Abstract
This chapter will focus on theory behind some bleeding-edge techniques and will prepare you to solve problems in univarient and multivarient data for time-series models using deep learning (covered in Chapters 6 and 7). In this chapter, we’ll start with an introduction to neural networks by reviewing perceptrons, activation functions, backpropagation, types of gradient descent, recurrent neural networks, long short-term memory, gated recurrent units, convolutional neural networks, and auto-encoders.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2020 B V Vishwas and Ashish Patel
About this chapter
Cite this chapter
Vishwas, B.V., Patel, A. (2020). Bleeding-Edge Techniques. In: Hands-on Time Series Analysis with Python. Apress, Berkeley, CA. https://doi.org/10.1007/978-1-4842-5992-4_5
Download citation
DOI: https://doi.org/10.1007/978-1-4842-5992-4_5
Published:
Publisher Name: Apress, Berkeley, CA
Print ISBN: 978-1-4842-5991-7
Online ISBN: 978-1-4842-5992-4
eBook Packages: Professional and Applied ComputingApress Access BooksProfessional and Applied Computing (R0)