Model building software tools | Mathematical modeling

Proposes a simulator-independent language for building neuronal network models. PyNN makes it possible to write a simulation script once, using the Python programming language, and run it without modification on any supported simulator (currently NEURON, NEST, PCSIM, Brian and the Heidelberg VLSI neuromorphic hardware). PyNN increases the productivity of neuronal network modelling by providing high-level abstraction, by promoting code sharing and reuse, and by providing a foundation for simulator-agnostic analysis, visualization and data-management tools. PyNN increases the reliability of modelling studies by making it much easier to check results on multiple simulators.

Serves for training, testing, finetuning, and deploying models, with well-documented examples for all of these tasks. Caffe is a program allowing extension to new formats, network layers, and loss functions. It can be useful for state-of-the-art deep learning algorithms and a collection of reference models. Moreover, this tool fits industry and internet-scale media needs by CUDA graphics processing unit (GPU) computation.

Assists users for numerical computation. Scilab aims to provide computing environment for engineering and scientific applications. This tool includes functionalities specifically for: (1) numerical analysis, (2) data visualization, (3) algorithm development, and (4) application deployment.