Log in

Relevant bibliographies by topics / Gradient learning algorithm / Journal articles

To see the other types of publications on this topic, follow the link: Gradient learning algorithm.

Journal articles on the topic 'Gradient learning algorithm'

Author: Grafiati

Published: 30 May 2022

Last updated: 31 July 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the top 50 journal articles for your research on the topic 'Gradient learning algorithm.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.

1

Jiao, Xianqi, Jia Liu, and Zhiping Chen. "Learning Complexity of Gradient Descent and Conjugate Gradient Algorithms." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 17 (2025): 17671–79. https://doi.org/10.1609/aaai.v39i17.33943.

Full text

Abstract:

Gradient Descent (GD) and Conjugate Gradient (CG) methods are among the most effective iterative algorithms for solving unconstrained optimization problems, particularly in machine learning and statistical modeling, where they are employed to minimize cost functions. In these algorithms, tunable parameters, such as step sizes or conjugate parameters, play a crucial role in determining key performance metrics, like runtime and solution quality. In this work, we introduce a framework that models algorithm selection as a statistical learning problem, and thus learning complexity can be estimated

APA, Harvard, Vancouver, ISO, and other styles

2

Dong, Xuemei, and Ding-Xuan Zhou. "Learning gradients by a gradient descent algorithm." Journal of Mathematical Analysis and Applications 341, no. 2 (2008): 1018–27. http://dx.doi.org/10.1016/j.jmaa.2007.10.044.

Full text

APA, Harvard, Vancouver, ISO, and other styles

3

Cai, Qingpeng, Ling Pan, and Pingzhong Tang. "Deterministic Value-Policy Gradients." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (2020): 3316–23. http://dx.doi.org/10.1609/aaai.v34i04.5732.

Full text

Abstract:

Reinforcement learning algorithms such as the deep deterministic policy gradient algorithm (DDPG) has been widely used in continuous control tasks. However, the model-free DDPG algorithm suffers from high sample complexity. In this paper we consider the deterministic value gradients to improve the sample efficiency of deep reinforcement learning algorithms. Previous works consider deterministic value gradients with the finite horizon, but it is too myopic compared with infinite horizon. We firstly give a theoretical guarantee of the existence of the value gradients in this infinite setting. Ba

APA, Harvard, Vancouver, ISO, and other styles

4

Kim, Kwang In. "Robust Distributed Gradient Aggregation Using Projections onto Gradient Manifolds." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 12 (2024): 13151–59. http://dx.doi.org/10.1609/aaai.v38i12.29214.

Full text

Abstract:

We study the distributed gradient aggregation problem where individual clients contribute to learning a central model by sharing parameter gradients constructed from local losses. However, errors in some gradients, caused by low-quality data or adversaries, can degrade the learning process when naively combined. Existing robust gradient aggregation approaches assume that local data represent the global data-generating distribution, which may not always apply to heterogeneous (non-i.i.d.) client data. We propose a new algorithm that can robustly aggregate gradients from potentially heterogeneou

APA, Harvard, Vancouver, ISO, and other styles

5

Li, Zhihao, Qingtao Wu, Moli Zhang, Lin Wang, Youming Ge, and Guoyong Wang. "Stochastic Zeroth-Order Multi-Gradient Algorithm for Multi-Objective Optimization." Mathematics 13, no. 4 (2025): 627. https://doi.org/10.3390/math13040627.

Full text

Abstract:

Multi-objective optimization (MOO) has become an important method in machine learning, which involves solving multiple competing objective problems simultaneously. Nowadays, many MOO algorithms assume that gradient information is easily available and use this information to optimize functions. However, when encountering situations where gradients are not available, such as black-box functions or non-differentiable functions, these algorithms become ineffective. In this paper, we propose a zeroth-order MOO algorithm named SZMG (stochastic zeroth-order multi-gradient algorithm), which approximat

APA, Harvard, Vancouver, ISO, and other styles

6

Note, Johan, and Maaruf Ali. "Comparative Analysis of Intrusion Detection System Using Machine Learning and Deep Learning Algorithms." Annals of Emerging Technologies in Computing 6, no. 3 (2022): 19–36. http://dx.doi.org/10.33166/aetic.2022.03.003.

Full text

Abstract:

Attacks against computer networks, “cyber-attacks”, are now common place affecting almost every Internet connected device on a daily basis. Organisations are now using machine learning and deep learning to thwart these types of attacks for their effectiveness without the need for human intervention. Machine learning offers the biggest advantage in their ability to detect, curtail, prevent, recover and even deal with untrained types of attacks without being explicitly programmed. This research will show the many different types of algorithms that are employed to fight against the different type

APA, Harvard, Vancouver, ISO, and other styles

7

Liu, Zhipeng, Rui Feng, Xiuhan Li, Wei Wang, and Xiaoling Wu. "Gradient-Sensitive Optimization for Convolutional Neural Networks." Computational Intelligence and Neuroscience 2021 (March 22, 2021): 1–16. http://dx.doi.org/10.1155/2021/6671830.

