基于極端學習機算法的學習_獨家原創(chuàng).doc
約30頁DOC格式手機打開展開
基于極端學習機算法的學習_獨家原創(chuàng),基于極端學習機算法的學習11900字自己原創(chuàng)的畢業(yè)論文，已經通過校內系統檢測，重復率低，僅在本站獨家出售，大家放心下載使用摘要 人工智能是一門邊沿學科，屬于自然科學、社會科學、技術科學三向的交叉學科。半個世紀以來，作為一門新興學科，人工智能一直在不停地發(fā)展，其涉及的學科越來越多，研究的范疇也越來越大，應用的領域也越來越...
內容介紹
此文檔由會員 小丑88 發(fā)布
基于極端學習機算法的學習
11900字
自己原創(chuàng)的畢業(yè)論文，已經通過校內系統檢測，重復率低，僅在本站獨家出售，大家放心下載使用
摘要 人工智能是一門邊沿學科，屬于自然科學、社會科學、技術科學三向的交叉學科。半個世紀以來，作為一門新興學科，人工智能一直在不停地發(fā)展，其涉及的學科越來越多，研究的范疇也越來越大，應用的領域也越來越廣。在其眾多學科中，機器學習的前饋神經網絡以及極端學習機算法便是本文要研究的內容。
通常，前饋神經網絡的學習速度遠遠慢于需求。這已經成為了在過去的幾十年里其應用的一個主要瓶頸?？赡艿膬蓚€關鍵原因是：1）較為緩慢的基于梯度的學習算法被廣泛用來訓練神經網絡，以及2）網絡中的所有參數都使用這種學習算法反復調整。因此，有學者提出了極端學習機（ELM）算法。ELM是一種簡單易用、有效的單隱層前饋神經網絡（SLFNs）學習算法，其本質在于隱層是不需要調整。理論上講，這種算法易于以極快的學習速度提供更好的泛化性能。
盡管ELM性能優(yōu)于前饋神經網絡，但依舊有著一些缺陷。為此，研究人員又提出了改進的ELM算法以彌補ELM的一些不足，例如增量極端學習機（I-ELM）、加強I-ELM（EI-ELM）、自適應增長極端學習機（AG-ELM）、基于微粒群算法改進的極端學習機（PSO-ELM）等等。實驗結果表明，PSO-ELM比ELM擁有更好的泛化性能，I-ELM、EI-ELM可以處理廣泛的神經元，AG-ELM有優(yōu)于ELM的逼近能力。本文對極端學習機及各種改進的極端學習機進行研究學習，并將其應用到sinc函數的回歸和UCI數據集中。
關鍵詞：人工智能；前饋神經網絡；極端學習機。
Learning based on ELM algorithms
Abstract Artificial intelligence is an edge discipline, which is an interdisciplinary course combining natural science, social science and technology science. As a new discipline, artificial intelligence has been developing for half a century. Meanwhile, more and more disciplines have been involved, larger and larger areas has been researched and wider and wider field has been applied. Among its large number of disciplines, feedforward neural networks of machine learning and the algorithms of extreme learning machine(ELM) are to be studied in this paper.
As usual, the learning speed of feedforward neural networks is in general far lower than required and it has been a major bottleneck in their applications for past decades. Two key reasons behind may be: 1) the slow gradient-based learning algorithms are extensively used to train neural networks, and 2) all the parameters of the networks are tuned iteratively by using such learning algorithms. Therefore, some scholars have proposed extreme learning machine algorithm. ELM is an easy-to-use and effective algorithm of single hidden-layer feedforward neural networks (SLFNs) and its essence is that the hidden-layers don’t need to be tuned.
Although ELM performs better than feedforward neural networks, it still has some drawbacks. To make up the drawbacks, the researchers also proposed some improved algorithms of ELM such as: incremental ELM(I-ELM), enhanced incremental ELM(EI-ELM), Extreme Learning Machine with Adaptive Growth of Hidden Nodes(AG-ELM), and Extreme Learning Machine with Particle Swarm Optimization(PSO-ELM) etc. Experimental results show that PSO-ELM has better generalization performance than ELM; I-ELM, EI-ELM can handle a wide range of neurons; AG-ELM has a better approximation ability than ELM. In this paper, we will learn ELM and various improved ELM, and apply them to the regression of the function sinc and the data sets of UCI.
Key words Artificial intelligence; feedforward neural networks; ELM; drawbacks.
