Artificial neural networks are powerful machine learning techniques that can learn to recognize images or paint in the style of Van Gogh. Recurrent neural networks offer a more general model that can learn input sequences and create output sequences. The resulting technique (Long Short-Term Memory in these examples) can write novels in the style of Tolstoy, Shakespeare, or write their own music.
________________________
Andrej Karpathy’s original article is available here:
Source code:
The paper “Long Short-Term Memory” by Sepp Hochreiter and Jürgen Schmidhuber is available here:
Continuing “Let It Go” from Disney with a recurrent neural network:
Recommended for you:
Artificial Neural Networks and Deep Learning –
Deep Neural Network Learns Van Gogh’s Art –
Creating Photographs Using Deep Learning –
A great write-up on how LSTMs work:
More applications of Long Short-Term Memory:
Subscribe if you would like to see more of these! –
The thumbnail image background was created by Brandon Giesbrecht (license: CC BY 2.0). Slight changes were made for better blending. –
Splash screen/thumbnail design: Felícia Fehér –
Music: “Gymnopedie no1” by Satie.
Károly Zsolnai-Fehér’s links:
Patreon →
Facebook →
Twitter →
Web →
source