Full text

Abstract:

Convolutional neural networks (CNNs) are effective models for image classification and recognition. Gradient descent optimization (GD) is the basic algorithm for CNN model optimization. Since GD appeared, a series of improved algorithms have been derived. Among these algorithms, adaptive moment estimation (Adam) has been widely recognized. However, local changes are ignored in Adam to some extent. In this paper, we introduce an adaptive learning rate factor based on current and recent gradients. According to this factor, we can dynamically adjust the learning rate of each independent parameter

APA, Harvard, Vancouver, ISO, and other styles

8

Iiduka, Hideaki, and Yu Kobayashi. "Training Deep Neural Networks Using Conjugate Gradient-like Methods." Electronics 9, no. 11 (2020): 1809. http://dx.doi.org/10.3390/electronics9111809.

Full text

Abstract:

The goal of this article is to train deep neural networks that accelerate useful adaptive learning rate optimization algorithms such as AdaGrad, RMSProp, Adam, and AMSGrad. To reach this goal, we devise an iterative algorithm combining the existing adaptive learning rate optimization algorithms with conjugate gradient-like methods, which are useful for constrained optimization. Convergence analyses show that the proposed algorithm with a small constant learning rate approximates a stationary point of a nonconvex optimization problem in deep learning. Furthermore, it is shown that the proposed

APA, Harvard, Vancouver, ISO, and other styles

9

Zhang, Jianfei, and Zhilin Liu. "PerFreezeClip: Personalized Federated Learning Based on Adaptive Clipping." Electronics 13, no. 14 (2024): 2739. http://dx.doi.org/10.3390/electronics13142739.

Full text

Abstract:

The problem of data heterogeneity is one of the main challenges facing federated learning (FL). Non-IID data usually introduce bias in the training process of FL models, which can impact the accuracy and convergence speed of the models. To this end, we propose a personalized federated learning (PFL) algorithm with adaptive dynamic adjustment of the gradient clipping boundaries and the idea of freezing to reduce the influence of non-IID data on the model, called PerFreezeClip. PerFreezeClip is a design decision regarding parameter architecture, comparing the private and federated models. PerFre

APA, Harvard, Vancouver, ISO, and other styles

10

Zhang, Baoquan, Chuyao Luo, Demin Yu, et al. "MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 15 (2024): 16687–95. http://dx.doi.org/10.1609/aaai.v38i15.29608.

Full text

Abstract:

Equipping a deep model the ability of few-shot learning (FSL) is a core challenge for artificial intelligence. Gradient-based meta-learning effectively addresses the challenge by learning how to learn novel tasks. Its key idea is learning a deep model in a bi-level optimization manner, where the outer-loop process learns a shared gradient descent algorithm (called meta-optimizer), while the inner-loop process leverages it to optimize a task-specific base learner with few examples. Although these methods have shown superior performance on FSL, the outer-loop process requires calculating second-

APA, Harvard, Vancouver, ISO, and other styles

11

Bastian, Michael R., Jacob H. Gunther, and Todd K. Moon. "A Simplified Natural Gradient Learning Algorithm." Advances in Artificial Neural Systems 2011 (July 24, 2011): 1–9. http://dx.doi.org/10.1155/2011/407497.

Full text

Abstract:

Adaptive natural gradient learning avoids singularities in the parameter space of multilayer perceptrons. However, it requires a larger number of additional parameters than ordinary backpropagation in the form of the Fisher information matrix. This paper describes a new approach to natural gradient learning that uses a smaller Fisher information matrix. It also uses a prior distribution on the neural network parameters and an annealed learning rate. While this new approach is computationally simpler, its performance is comparable to that of adaptive natural gradient learning.

APA, Harvard, Vancouver, ISO, and other styles

12

Banakar, Ahmad. "Lyapunov Stability Analysis of Gradient Descent-Learning Algorithm in Network Training." ISRN Applied Mathematics 2011 (July 5, 2011): 1–12. http://dx.doi.org/10.5402/2011/145801.

Full text

Abstract:

The Lyapunov stability theorem is applied to guarantee the convergence and stability of the learning algorithm for several networks. Gradient descent learning algorithm and its developed algorithms are one of the most useful learning algorithms in developing the networks. To guarantee the stability and convergence of the learning process, the upper bound of the learning rates should be investigated. Here, the Lyapunov stability theorem was developed and applied to several networks in order to guaranty the stability of the learning algorithm.

APA, Harvard, Vancouver, ISO, and other styles

13

Mohan, B. R., Dileep M, Vijay Bhuria, Sai Sudha Gadde, Kumarasamy M, and Achyutha Prasad N. "Potable Water Identification with Machine Learning: An Exploration of Water Quality Parameters." International Journal on Recent and Innovation Trends in Computing and Communication 11, no. 3 (2023): 178–85. http://dx.doi.org/10.17762/ijritcc.v11i3.6333.

Full text

Abstract:

In this research, we aim to determine the water potability using three machine learning classification algorithms: decision tree, gradient boosting and bagging classifier. These algorithms were trained and tested on a dataset of water quality measurements. The outcomes of the experiment showed that the gradient boosting algorithm achieved the highest F1-score of 0.78 among all the algorithms. This indicates that the gradient boosting algorithm was most effective in correctly identifying both the safe and contaminated water samples. The results of this study demonstrate that gradient boosting i

APA, Harvard, Vancouver, ISO, and other styles

14

Yang, Yang, Lipo Mo, Yusen Hu, and Fei Long. "The Improved Stochastic Fractional Order Gradient Descent Algorithm." Fractal and Fractional 7, no. 8 (2023): 631. http://dx.doi.org/10.3390/fractalfract7080631.

