Welcome to an interactive Jupyter Book for the research article:

"Efficient neural decoding of self-location with a deep recurrent network"
Tampuu A, Matiisen T, Ólafsdóttir HF, Barry C, Vicente R (2019)
PLoS Comput Biol 15(2): e1006822.

The article reports that the application of RNNs to neural data allowed flexible integration of temporal context, yielding improved accuracy relative to the more commonly used Bayesian approaches, and opening up new avenues for exploration of the neural code. This Jupyter Book reproduces the figures from the article, and lets you interact with them. You can edit and run the code inline directly on these pages, or launch a MyBinder session to run your code in a Jupyter Notebook interface in a new window. The figures are made interactive using Plotly. All of the code is contained inside one Jupyter notebook that uses SoS (Script of Scripts) workflows to enable communication between Python2 and Python3 kernels.