Abstract
In this chapter, we introduce the main concepts of Neural Networks and Deep Learning. We review the mathematical foundations and implement the classical Multilayer Perceptron and the Convolution Neural Networks with Keras on the top of TensorFlow. We show how to construct an image classification model, bridging theory with hands-on experience. Furthermore, to ensure effective model training and prevent overfitting, we introduce various techniques, such as regularization, dropout and data augmentation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In the context of neural networks, a hidden layer is a layer of artificial neurons or nodes that sits between the input layer and the output layer. It is called “hidden” because it does not directly interact with the external data or the final output of the network. Instead, the hidden layer(s) are responsible for processing and transforming the input data before passing it to the output layer.
- 2.
A minibatch is a subset of the training dataset that is used during the training of machine learning models, including neural networks. Instead of using the entire training dataset in a single step (which is known as batch or full-batch training), training is typically performed in smaller, manageable batches.
- 3.
In deep learning, an epoch is one complete pass through the entire training dataset during the training phase of a neural network. During an epoch, the algorithm processes the entire dataset, computes the loss, and updates the model’s parameters (weights and biases) once.
- 4.
- 5.
- 6.
- 7.
References
D.O. Hebb, The Organization of Behavior: A Neuropsychological Theory (Wiley, New York, 1949). ISBN 9780471367277
F. Rosenblatt, The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65(6), 386–408 (1958). https://doi.org/10.1037/h0042519
D.E. Rumelhart, G.E. Hinton, R.J. Williams, Learning representations by back-propagating errors. Nature 323(6088), 533–536 (1986)
A. Krizhevsky, I. Sutskever, G.E. Hinton, Imagenet classification with deep convolutional neural networks, in Advances in Neural Information Processing Systems 25 (2012)
Acknowledgements
This chapter was co-written by Jordi Vitrià and Santi Seguí.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2024 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Igual, L., Seguí, S. (2024). Deep Learning. In: Introduction to Data Science. Undergraduate Topics in Computer Science. Springer, Cham. https://doi.org/10.1007/978-3-031-48956-3_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-48956-3_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48955-6
Online ISBN: 978-3-031-48956-3
eBook Packages: Computer ScienceComputer Science (R0)