Full text

Abstract:

This paper mainly proposes some improved stochastic gradient descent (SGD) algorithms with a fractional order gradient for the online optimization problem. For three scenarios, including standard learning rate, adaptive gradient learning rate, and momentum learning rate, three new SGD algorithms are designed combining a fractional order gradient and it is shown that the corresponding regret functions are convergent at a sub-linear rate. Then we discuss the impact of the fractional order on the convergence and monotonicity and prove that the better performance can be obtained by adjusting the o

APA, Harvard, Vancouver, ISO, and other styles

15

Zhang, Chongjie, and Victor Lesser. "Multi-Agent Learning with Policy Prediction." Proceedings of the AAAI Conference on Artificial Intelligence 24, no. 1 (2010): 927–34. http://dx.doi.org/10.1609/aaai.v24i1.7639.

Full text

Abstract:

Due to the non-stationary environment, learning in multi-agent systems is a challenging problem. This paper first introduces a new gradient-based learning algorithm, augmenting the basic gradient ascent approach with policy prediction. We prove that this augmentation results in a stronger notion of convergence than the basic gradient ascent, that is, strategies converge to a Nash equilibrium within a restricted class of iterated games. Motivated by this augmentation, we then propose a new practical multi-agent reinforcement learning (MARL) algorithm exploiting approximate policy prediction. Em

APA, Harvard, Vancouver, ISO, and other styles

16

Hosen, Md Saikat, and Ruhul Amin. "Significant of Gradient Boosting Algorithm in Data Management System." Engineering International 9, no. 2 (2021): 85–100. http://dx.doi.org/10.18034/ei.v9i2.559.

Full text

Abstract:

Gradient boosting machines, the learning process successively fits fresh prototypes to offer a more precise approximation of the response parameter. The principle notion associated with this algorithm is that a fresh base-learner construct to be extremely correlated with the “negative gradient of the loss function” related to the entire ensemble. The loss function's usefulness can be random, nonetheless, for a clearer understanding of this subject, if the “error function is the model squared-error loss”, then the learning process would end up in sequential error-fitting. This study is aimed at

APA, Harvard, Vancouver, ISO, and other styles

17

B.Meena, Preethi, R.Gowtham, S.Aishvarya, S.Karthick, and D.G.Sabareesh. "Rainfall Prediction using Machine Learning and Deep Learning Algorithms." International Journal of Recent Technology and Engineering (IJRTE) 10, no. 4 (2021): 251–54. https://doi.org/10.35940/ijrte.D6611.1110421.

Full text

Abstract:

he project entitled as “Rainfall Prediction using Machine Learning & Deep Learning Algorithms” is a research project which is developed in Python Language and dataset is stored in Microsoft Excel. This prediction uses various machine learning and deep learning algorithms to find which algorithm predicts with most accurately. Rainfall prediction can be achieved by using binary classification under Data Mining. Predicting the rainfall is very important in several aspects of one’s country and can help from preventing serious natural disasters. For this prediction, Artificial

APA, Harvard, Vancouver, ISO, and other styles

18

Xian, Wenhan, Feihu Huang, and Heng Huang. "Communication-Efficient Frank-Wolfe Algorithm for Nonconvex Decentralized Distributed Learning." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 12 (2021): 10405–13. http://dx.doi.org/10.1609/aaai.v35i12.17246.

Full text

Abstract:

Recently decentralized optimization attracts much attention in machine learning because it is more communication-efficient than the centralized fashion. Quantization is a promising method to reduce the communication cost via cutting down the budget of each single communication using the gradient compression. To further improve the communication efficiency, more recently, some quantized decentralized algorithms have been studied. However, the quantized decentralized algorithm for nonconvex constrained machine learning problems is still limited. Frank-Wolfe (a.k.a., conditional gradient or proje

APA, Harvard, Vancouver, ISO, and other styles

19

Zuo, Xuan, Hui-Yan Li, Shan Gao, Pu Zhang, and Wan-Ru Du. "NALA: a Nesterov accelerated look-ahead optimizer for deep learning." PeerJ Computer Science 10 (July 3, 2024): e2167. http://dx.doi.org/10.7717/peerj-cs.2167.

Full text

Abstract:

Adaptive gradient algorithms have been successfully used in deep learning. Previous work reveals that adaptive gradient algorithms mainly borrow the moving average idea of heavy ball acceleration to estimate the first- and second-order moments of the gradient for accelerating convergence. However, Nesterov acceleration which uses the gradient at extrapolation point can achieve a faster convergence speed than heavy ball acceleration in theory. In this article, a new optimization algorithm which combines adaptive gradient algorithm with Nesterov acceleration by using a look-ahead scheme, called

APA, Harvard, Vancouver, ISO, and other styles

20

Li, Qunwei, Shaofeng Zou, and Wenliang Zhong. "Learning Graph Neural Networks with Approximate Gradient Descent." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 10 (2021): 8438–46. http://dx.doi.org/10.1609/aaai.v35i10.17025.

