Downloads: 118 | Weekly Hits: ⮙2
Research Paper | Computer Science & Engineering | India | Volume 6 Issue 8, August 2017
Evaluation of Convolutional Architectures for Offline Handwritten Digit Recognition
Amit Adate, Rishabh Saxena
Deep learning implementations have resulted in significant performance improvements in several application domains and as such several network architectures have been developed to facilitate their methods. This paper presents a comparative study of two architectures among those which are implemented for handwriting recognition, Highway CNN and LeNet-5. The evaluation is performed on two separate machines for both CPU (Intel-i5 3250M) and a GPU (Nvidia GTX-1060). We compared them not only on the basis of their accuracy, but also their training time, recognition time and their memory requirements. Our experiments demonstrate the advantage of global training and feature mapping on the MNIST dataset.
Keywords: CNN, Highway CNN, LeNet-5
Edition: Volume 6 Issue 8, August 2017
Pages: 1904 - 1907
How to Cite this Article?
Amit Adate, Rishabh Saxena, "Evaluation of Convolutional Architectures for Offline Handwritten Digit Recognition", International Journal of Science and Research (IJSR), https://www.ijsr.net/search_index_results_paperid.php?id=ART20176492, Volume 6 Issue 8, August 2017, 1904 - 1907
Enter Your Email Address and Click Download Button
Similar Articles with Keyword 'CNN'
Image Noise Reduction with Autoencoder using Tensor Flow
Jai Sehgal, Dr Yojna Arora
Detecting Pneumonia from X-Ray Images using Deep Learning
Deep Piyushkumar Patel
Convolution Neural Network Based Image Recognition
Sofia Hamid, Mrigana Walia
Glaucoma Detection Using Machine Learning
Erection Trusted and Effective Request Services in the Cloud with RASP Data Perturbation
Rashmi Kadu, Sonali Patil