frederikheber/tati repository overview

TATi is a software suite written in Python based on tensorflow⁠'s Python API. It brings advanced sampling methods to neural network training. Its tools allow to assess the loss manifold's topology that depends on the employed neural network and the dataset. Moreover, its simulation module makes applying present sampling Python codes in the context of neural networks easy and straight-forward. The goal of the software is to enable the user to analyze and adapt the network employed for a specific classification problem to best fit her or his needs.

TATi has received financial support from a seed funding grant and through a Rutherford fellowship from the Alan Turing Institute in London (R-SIS-003, R-RUT-001) and EPSRC grant no. EP/P006175/1 (Data Driven Coarse Graining using Space-Time Diffusion Maps, B. Leimkuhler PI). Moreover, the development was aided by a Microsoft Azure Sponsorship (MS-AZR-0143P).

Please take a look at the jupyter-notebook starting from this container. Check out the guided-tour notebooks that tell you about the various features of TATi.

Start the container by

docker run -p 8888:8888 frederikheber/tati:latest

and use the URL printed to the console to direct your browser to the jupyter notebook with a guided tour.