Full text

Abstract:

The first provably efficient algorithm for learning graph neural networks (GNNs) with one hidden layer for node information convolution is provided in this paper. Two types of GNNs are investigated, depending on whether labels are attached to nodes or graphs. A comprehensive framework for designing and analyzing convergence of GNN training algorithms is developed. The algorithm proposed is applicable to a wide range of activation functions including ReLU, Leaky ReLU, Sigmod, Softplus and Swish. It is shown that the proposed algorithm guarantees a linear convergence rate to the underlying true

APA, Harvard, Vancouver, ISO, and other styles

21

Singarimbun, Roy Nuary, Ondra Eka Putra, N. L. W. S. R. Ginantra, and Mariana Puspa Dewi. "Backpropagation Artificial Neural Network Enhancement using Beale-Powell Approach Technique." Journal of Physics: Conference Series 2394, no. 1 (2022): 012007. http://dx.doi.org/10.1088/1742-6596/2394/1/012007.

Full text

Abstract:

Abstract Machine learning algorithms can study existing data to perform specific tasks. One of the well-known machine learning algorithms is the backpropagation algorithm, but this algorithm often provides poor convergence speed in the training process and a long training time. The purpose of this study is to optimize the standard backpropagation algorithm using the Beale-Powell conjugate gradient algorithm so that the training time needed to achieve convergence is not too long, which later can be used as a reference and information for solving predictive problems. The Beale-Powell conjugate g

APA, Harvard, Vancouver, ISO, and other styles

22

Sanapala, Lavanya, and Lakshmeeswari Gondi. "Mitigating Gradient-Based Data Poisoning Attacks on Machine Learning Models: A Statistical Detection Method." Indian Journal Of Science And Technology 17, no. 21 (2024): 2218–31. http://dx.doi.org/10.17485/ijst/v17i21.1035.

Full text

Abstract:

Objectives: This research paper aims to develop a novel method for identifying gradient-based data poisoning attacks on industrial applications like autonomous vehicles and intelligent healthcare systems relying on machine learning and deep learning techniques. These algorithms performs well only if they are trained on good quality dataset. However, the ML models are prone to data poisoning attacks, targeting the training dataset, manipulate its input samples such that the machine learning algorithm gets confused and produces wrong predictions. The current detection techniques are effective to

APA, Harvard, Vancouver, ISO, and other styles

23

Zhi-Chao Dou, Zhi-Chao Dou, Shu-Chuan Chu Zhi-Chao Dou, Zhongjie Zhuang Shu-Chuan Chu, Ali Riza Yildiz Zhongjie Zhuang, and Jeng-Shyang Pan Ali Riza Yildiz. "GBRUN: A Gradient Search-based Binary Runge Kutta Optimizer for Feature Selection." 網際網路技術學刊 25, no. 3 (2024): 341–53. http://dx.doi.org/10.53106/160792642024052503001.

Full text

Abstract:

<p>Feature selection (FS) is a pre-processing technique for data dimensionality reduction in machine learning and data mining algorithms. FS technique reduces the number of features and improves the model generalization ability. This study presents a Gradient Search-based Binary Runge Kutta Optimizer (GBRUN) for solving the FS problem of high-dimensional. First, the proposed method converts the continuous Runge Kutta optimizer (RUN) into a binary version through S-, V-, and U-shaped transfer functions. Second, a gradient search method is introduced to improve the exploration capability o

APA, Harvard, Vancouver, ISO, and other styles

24

Sun, Haijing, Ying Cai, Ran Tao, et al. "An Improved Reacceleration Optimization Algorithm Based on the Momentum Method for Image Recognition." Mathematics 12, no. 11 (2024): 1759. http://dx.doi.org/10.3390/math12111759.

Full text

Abstract:

The optimization algorithm plays a crucial role in image recognition by neural networks. However, it is challenging to accelerate the model’s convergence and maintain high precision. As a commonly used stochastic gradient descent optimization algorithm, the momentum method requires many epochs to find the optimal parameters during model training. The velocity of its gradient descent depends solely on the historical gradients and is not subject to random fluctuations. To address this issue, an optimization algorithm to enhance the gradient descent velocity, i.e., the momentum reacceleration gra

APA, Harvard, Vancouver, ISO, and other styles

25

Popov, Vladimir. "Particle Swarm Optimization Technique for DNA Sensor Model Based Nanostructured Graphene." Advanced Materials Research 936 (June 2014): 415–18. http://dx.doi.org/10.4028/www.scientific.net/amr.936.415.

Full text

Abstract:

DNA biosensors has received significant attention. In particular, we can mention the model of a graphene-based DNA sensor which is used for electrical detection of DNA molecules. In this paper, we consider a method of selection of PSO parameters for optimization of the analytical model of a graphene-based DNA sensor. In particular, we consider genetic algorithms, multilayer perceptron networks with gradient learning algorithm, recurrent neural networks with gradient learning algorithm, and 4-order Runge Kutta neural networks with different learning algorithms. Also, we present experimental res

APA, Harvard, Vancouver, ISO, and other styles

26

MØLLER, MARTIN. "SUPERVISED LEARNING ON LARGE REDUNDANT TRAINING SETS." International Journal of Neural Systems 04, no. 01 (1993): 15–25. http://dx.doi.org/10.1142/s0129065793000031.

