Abstract
CNNs are a prime example of neuroscience influencing deep learning (LeCun, Bottou, Bengio, & Haffner, 1998). These neural networks are based on the seminal work done by Hubel and Wiesel (1962). They discovered that individual neuronal cells in the visual cortex responded only to the presence of visual features such as edges of certain orientations. From their experiments they deduced that the visual cortex contains a hierarchical arrangement of neuronal cells. These neurons are sensitive to specific subregions in the visual field, with these subregions being tiled to cover the entire visual field. They in fact act as localized filters over the input space, making them well suited to exploiting the strong spatial correlation found in natural images. CNNs have been immensely successful in many computer vision tasks not just because of the inspiration drawn from neuroscience, but also due to the clever engineering principles employed. Although they have traditionally been used for applications in the field of computer vision such as face recognition and image classification, CNNs have also been used in other areas such as speech recognition and natural language processing for certain tasks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Epoch refers to the CNN having seen the whole training set.
- 2.
CIFAR stands for the Canadian Institute for Advanced Research. They are partly responsible for funding Hinton and LeCun during the neural network winter, leading to the eventual resurgence of neural networks as deep learning.
- 3.
We also implemented the same notebooks using Keras, which can be found at http://bit.ly/Ch06Keras .
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2018 Mathew Salvaris, Danielle Dean, Wee Hyong Tok
About this chapter
Cite this chapter
Salvaris, M., Dean, D., Tok, W.H. (2018). Convolutional Neural Networks. In: Deep Learning with Azure. Apress, Berkeley, CA. https://doi.org/10.1007/978-1-4842-3679-6_6
Download citation
DOI: https://doi.org/10.1007/978-1-4842-3679-6_6
Published:
Publisher Name: Apress, Berkeley, CA
Print ISBN: 978-1-4842-3678-9
Online ISBN: 978-1-4842-3679-6
eBook Packages: Professional and Applied ComputingApress Access BooksProfessional and Applied Computing (R0)