions while producing power. This thesis evaluates the value of being able to make accurate predictions in the use of solar energy. It uses predicted solar power and load for a system and a battery to store the energy for future use and calculates the operating cost or profit in several designed conditions. Various factors like a different place, tuning the capacity of sources, changing buy/sell …

Go to article

Simulation Research On Armored Equipment Maintenance Support Resource Optimization, Huiqi Zhang, Chunliang Chen, Junyan Liu, Liu Shuai, Yongqing Zhang Sep 2020

Simulation Research On Armored Equipment Maintenance Support Resource Optimization, Huiqi Zhang, Chunliang Chen, Junyan Liu, Liu Shuai, Yongqing Zhang

Journal of System Simulation

Abstract: Contraposing the problem of armored equipment maintenance resource computation and optimization, the armored equipment maintenance support process was analyzed. The armored equipment maintenance support process concept model and the mathematic model were constructed based on discrete system modeling theory; while the simulation model based on net discrete event was given in apply of Anylogic software. The armored equipment maintenance support task fulfilling degree, the resource utilization degree, and the mean maintenance time were got by simulation computation. As a result that maintenance support resource was evaluated based on index weight, and the optimized values of the maintenance support resource …

Go to article

Quadratic Rational Trigonometric Spline Curves With Shape Controlling, Xinru Liu, Manman Wei, Shengjun Liu, Dangfu Yang Aug 2020

Quadratic Rational Trigonometric Spline Curves With Shape Controlling, Xinru Liu, Manman Wei, Shengjun Liu, Dangfu Yang

Journal of System Simulation

Abstract: A new quadratic rational trigonometric spline curve with a shape parameter was proposed. The value control and the inflection-point control of the interpolation scheme were discussed in theory. And the optimal methods for calculating the desired inflection-points was proposed, by using optimization theory. Numerical experiments show the interpolation spline and the optimization method can be used in modeling design.

Go to article

Adaptive Quick Artificial Bee Colony Algorithm Based On Opposition Learning, Xiaojian Yang, Yiwei Dong Aug 2020

Adaptive Quick Artificial Bee Colony Algorithm Based On Opposition Learning, Xiaojian Yang, Yiwei Dong

Journal of System Simulation

Abstract: On the basis of analyzing such shortcomings of the artificial bee colony algorithm (ABC) as slow convergence, low convergence precision and premature convergence, the opposition-learning adaptive quick artificial bee colony algorithm (OAQABC) was proposed. A new step size was proposed, which made the around food source parameter of quick artificial bee colony algorithm (QABC) adaptive, and combined the opposition-based learning to improve the employed bee phase. The experimental results show that OAQABC has better performance than basic ABC and QABC. Also the optimization performance of OAQABC is better than particle swarm optimization (PSO) algorithm and Cuckoo Search (CS) algorithm …

Go to article

Affinity Propagation Based Improved Group Search Optimizer Clustering Algorithm, Zhang Kang, Xingsheng Gu Aug 2020

Affinity Propagation Based Improved Group Search Optimizer Clustering Algorithm, Zhang Kang, Xingsheng Gu

Journal of System Simulation

Abstract: The essence of clustering is an optimization problem. It can be solved by swarm intelligent algorithms which are the popular research area in recent years. A novel Group Search Optimizer (GSO) algorithm named Fast Global Group Search Optimizer (FGGSO) was proposed. FGGSO improved the individuals' updating strategies of GSO, adopting the campaign strategy, destruction-construction strategy and accelerating-jumping strategy. By this means, the proposed algorithm improved the global and local search capability of the original GSO. Furthermore, based on this FGGSO algorithm, a novel improved AP algorithm was proposed. On account of deficiency of AP clustering unable to deal with …

Go to article

Semi-Steady-State Jaya Algorithm For Optimization, Uday K. Chakraborty Aug 2020

Semi-Steady-State Jaya Algorithm For Optimization, Uday K. Chakraborty

Educator Preparation & Leadership Faculty Works

The Jaya algorithm is arguably one of the fastest-emerging metaheuristics amongst the newest members of the evolutionary computation family. The present paper proposes a new, improved Jaya algorithm by modifying the update strategies of the best and the worst members in the population. Simulation results on a twelve-function benchmark test-suite and a real-world problem show that the proposed strategy produces results that are better and faster in the majority of cases. Statistical tests of significance are used to validate the performance improvement.