Full text

Abstract:

Efficient supervised learning on large redundant training sets requires algorithms where the amount of computation involved in preparing each weight update is independent of the training set size. Off-line algorithms like the standard conjugate gradient algorithms do not have this property while on-line algorithms like the stochastic backpropagation algorithm do. A new algorithm combining the good properties of off-line and on-line algorithms is introduced.

APA, Harvard, Vancouver, ISO, and other styles

27

Le, Hung, Majid Abdolshah, Thommen K. George, Kien Do, Dung Nguyen, and Svetha Venkatesh. "Episodic Policy Gradient Training." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 7 (2022): 7317–25. http://dx.doi.org/10.1609/aaai.v36i7.20694.

Full text

Abstract:

We introduce a novel training procedure for policy gradient methods wherein episodic memory is used to optimize the hyperparameters of reinforcement learning algorithms on-the-fly. Unlike other hyperparameter searches, we formulate hyperparameter scheduling as a standard Markov Decision Process and use episodic memory to store the outcome of used hyperparameters and their training contexts. At any policy update step, the policy learner refers to the stored experiences, and adaptively reconfigures its learning algorithm with the new hyperparameters determined by the memory. This mechanism, dubb

APA, Harvard, Vancouver, ISO, and other styles

28

Huang, Feihu, Bin Gu, Zhouyuan Huo, Songcan Chen, and Heng Huang. "Faster Gradient-Free Proximal Stochastic Methods for Nonconvex Nonsmooth Optimization." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 1503–10. http://dx.doi.org/10.1609/aaai.v33i01.33011503.

Full text

Abstract:

Proximal gradient method has been playing an important role to solve many machine learning tasks, especially for the nonsmooth problems. However, in some machine learning problems such as the bandit model and the black-box learning problem, proximal gradient method could fail because the explicit gradients of these problems are difficult or infeasible to obtain. The gradient-free (zeroth-order) method can address these problems because only the objective function values are required in the optimization. Recently, the first zeroth-order proximal stochastic algorithm was proposed to solve the no

APA, Harvard, Vancouver, ISO, and other styles

29

Arif Ali, Zeravan, Ziyad H. Abduljabbar, Hanan A. Tahir, Amira Bibo Sallow, and Saman M. Almufti. "eXtreme Gradient Boosting Algorithm with Machine Learning: a Review." Academic Journal of Nawroz University 12, no. 2 (2023): 320–34. http://dx.doi.org/10.25007/ajnu.v12n2a1612.

Full text

Abstract:

The primary task of machine learning is to extract valuable information from the data that is generated every day, process it to learn from it, and take useful actions. Original language process, pattern detection, search engines, medical diagnostics, bioinformatics, and chemical informatics are all examples of application areas for machine learning. XGBoost is a recently released machine learning algorithm that has shown exceptional capability for modeling complex systems and is the most superior machine learning algorithm in terms of prediction accuracy and interpretability and classificatio

APA, Harvard, Vancouver, ISO, and other styles

30

Chu, Enming, Dengbo Li, and Yangfan Tong. "Optimized federated learning based on Adagrad algorithm and algorithm optimization." Applied and Computational Engineering 19, no. 1 (2023): 9–17. http://dx.doi.org/10.54254/2755-2721/19/20231000.

Full text

Abstract:

Federated learning allows you to train machine learning models without sharing your local data. Due to the No-iid problem, this paper is based on the Moon algorithm, which can have excellent performance in datasets of images with models that use deep learning and outperforms FedAvg, FedProx, and other algorithms, with the goal to decrease communication costs while enhancing efficiency more effectively. This study optimizes its gradient descent technique based on Moon's algorithm by utilizing Adaptive Gradient (AdaGrad) optimizer and combining with knowledge distillation to improve Moon's algor

APA, Harvard, Vancouver, ISO, and other styles

31

Popov, Vladimir. "Particle Swarm Optimization Technique for Task-Resource Scheduling for Robotic Clouds." Applied Mechanics and Materials 565 (June 2014): 243–46. http://dx.doi.org/10.4028/www.scientific.net/amm.565.243.

Full text

Abstract:

The task-resource scheduling problem is one of the fundamental problems for cloud computing. There are a large number of heuristics based approaches to various scheduling workflow applications. In this paper, we consider the problem for robotic clouds. We propose new method of selection of parameters of a particle swarm optimization algorithm for solution of the task-resource scheduling problem for robotic clouds. In particular, for the prediction of values of the inertia weight we consider genetic algorithms, multilayer perceptron networks with gradient learning algorithm, recurrent neural ne

APA, Harvard, Vancouver, ISO, and other styles

32

Jinan, Abwabul, Zakarias Situmorang, and Rika Rosnelly. "Bulldog Breed Classification Using VGG-19 and Ensemble Learning." International Conference on Information Science and Technology Innovation (ICoSTEC) 2, no. 1 (2023): 29–33. http://dx.doi.org/10.35842/icostec.v2i1.32.

