Reinforcement Learning for Finance: Solve Problems in Finance with CNN and RNN Using the TensorFlow Library

© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2023

S. AhlawatReinforcement Learning for Financehttps://doi.org/10.1007/978-1-4842-8835-1_3

3. Convolutional Neural Networks

Samit Ahlawat¹  

(1)

Irvington, NJ, USA

 

Convolutional neural networks (CNNs) are a category of neural networks that can be used to identify spatial patterns in a robust manner. They achieve this robustness by a parsimonious use of parameters and by systematic identification of simple patterns that are aggregated into complex specifications using subsequent layers. They are able to recognize features in a translation-invariant fashion. Their use in modern digital imaging technology is ubiquitous, with most cameras programmed to pick out faces ...