Large and Deep Convolutional Neural Networks achieve good results in image classification tasks, but they need methods to prevent overfitting. In this paper we compare performance of different regularization techniques on ImageNet Large Scale Visual Recognition Challenge 2013. We show empirically that Dropout works better than DropConnect on ImageNet dataset.
AASRI Procedia Template
Write in a clean editor, then format for AASRI Procedia in one click — DocuGuru applies the official Elsevier template with numbered references and exports a submission-ready PDF plus the editable LaTeX source. Free to start.
About the AASRI Procedia format
AASRI Procedia is a peer-reviewed journal published by Elsevier, covering Video Surveillance and Tracking Methods, Advanced Computational Techniques and Applications, Energy Efficient Wireless Sensor Networks.
| Publisher | Elsevier |
|---|---|
| Reference style | Numbered (Elsevier) Numbered — [1], [2] in the text [1] A. Smith, B. Jones, C. Lee, A representative article title, AASRI Procedia 12 (2023) 45–58.
Formats any DOI in AASRI Procedia style. No sign-up. |
| Publishes research in | Video Surveillance and Tracking Methods Advanced Computational Techniques and Applications Energy Efficient Wireless Sensor Networks Advanced Measurement and Detection Methods Advanced Image and Video Retrieval Techniques |
| ISSN | 2212-6716 |
| h-index | 26 |
| i10-index | 100 |
| Total citations | 3,868 |
| Top institutions publishing here | North China Electric Power University |
| Journal website | www.sciencedirect.com |
| You get | A submission-ready PDF and the editable LaTeX source — ready to submit. |
Papers published in AASRI Procedia per year
Citation impact of AASRI Procedia by publication year
Citations each year’s papers have accumulated so far — the most recent years are still building up.
Most-cited papers in AASRI Procedia
Radio Frequency Identification RFID is a non-contact automatic identification technology, which signals through radio frequency automatic identification and access to relevant target data, no need for manual intervention to identify job can work in a variety of harsh environment. Because the logistics in the production control flow with information not to match, more and more…
In Genetic Algorithm, the population size is an important parameter which directly influences the ability to search an optimum solution in the search space. Many researchers have revealed that having a large number of population leads to the accuracy of getting an optimal solution. But having a large population size will not be a good…
Robust and automatic thresholding of gray level images has been commonly used in the field of pattern recognition and computer vision for objects detecting, tracking and recognizing. The Otsu scheme, a widely used image thresholding technique, provides approving results for segmenting a gray level image with only one modal distribution in gray level histogram. However,…
This paper presents a factorial analysis on the tensile strength of a coir-based composite. Three interested parameters in this study are fiber volume fraction, curing time and compression load applied during fabrication of the composite. The experimental setting is based on the full-factorial design of experiments, which amounts to a total of 18 tensile test…