[Pycon] [new paper] "Vaibhav Srivastava" - Reincarnating Shakespeare with Recurrent Neural Networks

[info a pycon.it]

Title:  Reincarnating Shakespeare with Recurrent Neural Networks
Duration: 240 (includes Q&A)
Q&A Session: 0
Language: en
Type: Training

Abstract: This talk demonstrates how to generate text using an RNN using tf.keras and eager execution. If you like, you can write a similar model using less code. Here, we show a lower-level implementation that’s useful to understand as prework before diving in to deeper examples.

**Topics covered during the talk:**
1. What are Recurrent Neural Networks (RNNs)?
2. Discussing and Implementing LSTM in Tensorflow (Keras)
3. Training Character-level and Word-level language models on Shakespeare Corpus to generate some fun text!

**Prerequisites:**
1. Python programming fundamentals.
2. Basics of Linear Algebra and Probability
3. Tensorflow/ Keras
4. Basic Knowledge of Neural Networks

_Note:_ The code for this session runs on Google Colab, hence the audience won’t be required to setup there laptops with Python and other dependencies.



Tags: [u'code generation', u'neural network', u'nlp', u'GPUComputing', u'buildbot', u'mathematical-modelling', u'machine-learning', u'Artificial Intelligence']