INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
A common practice to gain invariant features in object recognition models is to aggregate multiple low-level features over a small neighbourhood. However, the differences between those models make a comparison of the properties of different aggregation functions hard. Our aim is to predict the Handwritten Digit by training MNIST handwritten digit dataset by Convolutional Neural Network and Comparing the Accuracy, Loss, Validation Accuracy, Validation Loss, Time taken, Test data Accuracy with Confusion Matrix of MaxPooling2D, GlobalAveragePooling2D, AveragePooling2D layers in our CNN model. Empirical results show that a maximum pooling operation significantly outperforms subsampling operations. we achieve 0.5-0.7 % error in maximum pooling layer and 1-0.7 % error in Average Pooling layer while 8-9% error in Global Average Pooling Layer.
While entire models have been extensively compared, there has been no research evaluating the choice of the aggregation function so far. The aim of our work is therefore to empirically determine which of the established aggregation functions is more suitable for vision tasks. Additionally, we investigate if ideas from signal processing, such as overlapping receptive fields and window functions can improve recognition performance.
Keywords:
tf – Tensorflow, cnn – Convolutional Neural Network, nn – Neural Network, mnist – Modified National Institute of Standards and Technology database
Cite Article:
"Predict Handwritten digit with CNN and Compare types of Pooling Layers", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.7, Issue 1, page no.1-5, January-2022, Available :http://www.ijnrd.org/papers/IJNRD2201001.pdf
Downloads:
000118755
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn