Welcome to PARROT’s documentation!

Contents:

• Getting Started with PARROT
  • Installation
  • Testing
  • Example datasets
• parrot-train
• parrot-optimize
• parrot-predict
• parrot-cvsplit
• Basic Examples:
  • parrot-train
  • parrot-predict
• Advanced Examples:
  • Advanced parrot-train options:
  • Hyperparameter tuning with parrot-optimize:
  • Integrating trained PARROT networks into Python workflows:
• Evaluating a Network with Cross-Validation:
• Machine Learning Resources:
  • First things first, what is ‘Machine Learning’?
  • When can I use machine learning for my research?
  • What is a recurrent neural network (RNN)?
  • What are the hyperparameters of the networks used by PARROT? What should I set them as?
  • What is ‘encoding’?
  • What are over-fitting and under-fitting?
  • How should I set up my dataset?
  • How should I tackle a huge dataset?
  • How can I validate that my trained network is performing well?
  • What are the different performance metrics for evaluating ML networks?
  • How does PARROT choose the optimal hyperparameters?
• Module Documentation
  • brnn_architecture.py
  • encode_sequence.py
  • process_input_data.py
  • train_network.py
  • bayesian_optimization.py
  • brnn_plot.py
  • py_predictor.py