Issues in Training a Convolutional Neural Network Model for Image Classification

  • Soumya Joshi
  • Dhirendra Kumar VermaEmail author
  • Gaurav Saxena
  • Amit Paraye
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1046)


Convolutional neural networks (CNN) are a boon to image classification algorithms as it can learn highly abstract features and work with less parameter. Overfitting, exploding gradient, and class imbalance are the major challenges while training the model using CNN. These issues can diminish the performance of the model. Proper understanding and use of corrective measures can substantially prevent the model from these issues and can increase the efficiency of the model. In this paper the conceptual understanding of the basic CNN model along with its key layers is provided. The paper summarizes the results of training the deep learning model using CNN on publicly available datasets of cats and dogs. Finally the paper discusses various methods such as data augmentation, regularization, dropout, etc. to prevent the CNN model from overfitting problem. The paper will also help beginners to have a broad comprehension of CNN and motivate them to venture in this field.


Convolutional neural networks Deep learning Image classification Data augmentation Image dataset 


  1. 1.
    Mohamed, A.-R., Dahl, G.E., Hinton, G.: Acoustic modeling using deep belief networks. IEEE Trans. Audio Speech Lang. Process. 20(1), 14–22 (2012)CrossRefGoogle Scholar
  2. 2.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRefGoogle Scholar
  3. 3.
    Hu, G., Wang, K., Peng, Y., Qiu, M., Shi, J., Liu, L.: Deep learning methods for underwater target feature extraction and recognition. Comput. Intell. Neurosci. 2018, 10 (2018). Article ID 1214301CrossRefGoogle Scholar
  4. 4.
  5. 5.
  6. 6.
  7. 7.
  8. 8.
  9. 9.
  10. 10.
  11. 11.
  12. 12.
  13. 13.
    Jaswal, D., Vishvanathan, S., Soman K.P.: Image classification using convolutional neural networks. Int. J. Adv. Res. Technol. 3(6) (2014)CrossRefGoogle Scholar
  14. 14.
    Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning (Adaptive Computation and Machine Learning) (2016)Google Scholar
  15. 15.

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Soumya Joshi
    • 1
  • Dhirendra Kumar Verma
    • 2
    Email author
  • Gaurav Saxena
    • 2
  • Amit Paraye
    • 2
  1. 1.Medicaps Institute of Technology and ManagementIndoreIndia
  2. 2.Computer Division, Department of Atomic EnergyRaja Ramanna Centre for Advanced TechnologyIndoreIndia

Personalised recommendations