Go to article

Least-Energy Maneuver Of Five-Link Manipulator Constrained Within Tunnel Space Using Direct Collocation, Xiuqiang Pan, Chengcai Mei, Junjie Chen Aug 2020

Least-Energy Maneuver Of Five-Link Manipulator Constrained Within Tunnel Space Using Direct Collocation, Xiuqiang Pan, Chengcai Mei, Junjie Chen

Journal of System Simulation

Abstract: Optimal control and designs least-energy maneuver control laws for a five-linked manipulator were applied in order to carry out designated tasks in a confined space. Lagrange-Euler equation described the relationships between the actuators and system dynamics. Euler-Lagrange formulation indicates how optimization can be achieved when optimum occurs. Direct collocation method was introduced in order to solve this highly nonlinear dynamic optimal control problem. Simulations were done to exploit how the manipulator reacted to the constraint. In this study, the diameter of the cylindrical space was shrunken each time by 0.1 meters. The value of the cost function and …

Go to article

Optimization Scheme Of Average Time For Finding Idle Channel In Cognitive Radio System, Qiao Pei, Liyuan Xiao, Yanyan Han, Gao Ling Jul 2020

Optimization Scheme Of Average Time For Finding Idle Channel In Cognitive Radio System, Qiao Pei, Liyuan Xiao, Yanyan Han, Gao Ling

Journal of System Simulation

Abstract: In cognitive radio system, periodic spectrum sensing was taken by secondary users to prevent the interference to primary users. Supposed that there are many primary user channels, when the current primary user occupies channel, secondary users do spectrum handover. During spectrum handover, the time of finding an idle channel is a random variable. In order to speed up spectrum handover, the system used equal gain combining cooperative spectrum sensing to inspect an idle channel. This pattern optimized the sensing time of the single user channel, in order to get the best effect of the average time in finding idle …

Go to article

Big Data, Spatial Optimization, And Planning, Kai Cao, Wenwen Li, Richard Church Jul 2020

Big Data, Spatial Optimization, And Planning, Kai Cao, Wenwen Li, Richard Church

Research Collection School Of Computing and Information Systems

Spatial optimization represents a set of powerful spatial analysis techniques that can be used to identify optimal solution(s) and even generate a large number of competitive alternatives. The formulation of such problems involves maximizing or minimizing one or more objectives while satisfying a number of constraints. Solution techniques range from exact models solved with such approaches as linear programming and integer programming, or heuristic algorithms, i.e. Tabu Search, Simulated Annealing, and Genetic Algorithms. Spatial optimization techniques have been utilized in numerous planning applications, such as location-allocation modeling/site selection, land use planning, school districting, regionalization, routing, and urban design. These methods …

Go to article

Parameters Optimization For Variable Speed And Pitch Controller Of Wind Turbine Based On Bladed, Gao Feng, Wang Wei, Xinmei Ling Jun 2020

Parameters Optimization For Variable Speed And Pitch Controller Of Wind Turbine Based On Bladed, Gao Feng, Wang Wei, Xinmei Ling

Journal of System Simulation

Abstract: Due to nonlinearity and time-varying parameters of wind power system, its controller parameters are hard to be calculated and tuned during the process of design and optimization. The linear model which is suitable for parameters tuning was built through model linearization of Bladed and model reducing-order algorithm. The PI parameter was tuned with the IM-PSO (Immune Memory Particle Swarm Optimization). Moreover, the gain coefficient of optimal torque control and the gain divisor of adaptive PI pitch control conducted optimizing calculation based on the identification parameters of Bladed. A set of optimization method for variable speed and pitch controller …

Go to article

Real-Time Control Method Of Hsss Based On Single Phrase Self Decoupling Strategy, Yingping Yi, Bogang Qu, Zhang Yang Jun 2020

Real-Time Control Method Of Hsss Based On Single Phrase Self Decoupling Strategy, Yingping Yi, Bogang Qu, Zhang Yang

Journal of System Simulation

Abstract: Zero Crossing Detection (ZCD) and phase locked loop are widely applied in the real-time control. Compared the performances of ZCD, SSRF SPLL and DDSRF SPLL,a method named as Single Phase Self Decoupling SPLL (SPSD SPLL) for HSSS(Hybrid Solid State Switch) is proposed and the mathematical method and control methods are given. The control parameters were obtained by analyzing the steady and dynamic performance of SPSD SPLL. By establishing the real-time controlling models based on the above strategies and HSSS model in the MATLAB/Simulink, the simulation and optimization analysis results verified that the SPSD SPLL was well performed …

