Lesson 20 of 21 · Part V, Deep learning and beyond

Recurrent neural networks (RNN)

Sequences and transductions, the finite memory of IDNNs and the state of recurrent units, the Simple RNN, unfolding and backpropagation through time, then transformers, Echo State Networks and recursive networks.

11 figures to manipulate.

In this lesson

• Why sequential data
• From flat data to structured data
• Memory in neural networks
• Learning: unfolding
• Related approaches
• Toward structured domains

Other lessons

Unsupervised learning — K-means and SOM · Learning on structured data and graphs · All lessons

Notes by Fabio Piscitelli — Machine Learning (654AA), Prof. Alessio Micheli, University of Pisa, a.y. 2026/27.