Full text

Abstract:

In image classification, the C4.5, Adaboost, and Gradient Boosting algorithms need another method to extract the image's features in the classification process. This research employs transfer learning with the VGG-19 network for the image's features extraction and transfers the result as a dataset to classify image-based Bulldog breeds. As the classifier to classify the extracted features from the VGG 16 model, we employ three ensemble learning algorithms, namely C4.5, AdaBoost, and Gradient Boost. The training data classification results of the American, English, and French bulldog breeds sho

APA, Harvard, Vancouver, ISO, and other styles

33

Luo, Zhikun, Huafei Sun, and Xiaomin Duan. "The Extended Hamiltonian Algorithm for the Solution of the Algebraic Riccati Equation." Journal of Applied Mathematics 2014 (2014): 1–8. http://dx.doi.org/10.1155/2014/693659.

Full text

Abstract:

We use a second-order learning algorithm for numerically solving a class of the algebraic Riccati equations. Specifically, the extended Hamiltonian algorithm based on manifold of positive definite symmetric matrices is provided. Furthermore, this algorithm is compared with the Euclidean gradient algorithm, the Riemannian gradient algorithm, and the new subspace iteration method. Simulation examples show that the convergence speed of the extended Hamiltonian algorithm is the fastest one among these algorithms.

APA, Harvard, Vancouver, ISO, and other styles

34

Syed Shahul Hameed, A., and Narendran Rajagopalan. "SPGD: Search Party Gradient Descent Algorithm, a Simple Gradient-Based Parallel Algorithm for Bound-Constrained Optimization." Mathematics 10, no. 5 (2022): 800. http://dx.doi.org/10.3390/math10050800.

Full text

Abstract:

Nature-inspired metaheuristic algorithms remain a strong trend in optimization. Human-inspired optimization algorithms should be more intuitive and relatable. This paper proposes a novel optimization algorithm inspired by a human search party. We hypothesize the behavioral model of a search party searching for a treasure. Motivated by the search party’s behavior, we abstract the “Divide, Conquer, Assemble” (DCA) approach. The DCA approach allows us to parallelize the traditional gradient descent algorithm in a strikingly simple manner. Essentially, multiple gradient descent instances with diff

APA, Harvard, Vancouver, ISO, and other styles

35

Amari, Shun-ichi. "Natural Gradient Works Efficiently in Learning." Neural Computation 10, no. 2 (1998): 251–76. http://dx.doi.org/10.1162/089976698300017746.

Full text

Abstract:

When a parameter space has a certain underlying structure, the ordinary gradient of a function does not represent its steepest direction, but the natural gradient does. Information geometry is used for calculating the natural gradients in the parameter space of perceptrons, the space of matrices (for blind source separation), and the space of linear dynamical systems (for blind source deconvolution). The dynamical behavior of natural gradient online learning is analyzed and is proved to be Fisher efficient, implying that it has asymptotically the same performance as the optimal batch estimatio

APA, Harvard, Vancouver, ISO, and other styles

36

Liu, Bo, Ian Gemp, Mohammad Ghavamzadeh, Ji Liu, Sridhar Mahadevan, and Marek Petrik. "Proximal Gradient Temporal Difference Learning: Stable Reinforcement Learning with Polynomial Sample Complexity." Journal of Artificial Intelligence Research 63 (November 15, 2018): 461–94. http://dx.doi.org/10.1613/jair.1.11251.

Full text

Abstract:

   In this paper, we introduce proximal gradient temporal difference learning, which provides a principled way of designing and analyzing true stochastic gradient temporal difference learning algorithms. We show how gradient TD (GTD) reinforcement learning methods can be formally derived, not by starting from their original objective functions, as previously attempted, but rather from a primal-dual saddle-point objective function. We also conduct a saddle-point error analysis to obtain finite-sample bounds on their performance. Previous analyses of this class of algorithms us

APA, Harvard, Vancouver, ISO, and other styles

37

Zhu, Yancheng, Qiwei Wu, and Jianzi Liu. "A Comparative Study of Contrastive Learning-Based Few-Shot Unsupervised Algorithms for Efficient Deep Learning." Journal of Physics: Conference Series 2560, no. 1 (2023): 012048. http://dx.doi.org/10.1088/1742-6596/2560/1/012048.

Full text

Abstract:

Abstract The rapid development in computer vision algorithms, particularly in target detection algorithms based on deep neural networks, has led to significant advancements in various fields. However, recent research on target detection algorithms has shifted towards small sample scenarios with long-tailed distribution of categories, where achieving high accuracy target detection with limited data has become a crucial research topic. Deep neural networks often face several challenges when dealing with limited data, including convergence problems, overfitting, and poor generalization performanc

APA, Harvard, Vancouver, ISO, and other styles

38

Liu, Jian, and Liming Feng. "Diversity Evolutionary Policy Deep Reinforcement Learning." Computational Intelligence and Neuroscience 2021 (August 3, 2021): 1–11. http://dx.doi.org/10.1155/2021/5300189.

