Open Source Python Scientific/Engineering Software - Page 54

The NUMIPAD library implements several methods/algorithms to solve inverse problems and adaptive decomposition (i.e. Tikhonov regularization, Total Variation, Basis Pursuit, etc.)

NVIDIA Isaac‑GR00T N1.5 is an open-source foundation model engineered for generalized humanoid robot reasoning and manipulation skills. It accepts multimodal inputs—such as language and images—and uses a diffusion transformer architecture built upon vision-language encoders, enabling adaptive robot behaviors across diverse environments. It is designed to be customizable via post-training with real or synthetic data. The vision-language model remains frozen during both pretraining and finetuning, preserving language understanding and improving generalization. Streamlined MLP connection between vision encoder and LLM with added layer normalization.

A platform independent framework to remote control Lego Mindstorms NXT from Python. Using PyBluez http://org.csail.mit.edu/pybluez/ for Bluetooth connectivity and wxPython http://www.wxpython.org/ for UI.

Naimath (syn. blessing) is a project to create tools for diagnosis, management of clinical cases in the form of Rule based Medical Expert System integrating Interactive Health education, Semantified EMR, and serve as a learning tool for students. Website seen at www.naimath.com

Tools for analysis of multiwavelength anomalous diffraction data collected on synchrotron beamlines, more specifically developed for grazing incidence diffraction on nanostructures.

Napkin (also titled “An Infinitely Large Napkin”) is a lightweight, semi-formal introduction to higher mathematics, aimed at giving readers a bird’s-eye view over various mathematical fields. It is not a polished textbook full of full proofs; rather it offers clean definitions, theorem statements, intuitive motivations, and informal sketches of why things work, with the goal of building conceptual understanding. The coverage spans undergraduate and early graduate topics, designed to show how different areas of math fit together—linear algebra, analysis, topology, number theory, and more—without going deeply into every subtopic. Because it is written in LaTeX (with supporting Asymptote or other tools), readers can compile their own version, and the repository integrates diagrams, flowcharts, and supplementary files.

Narcissistic number library for Python

The main idea behind this project is the use of a common text to enclose a message by manipulating the structure of the semantic tree of each phrase in the text.

Platform providing the support for Wireless Sensor Networks in the domain of Natural Hazards as a Service. The objective of the WSN platform is monitoring the behaviour of rockfall barriers, rockfall netting, rock sheds and other protection systems

NetBuilder' is a tool for building, visualizing, and simulating multi-layered biological networks, structured as hierarchical Petri-nets. It has a built-in stochastic simulator, but also provides easy access to other simulation and analysis.

Remotely monitor and control a network.

The NetEpi project is developing open-source, network-enabled tools for epidemiology and public health practice.

NetView P has been re-structured as a package for R and moved to GitHub: https://github.com/esteinig/netview

Network Visualization is a mature part of computer science that is enjoying a good deal of growth, partially fueled by Bioinformatics. Network is a synonym for Graph, and both refer to a collection of nodes and edges.

NeuraPy is now hosted on github This is a collection of Python modules that read files encountered in neuroscience experiments. Included are modules to read lablib files and modules to read Cyberkinetics Cerebus system .nev and .ns3 files

Net.py is a tool for learning about neural nets. Currently, it only allows the user to experiment with a Hopfield net. I am now extending it to cover the Kohonen net. I'd be pleased to receive suggestions and criticism.

This project implements in C++ a bunch of known Neural Networks. So far the project implements: LVQ in several variants, SOM in several variants, Hopfield network and Perceptron. Other neural network types are planned, but not implemented yet. The project can run in two modes: command line tool and Python 7.2 extension. Currently, Python version appears more functional, as it allows easy interaction with algorithms developed by other people.

Simulator of virtual animals made up of biological neural networks for research in the Computational Neuroscience field.

NeuroPython is a Python module created for easy simulation of neural networks.

Newton is a high-performance, GPU-accelerated physics simulation engine designed primarily for robotics research, machine learning, and advanced simulation workflows. Built on top of NVIDIA Warp, it leverages GPU parallelism to deliver scalable and efficient simulation environments that support rapid iteration and experimentation. The engine extends previous simulation frameworks by introducing differentiable physics capabilities, allowing it to integrate seamlessly with machine learning models and optimization pipelines. Newton supports OpenUSD for modern 3D scene representation and interoperability, making it suitable for complex simulation ecosystems. It is developed as a Linux Foundation project with contributions from major organizations like NVIDIA, Google DeepMind, and Disney Research, highlighting its relevance in cutting-edge robotics and AI development.

Extensions to the circuit simulator Ngspice. One extension is the integration of the next generation build system SCons.

This project has moved to http://sourceforge.net/projects/ngspice-ext.

This project, developed at UCL London, provides code for tomographic reconstruction. NiftyRec is written in C and has Python and Matlab extensions. Computationally intensive functions have a GPU accelerated version based on CUDA.

This is a unix distribution I made so that I can develop from anywhere--a virtual desk if you will. Some of my friends and colleagues have found it useful, and an easily accessible place to put the operating system up is on the internet.

This program was written to dimonstrate errors in transmission for a presentation on Claude Shannon's Noisy Channel Coding Theorem. It takes an input file, the probability of a bit being flipped, and, if specified, the size of the header of the file. The program was intended to take monochrome bitmap files as input, so that each bit refers to a pixel in the image and thus, it would be easy to see errors in the output file, as some of the pixels would be flipped; however, it will work on any input file.