Talk: Recurrent Neural Networks

Presentation given for the January meeting of Danbury AI.

Recurrent Neural Networks ( RNN ) are a special configuration of Neural Networks for processing sequential data. In this talk we discuss the ideas behind RNNs and several fascinating applications of RNNs which allow us to produce samples of high perceptual similarity to training set data.

“Much as almost any function can be considered a feedforward neural network, essentially any function involving recurrence can be considered a recurrent neural network.” – http://www.deeplearningbook.org/

SLIDES


About the Author: Andrew Ribeiro

I am a computer scientist working in the field of Artificial Intelligence as the co-founder of Knowledge-Exploration Systems -- a Danbury based AI and systems development contractor. I studied traditional computer science at WCSU and extended my knowledge to include AI by taking online courses, reading the classic books, and reading research papers in the field while applying the ideas to commercial R&D applications. Due to the intensive intellectual demands of mastering such a diverse field, I also co-founded Danbury AI in 2016 to foster a local community of AI experts and enthusiasts that help each other grow and learn.

Leave A Reply

Your email address will not be published. Required fields are marked *