深度多模態神經網路──應用於少量樣本數的高效能機器學習模型;Deep Multimodal Neural Network: A Highly Efficient Machine Learning Model Applicable to Low Sample Numbers

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Computer Science and Information Engineering > Electronic Thesis & Dissertation > Item 987654321/81093

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/81093

Title:	深度多模態神經網路──應用於少量樣本數的高效能機器學習模型;Deep Multimodal Neural Network: A Highly Efficient Machine Learning Model Applicable to Low Sample Numbers
Authors:	張哲維;Chang, Che-Wei
Contributors:	資訊工程學系
Keywords:	深度學習;神經網路;視覺檢測;種子辨識;特徵縮減;多模態;deep learning;neural network;vision inspection;seed recognition;feature reduction;multimodal
Date:	2019-07-18
Issue Date:	2019-09-03 15:34:15 (UTC+8)
Publisher:	國立中央大學
Abstract:	在醫療、工業及生物識別等許多不易取得大量數據的領域中，如何利用少量數據來進行有效的深度神經網路訓練，以完成分類任務，一直是欲克服的難題，而神經網路的可解釋性，同樣是相當重要的議題。現有的相關研究雖然能利用少樣本進行學習來達到有效的辨識，但要即時完成辨識任務，所消耗的功率、運算資源及硬體成本非常高，也存在著許多優化問題，並且缺乏可解釋性與良好的收斂性。因此本論文提出泛用且可解釋的深度多模態神經網路，以色彩、紋理和形狀做為主要特徵，利用統計與量化的方式，層層萃取出精簡且具鑑別性的多模態特徵，最後利用特徵間的互補性做出正確的分類決策。深度多模態神經網路使用基因演算法進行參數最佳化，以提升辨識率與實現增量學習。實驗結果深度多模態神經網路在少樣本多分類的辨識率高於淺層卷積神經網路12%，並且高於ResNet50 9.33%，而學習速度與運行速度也遠快於兩者，參數使用數量與模型大小則遠小於兩者，並且展現了相當優異的收斂性。深度多模態神經網路能夠實現於硬體資源有限且需要即時運行的嵌入式系統中，達到高速、即時、低功耗、低成本的目的。;In healthcare, industrial, and biometrics fields where obtaining a large amount of data is difficult, how to perform classification through deep learning using neural networks and a limited amount of data has become a problem remaining to be resolved. The interpretability of a neural network is another imperative topic. Previous studies have achieved effective recognition through machine learning using a small amount of data. However, real-time recognition still requires a large amount of power and computation resources as well as expensive hardware. Various problems concerning optimization also exist. In addition, such recognition processes result in undesirable interpretability and convergence. Therefore, this study proposed a widely applicable and interpretable deep multimodal neural network. Colors, textures, and shapes were used as the main features, and statistical and quantization methods were adopted to extract simple and identifiable multimodal features. Finally, the complementary characteristics of the extracted features were employed to perform classification. A genetic algorithm was used to optimize the parameters used in the deep multimodal neural network and therefore improve the recognition accuracy and achieve incremental learning. The experimental results revealed that when a small number of samples was used, the recognition rate of the deep multimodal neural network exceeded that of a shallow convolutional neural network by 12% and that of ResNet50 by 9.33%. Moreover, the deep multimodal neural network also exhibited faster learning and computation speeds than did these two networks, in addition to demonstrating excellent convergence. Deep multimodal neural networks can be applied to embedded systems with limited hardware resources that require real-time operations, thereby achieving the goals of high computation speed, instantaneity, low energy consumption, and low costs.
Appears in Collections:	[Graduate Institute of Computer Science and Information Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	194	View/Open

社群 sharing

Loading...