Software and Tutorials

One of the most important objective of the Continuous AI project is to provide an easy access to Continuous Learning both in terms of didactic materials and open software for business/research. In this page we will try to collect every open-source project or tutorial related to Continuous Learning.


  • CORe50 benchmark: Continuous Learning benchmark for object recognition and robotics
  • NORB sequencer: Java application (with GUI) to make small videos out of the NORB dataset.
  • GEM implementation: Implementation of the CL strategy “Gradient Episodic Memory”.
  • OpenAI Gym: Open source interface that provides a ready-to-use suite of reinforcement learning tasks for evaluating performance of your algorithm.
  • DeepMind Lab: 3D learning environment that provides a suite of challenging 3D navigation and puzzle-solving tasks for learning agents.
  • DEN: TensorFlow implementation of the CL strategy “Dynamically Expandable Networks”.