Go to article

Scheduling Problem Of Unidirectional Material Handling System With Short-Cut, Juntao Li, Kun Xia, Kise Hiroshi Jun 2020

Scheduling Problem Of Unidirectional Material Handling System With Short-Cut, Juntao Li, Kun Xia, Kise Hiroshi

Journal of System Simulation

Abstract: Unidirectional circulation-type material handling system on a single loop with a shortcut is a typical and basic unit in a flexible manufacturing system or logistics system. It is widely used in semiconductor wafer fabrication system. Superposition efficiency of the basic unit often determines the one of the whole system. Different scheduling rules impact the interference between AGVs and then have an important effect on the efficiency of the whole system. To decrease the interference and improve performance of the system, a mathematical model of this system was made, analyzing this system by simulation and comparing the merits and …

Go to article

Study On Vacuum Dehydration Rate From Oil Based On T_S Fuzzy Identifying Model, Liu Ge, Bin Chen, Xianming Zhang Jun 2020

Study On Vacuum Dehydration Rate From Oil Based On T_S Fuzzy Identifying Model, Liu Ge, Bin Chen, Xianming Zhang

Journal of System Simulation

Abstract: The process of vacuum dehydration from oil is time-varying, nonlinear, and difficult to be specified with mathematical methods. Takagi-Sugeno (T_S) fuzzy model of vacuum dehydration rate of oil purifier is proposed, which a method of applying Fuzzy C-Means (FCM) clustering algorithm and using the least square method identifying the consequent parameters. The nonlinear mapping is set up from four influence factors (the initial water content, the vacuum pressure , the initial temperature and running time) to vacuum dehydration rate using the T_S fuzzy model. The simulation and experimental results show the T_S model reflects the laws of the influences …

Go to article

Improved Particle Swarm Optimization Based On Lévy Flights, Rongyu Li, Wang Ying Jun 2020

Improved Particle Swarm Optimization Based On Lévy Flights, Rongyu Li, Wang Ying

Journal of System Simulation

Abstract: The particle swarm optimization (PSO) has some demerits, such as relapsing into local extremum, slow convergence velocity and low convergence precision in the late evolutionary. The Lévy particle swarm optimization (Lévy PSO) was proposed. In the particle position updating formula, Lévy PSO eliminated the impact of speed on the convergence rate, and used Levy flight to change the direction of particle positions movement to prevent particles getting into local optimum value, and then using greedy strategy to update the evaluation and choose the best solution to obtain the global optimum. The experimental results show that Lévy PSO can effectively …

Go to article

Goods Consumed During Transit In Split Delivery Vehicle Routing Problems: Modeling And Solution, Wenzhe Yang, Di Wang, Wei Pang, Ah-Hwee Tan, You Zhou Jun 2020

Goods Consumed During Transit In Split Delivery Vehicle Routing Problems: Modeling And Solution, Wenzhe Yang, Di Wang, Wei Pang, Ah-Hwee Tan, You Zhou

Research Collection School Of Computing and Information Systems

This article presents the modeling and solution of an extended type of split delivery vehicle routing problem (SDVRP). In SDVRP, the demands of customers need to be met by efficiently routing a given number of capacitated vehicles, wherein each customer may be served multiple times by more than one vehicle. Furthermore, in many real-world scenarios, consumption of vehicles en route is the same as the goods being delivered to customers, such as food, water and fuel in rescue or replenishment missions in harsh environments. Moreover, the consumption may also be in virtual forms, such as time spent in constrained tasks. …

Go to article

Adaptive Loss-Aware Quantization For Multi-Bit Networks, Zhongnan Qu, Zimu Zhou, Yun Cheng, Lothar Thiele Jun 2020

Adaptive Loss-Aware Quantization For Multi-Bit Networks, Zhongnan Qu, Zimu Zhou, Yun Cheng, Lothar Thiele

Research Collection School Of Computing and Information Systems

We investigate the compression of deep neural networks by quantizing their weights and activations into multiple binary bases, known as multi-bit networks (MBNs), which accelerate the inference and reduce the storage for the deployment on low-resource mobile and embedded platforms. We propose Adaptive Loss-aware Quantization (ALQ), a new MBN quantization pipeline that is able to achieve an average bitwidth below one-bit without notable loss in inference accuracy. Unlike previous MBN quantization solutions that train a quantizer by minimizing the error to reconstruct full precision weights, ALQ directly minimizes the quantizationinduced error on the loss function involving neither gradient approximation nor …

Go to article

First Prev Next Last