目 錄
第一章 緒論 1
1.1 神經網絡的發(fā)展史 1
1.2 前饋神經網絡和BP算法 2
1.2.1 前饋神經網絡概述 2
1.2.2 BP算法 3
1.3 極端學習機ELM的提出 5
1.4 論文的結構安排 5
第二章 極端學習機（ELM）相關概念及其算法 6
2.1 極端學習機的學習理論 6
2.2 極端學習機 7
2.2.1 摩爾彭德羅斯廣義逆 7
2.2.2 極端學習機算法 8
2.2.3 極端學習機的優(yōu)缺點 10
第三章 ELM的改進算法 11
3.1 I-ELM 11
3.2 AG-ELM 12
3.3 PSO-ELM 14
3.3.1 微粒群算法（PSO） 14
3.3.2 PSO-ELM 15
第四章 極端學習機及其改進算法的應用 18
4.1 PSO-ELM的應用和UCI數據集的分類 18
4.1.1. PSO-ELM應用于SINC函數逼近 18
4.1.2 PSO的UCI數據集分類 19
4.2 ELM及其改進算法在UCI數據集上的應用 20
結論 24
致謝 25
參考文獻 26
11900字
自己原創(chuàng)的畢業(yè)論文，已經通過校內系統檢測，重復率低，僅在本站獨家出售，大家放心下載使用
摘要 人工智能是一門邊沿學科，屬于自然科學、社會科學、技術科學三向的交叉學科。半個世紀以來，作為一門新興學科，人工智能一直在不停地發(fā)展，其涉及的學科越來越多，研究的范疇也越來越大，應用的領域也越來越廣。在其眾多學科中，機器學習的前饋神經網絡以及極端學習機算法便是本文要研究的內容。
通常，前饋神經網絡的學習速度遠遠慢于需求。這已經成為了在過去的幾十年里其應用的一個主要瓶頸?？赡艿膬蓚€關鍵原因是：1）較為緩慢的基于梯度的學習算法被廣泛用來訓練神經網絡，以及2）網絡中的所有參數都使用這種學習算法反復調整。因此，有學者提出了極端學習機（ELM）算法。ELM是一種簡單易用、有效的單隱層前饋神經網絡（SLFNs）學習算法，其本質在于隱層是不需要調整。理論上講，這種算法易于以極快的學習速度提供更好的泛化性能。
盡管ELM性能優(yōu)于前饋神經網絡，但依舊有著一些缺陷。為此，研究人員又提出了改進的ELM算法以彌補ELM的一些不足，例如增量極端學習機（I-ELM）、加強I-ELM（EI-ELM）、自適應增長極端學習機（AG-ELM）、基于微粒群算法改進的極端學習機（PSO-ELM）等等。實驗結果表明，PSO-ELM比ELM擁有更好的泛化性能，I-ELM、EI-ELM可以處理廣泛的神經元，AG-ELM有優(yōu)于ELM的逼近能力。本文對極端學習機及各種改進的極端學習機進行研究學習，并將其應用到sinc函數的回歸和UCI數據集中。
關鍵詞：人工智能；前饋神經網絡；極端學習機。
Learning based on ELM algorithms
Abstract Artificial intelligence is an edge discipline, which is an interdisciplinary course combining natural science, social science and technology science. As a new discipline, artificial intelligence has been developing for half a century. Meanwhile, more and more disciplines have been involved, larger and larger areas has been researched and wider and wider field has been applied. Among its large number of disciplines, feedforward neural networks of machine learning and the algorithms of extreme learning machine(ELM) are to be studied in this paper.
As usual, the learning speed of feedforward neural networks is in general far lower than required and it has been a major bottleneck in their applications for past decades. Two key reasons behind may be: 1) the slow gradient-based learning algorithms are extensively used to train neural networks, and 2) all the parameters of the networks are tuned iteratively by using such learning algorithms. Therefore, some scholars have proposed extreme learning machine algorithm. ELM is an easy-to-use and effective algorithm of single hidden-layer feedforward neural networks (SLFNs) and its essence is that the hidden-layers don’t need to be tuned.
Although ELM performs better than feedforward neural networks, it still has some drawbacks. To make up the drawbacks, the researchers also proposed some improved algorithms of ELM such as: incremental ELM(I-ELM), enhanced incremental ELM(EI-ELM), Extreme Learning Machine with Adaptive Growth of Hidden Nodes(AG-ELM), and Extreme Learning Machine with Particle Swarm Optimization(PSO-ELM) etc. Experimental results show that PSO-ELM has better generalization performance than ELM; I-ELM, EI-ELM can handle a wide range of neurons; AG-ELM has a better approximation ability than ELM. In this paper, we will learn ELM and various improved ELM, and apply them to the regression of the function sinc and the data sets of UCI.
Key words Artificial intelligence; feedforward neural networks; ELM; drawbacks.
目 錄
第一章 緒論 1
1.1 神經網絡的發(fā)展史 1
1.2 前饋神經網絡和BP算法 2
1.2.1 前饋神經網絡概述 2
1.2.2 BP算法 3
1.3 極端學習機ELM的提出 5
1.4 論文的結構安排 5
第二章 極端學習機（ELM）相關概念及其算法 6
2.1 極端學習機的學習理論 6
2.2 極端學習機 7
2.2.1 摩爾彭德羅斯廣義逆 7
2.2.2 極端學習機算法 8
2.2.3 極端學習機的優(yōu)缺點 10
第三章 ELM的改進算法 11
3.1 I-ELM 11
3.2 AG-ELM 12
3.3 PSO-ELM 14
3.3.1 微粒群算法（PSO） 14
3.3.2 PSO-ELM 15
第四章 極端學習機及其改進算法的應用 18
4.1 PSO-ELM的應用和UCI數據集的分類 18
4.1.1. PSO-ELM應用于SINC函數逼近 18
4.1.2 PSO的UCI數據集分類 19
4.2 ELM及其改進算法在UCI數據集上的應用 20
結論 24
致謝 25
參考文獻 26