Full text

Abstract:

The reinforcement learning algorithms based on policy gradient may fall into local optimal due to gradient disappearance during the update process, which in turn affects the exploration ability of the reinforcement learning agent. In order to solve the above problem, in this paper, the cross-entropy method (CEM) in evolution policy, maximum mean difference (MMD), and twin delayed deep deterministic policy gradient algorithm (TD3) are combined to propose a diversity evolutionary policy deep reinforcement learning (DEPRL) algorithm. By using the maximum mean discrepancy as a measure of the dista

APA, Harvard, Vancouver, ISO, and other styles

39

Lu, Yanbo, Huimin Gao, Yi Zhang, and Yong Xu. "FAFedZO: Faster Zero-Order Adaptive Federated Learning Algorithm." Electronics 14, no. 7 (2025): 1452. https://doi.org/10.3390/electronics14071452.

Full text

Abstract:

Federated learning represents a newly emerging methodology in the field of machine learning that enables distributed agents to collaboratively learn a centralized model without sharing their raw data. Some scholars have already proposed many first-order algorithms and second-order algorithms for federated learning to reduce communication costs and speed up convergence. However, these algorithms generally rely on gradient or Hessian information, and we find it difficult to solve such federated optimization problems when the analytical expression of the loss function is not available, that is, w

APA, Harvard, Vancouver, ISO, and other styles

40

Zhou, Chengmin, Bingding Huang, and Pasi Fränti. "A review of motion planning algorithms for intelligent robots." Journal of Intelligent Manufacturing 33, no. 2 (2021): 387–424. http://dx.doi.org/10.1007/s10845-021-01867-z.

Full text

Abstract:

AbstractPrinciples of typical motion planning algorithms are investigated and analyzed in this paper. These algorithms include traditional planning algorithms, classical machine learning algorithms, optimal value reinforcement learning, and policy gradient reinforcement learning. Traditional planning algorithms investigated include graph search algorithms, sampling-based algorithms, interpolating curve algorithms, and reaction-based algorithms. Classical machine learning algorithms include multiclass support vector machine, long short-term memory, Monte-Carlo tree search and convolutional neur

APA, Harvard, Vancouver, ISO, and other styles

41

Arthur, C. K., V. A. Temeng, and Y. Y. Ziggah. "Performance Evaluation of Training Algorithms in Backpropagation Neural Network Approach to Blast-Induced Ground Vibration Prediction." Ghana Mining Journal 20, no. 1 (2020): 20–33. http://dx.doi.org/10.4314/gm.v20i1.3.

Full text

Abstract:

Abstract Backpropagation Neural Network (BPNN) is an artificial intelligence technique that has seen several applications in many fields of science and engineering. It is well-known that, the critical task in developing an effective and accurate BPNN model depends on an appropriate training algorithm, transfer function, number of hidden layers and number of hidden neurons. Despite the numerous contributing factors for the development of a BPNN model, training algorithm is key in achieving optimum BPNN model performance. This study is focused on evaluating and comparing the performance of

APA, Harvard, Vancouver, ISO, and other styles

42

Rudini, Edwin, and Ferda Ernawan. "Prediction of Alzheimer's Dementia Using Soft Voting Ensemble Learning with Machine Learning." IJACI : International Journal of Advanced Computing and Informatics 1, no. 1 (2025): 48–55. https://doi.org/10.71129/ijaci.v1.i1.pp48-55.

Full text

Abstract:

Alzheimer's dementia (AD) is a degenerative brain disease characterized by a decline in cognitive function and memory. Predicting AD is crucial for preventing the disease from becoming more severe. Machine learning algorithms can aid in the early prediction of AD. The aim of this study is to develop a predictive model with improved accuracy using ensemble learning methods and machine learning algorithms. The experiment used the Oasis Longitudinal dataset from Oasis Brains, which includes details of patients with and without AD. This study proposed a binary classification using an ensemble lear

APA, Harvard, Vancouver, ISO, and other styles

43

Zhang, Junzi, Jongho Kim, Brendan O'Donoghue, and Stephen Boyd. "Sample Efficient Reinforcement Learning with REINFORCE." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 12 (2021): 10887–95. http://dx.doi.org/10.1609/aaai.v35i12.17300.

Full text

Abstract:

Policy gradient methods are among the most effective methods for large-scale reinforcement learning, and their empirical success has prompted several works that develop the foundation of their global convergence theory. However, prior works have either required exact gradients or state-action visitation measure based mini-batch stochastic gradients with a diverging batch size, which limit their applicability in practical scenarios. In this paper, we consider classical policy gradient methods that compute an approximate gradient with a single trajectory or a fixed size mini-batch of trajectorie

APA, Harvard, Vancouver, ISO, and other styles

44

Li, Mingfeng. "Comprehensive Review of Backpropagation Neural Networks." Academic Journal of Science and Technology 9, no. 1 (2024): 150–54. http://dx.doi.org/10.54097/51y16r47.

Full text

Abstract:

The Backpropagation Neural Network (BPNN) is a deep learning model inspired by the biological neural network. Introduced in the 1980s, the BPNN quickly became a focal point in neural network research due to its outstanding learning capability and adaptability. The network structure consists of input, hidden, and output layers, and it optimizes weights through the backpropagation algorithm, widely applied in image recognition, speech processing, natural language processing, and more. The mathematical model of neurons describes the relationship between input and output, and the training process

APA, Harvard, Vancouver, ISO, and other styles

45

Vasquez-Jalpa, Carlos, Mariko Nakano, Martin Velasco-Villa, and Osvaldo Lopez-Garcia. "NRNH-AR: A Small Robotic Agent Using Tri-Fold Learning for Navigation and Obstacle Avoidance." Applied Sciences 15, no. 15 (2025): 8149. https://doi.org/10.3390/app15158149.

