Skip to content

mingusb/cemer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🧠 emergent | C++ Neural Network Simulator

6/4/26 Update: I have confirmed that a frontier model can get emergent working on Ubuntu 26.04 and Qt6.*.

Language C++ Status Deprecated License MIT Build Passing

emergent is a comprehensive neural network simulator that enables the creation and analysis of complex, sophisticated models of the brain.

📑 Table of Contents

🚀 Overview

emergent is a comprehensive neural network simulator that enables the creation and analysis of complex, sophisticated models of the brain in the world.

Warning

We are no longer developing this software. We are now developing a new framework based on the Go language, with a Python interface: https://github.com/emer/emergent

Neural Network Simulation Features

  • Full browser and 3D GUI for constructing, visualizing, & interacting.

    • Accessible to non-programmers
    • Highly productive for experts, used daily in scientific research.
  • Powerful C++ scripting language, css (not that css), GUI Programming environment (IDE) -- TypeAccess access to C++.

  • Rich, dynamic, embodied environments for training networks:

    • DataTable for network inputs and DataProc, DataAnal, DataGen (filtering, grouping, sorting, dimensionality reduction, graphing, etc).
    • Newtonian physics simulator for Virtual Environment, e.g., a biophysically realistic human arm, and realistic embodied, dynamic vision.
    • Sensory filtering for vision, audition, and vocal-tract speech.
  • Many classic neural network algorithms and variants: Backpropagation (e.g., deep convolutional neural networks), Constraint Satisfaction, Self Organizing, and the Leabra algorithm which incorporates many of the most important features from each of these algorithms, in a biologically consistent manner. Also, symbolic / subsymbolic ACT-R.

  • Highly optimized vector-based back-end code with thread-specific memory allocation, and GPU (CUDA); Convenient compute cluster for GUI-based job control and data management.

  • In use for decades, for hundreds of scientific publications from a variety of different labs. Detailed models of the hippocampus, prefrontal cortex, basal ganglia, visual cortex, cerebellum, etc.

    • Direct descendant of earlier simulators: PDP (1986) and PDP++ (1995).

3D GUI visualization of emergent neural network simulation

💻 Installation & Setup

Prerequisites & Dependencies

Basic Setup

Main documentation is here: https://grey.colorado.edu/emergent -- basic install and build information is on the Github Wiki.

💡 Usage

To run the emergent GUI after installation, you can launch it via your command line interface.

# Example execution of the emergent GUI
emergent --project my_network.proj

🐛 Issues & Support

If you encounter any issues or have questions regarding this deprecated repository, please refer to the Issues page or consult the wiki documentation. Note that support may be limited due to its deprecated status.

🤝 Contributing

Contributions to improve the documentation or fix critical bugs are welcome. Please ensure your pull requests follow the standardized coding style and open an issue for major changes before contributing.

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.

Return to main profile

About

emergent™: The Original Deep Learning Integrated Development Environment (Co-Author) [1985-2005][2005-2015][2015-2026]

Resources

License

Stars

Watchers

Forks

Packages

 
 
 

Contributors