Project 4

Using the Text generation with an RNN from Thursday, replace the shakespeare.txt with a screen play script from your favorite movie. Use the RNN model to generate new text from the source document and then use that machine generated output as the basis for a 5 to 8 minute production on Monday. Be sure to assign a role for each team member such that everyone has a chance to perform. Use the text generated from your RNN model as the basis for your theatrical production, but also feel free to modify it as you please in order to make your presentation more entering. By Monday evening, answer the following questions as a group and post to your GitHub index.

• How did you modify the data and python script in order to generate comprehensible text?
• Did your output seem to generate text that was relying more on the entire corpus of your screen play (i.e. more associated with long term memory) or was it also able to incorporate some more immediate sequential associations (i.e. more associated with short term memory)?
• Did you make any changes to the model itself?
• Were there any unexpected or surprising phrases or statements that were generated by your RNN?

As a stretch goal, for your Monday morning presentation, produce one or two images (using the neural style transfer and/or deep dream methods) that you can use as a virtual background to supplement your RNN generated and inspired theatrical production.