Cognity is an object-oriented neural network library for Java. It's goal is to provide easy-to-use, high level architecture for neural network computations along with reasonable performance.

Features

  • Neural networks: multilayer perceptron
  • Learning algorithms: backpropagation with momentum
  • Activation functions: tanh, sigmoid, gaussian, heaviside step function, linear
  • Weight randomization algorithms: uniform randomization
  • Basic data structures for neural network training
  • Importing and exporting data to Matlab files

Project Activity

See All Activity >

Categories

Frameworks, Libraries, Machine Learning, Neural Network Libraries

License

Apache License V2.0

Follow cognity

cognity Web Site

Other Useful Business Software
Build Securely on AWS with Proven Frameworks Icon
Build Securely on AWS with Proven Frameworks

Lay a foundation for success with Tested Reference Architectures developed by Fortinet’s experts. Learn more in this white paper.

Moving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
Download Now
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of cognity!

Additional Project Details

Intended Audience

Developers, Engineering, Science/Research

Programming Language

Java

Related Categories

Java Frameworks, Java Libraries, Java Machine Learning Software, Java Neural Network Libraries

Registered

2011-11-06
Report inappropriate content