Abstract
In classical concept learning, each training example is a vector of attribute values. At a more advanced level, however, each example can be a series of such vectors. For instance, one such series can represent the sine function and another may represent an exponential function, and we want the computer to tell them apart. Alternatively, the computer may be asked to alert the user that a pulse from source A was immediately followed by a small growth in signal from source B. In both cases, the goal is to recognize specific temporal patterns. This is why we need techniques to enable temporal learning.
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.
This is what previous chapters called one-hot representation.
References
Elman, J. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211.
Hochreiter, S., & Schmidhuber, J. (1997). Long short term memory. Neural computation, 9 (8), 1735–1780.
Rumelhart, D. E. & McClelland, J. L. (1986). Parallel distributed processing. Cambridge: MIT Bradford Press.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Kubat, M. (2021). Temporal Learning. In: An Introduction to Machine Learning. Springer, Cham. https://doi.org/10.1007/978-3-030-81935-4_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-81935-4_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-81934-7
Online ISBN: 978-3-030-81935-4
eBook Packages: Computer ScienceComputer Science (R0)