Full text

Abstract:

We propose a tri-fold learning algorithm, called Neuroevolution of Hybrid Neural Networks in a Robotic Agent (acronym in Spanish, NRNH-AR), based on deep reinforcement learning (DRL), with self-supervised learning (SSL) and unsupervised learning (USL) steps, specifically designed to be implemented in a small autonomous navigation robot capable of operating in constrained physical environments. The NRNH-AR algorithm is designed for a small physical robotic agent with limited resources. The proposed algorithm was evaluated in four critical aspects: computational cost, learning stability, require

APA, Harvard, Vancouver, ISO, and other styles

46

Atiyah, Oqbah Salim, and Saadi Hamad Thalij. "Evaluation of COVID-19 Cases based on Classification Algorithms in Machine Learning." Webology 19, no. 1 (2022): 4878–87. http://dx.doi.org/10.14704/web/v19i1/web19326.

Full text

Abstract:

COVID-19 has appeared in china, spread rapidly the world wide and caused with many injuries, deaths between humans. It is possible to avoid the spread of the disease or reduce its spread with the machine learning and the diagnostic techniques, where the use classification algorithms are one of the fundamental issues for prediction and decision-making to help of the early detection, diagnose COVID-19 cases and identify dangerous cases that need admit Intensive Care Unit to provide treatment in a timely manner. In this paper, we use the machine learning algorithms to classify the COVID-19 cases,

APA, Harvard, Vancouver, ISO, and other styles

47

Gasnikov, A. V., M. S. Alkousa, A. V. Lobanov, et al. "On Quasi-Convex Smooth Optimization Problems by a Comparison Oracle." Nelineinaya Dinamika 20, no. 5 (2024): 813–25. https://doi.org/10.20537/nd241211.

Full text

Abstract:

Frequently, when dealing with many machine learning models, optimization problems appear to be challenging due to a limited understanding of the constructions and characterizations of the objective functions in these problems. Therefore, major complications arise when dealing with first-order algorithms, in which gradient computations are challenging or even impossible in various scenarios. For this reason, we resort to derivative-free methods (zeroth-order methods). This paper is devoted to an approach to minimizing quasi-convex functions using a recently proposed (in [56]) comparison oracle

APA, Harvard, Vancouver, ISO, and other styles

48

Hou, Yueqi, Xiaolong Liang, Jiaqiang Zhang, Qisong Yang, Aiwu Yang, and Ning Wang. "Exploring the Use of Invalid Action Masking in Reinforcement Learning: A Comparative Study of On-Policy and Off-Policy Algorithms in Real-Time Strategy Games." Applied Sciences 13, no. 14 (2023): 8283. http://dx.doi.org/10.3390/app13148283.

Full text

Abstract:

Invalid action masking is a practical technique in deep reinforcement learning to prevent agents from taking invalid actions. Existing approaches rely on action masking during policy training and utilization. This study focuses on developing reinforcement learning algorithms that incorporate action masking during training but can be used without action masking during policy execution. The study begins by conducting a theoretical analysis to elucidate the distinction between naive policy gradient and invalid action policy gradient. Based on this analysis, we demonstrate that the naive policy gr

APA, Harvard, Vancouver, ISO, and other styles

49

Zhao, Changyuan, Hongyang Du, Guangyuan Liu, and Dusit Niyato. "Supervised Score-Based Modeling by Gradient Boosting." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 21 (2025): 22768–76. https://doi.org/10.1609/aaai.v39i21.34437.

Full text

Abstract:

Score-based generative models can effectively learn the distribution of data by estimating the gradient of the distribution. Due to the multi-step denoising characteristic, researchers have recently considered combining score-based generative models with the gradient boosting algorithm, a multi-step supervised learning algorithm, to solve supervised learning tasks. However, existing generative model algorithms are often limited by the stochastic nature of the models and the long inference time, impacting prediction performances. Therefore, we propose a Supervised Score-based Model (SSM), which

APA, Harvard, Vancouver, ISO, and other styles

50

Kaushalya, Dissanayak, and Gapar Md Johar Md. "Two-level boosting classifiers ensemble based on feature selection for heart disease prediction." Two-level boosting classifiers ensemble based on feature selection for heart disease prediction 32, no. 1 (2023): 381–91. https://doi.org/10.11591/ijeecs.v32.i1.pp381-391.

Full text

Abstract:

Heart disease is a prevalent global health concern, necessitating early detection to save lives. Machine learning has revolutionized medical research, prompting the investigation of boosting algorithms for heart disease prediction. This study employs three heart disease datasets from the University of California Irvine (UCI) repository: Cleveland, Statlog, and Long Beach, with 14 features each. Recursive feature elimination with a support vector machine (SVM) is utilized to identify significant features. Five boosting algorithms (gradient boosting algorithm (GB), adaptive boosting algorithms (

APA, Harvard, Vancouver, ISO, and other styles

We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!