Welcome to biolearn’s documentation!

biolearn library provides two different implementations of unsupervised neural networks with biological-inspired learning rules. The models are both based on neurons competiton and they are mathematically described in the following papers:

• D. Krotov, J. Hopfield, Unsupervised Learning by Competing Hidden Units

• G. Castellani et al., Solutions of the BCM learning rule in a network of lateral interacting nonlinear neurons

Contents:

• Introduction
• Theory
  • BCM with lateral interactions
  • Weights orthogonalization
• Python API
  • Base
    • Base
      • Base.fit()
      • Base.fit_transform()
      • Base.load_weights()
      • Base.predict()
      • Base.save_weights()
      • Base.transform()
  • BCM
    • BCM
      • BCM.fit()
      • BCM.fit_transform()
      • BCM.get_params()
      • BCM.load_weights()
      • BCM.predict()
      • BCM.save_weights()
      • BCM.set_params()
      • BCM.transform()
  • Hopfield
    • Hopfield
      • Hopfield.fit()
      • Hopfield.fit_transform()
      • Hopfield.get_params()
      • Hopfield.load_weights()
      • Hopfield.predict()
      • Hopfield.save_weights()
      • Hopfield.set_params()
      • Hopfield.transform()
• MNIST Examples
  • BCM model
  • Hopfield model
• References