论文信息 - rFBP: Replicated Focusing Belief Propagation algorithm

rFBP: Replicated Focusing Belief Propagation algorithm

The rFBP project implements a scikit-learn compatible machine-learning binary classifier leveraging fully connected neural networks with a learning algorithm (Replicated Focusing Belief Propagation, rFBP) that is quickly converging and robust (less prone to brittle overfitting) for ill-posed datasets (very few samples compared to the number of features). The current implementation works only with binary features such as one-hot encoding for categorical data.

[1] W. Krauth,et al. Storage capacity of memory networks with binary couplings , 1989 .

[2] Yoshiyuki Kabashima,et al. Origin of the computational hardness for learning with binary synapses , 2014, Physical review. E, Statistical, nonlinear, and soft matter physics.

[3] G. Parisi,et al. Mean field theory of spin glasses: statics and dynamics , 2007 .

[4] Ronald L. Rivest,et al. Training a 3-node neural network is NP-complete , 1988, COLT '88.

[5] Carlo Baldassi,et al. Local entropy as a measure for sampling solutions in Constraint Satisfaction Problems , 2015 .

[6] Riccardo Zecchina,et al. Learning by message-passing in networks of discrete synapses , 2005, Physical review letters.

[7] Riccardo Zecchina,et al. Learning and Generalization Theories of Large Committee-Machines , 1995, cond-mat/9601122.

[8] Carlo Baldassi,et al. A Max-Sum algorithm for training discrete neural networks , 2015, ArXiv.

[9] Carlo Baldassi,et al. Learning may need only a few bits of synaptic precision. , 2016, Physical review. E.

[10] Monasson,et al. Weight space structure and internal representations: A direct approach to learning and generalization in multilayer neural networks. , 1995, Physical review letters.