The high-order Boltzmann machine: learned distribution and topology


In this paper we give a formal definition of the high-order Boltzmann machine (BM), and extend the well-known results on the convergence of the learning algorithm of the two-order BM. From the Bahadur-Lazarsfeld expansion we characterize the probability distribution learned by the high order BM. Likewise a criterion is given to establish the topology of the BM depending on the significant correlations of the particular probability distribution to be learned.

DOI: 10.1109/72.377984

Cite this paper

@article{Albizuri1995TheHB, title={The high-order Boltzmann machine: learned distribution and topology}, author={F. Xabier Albizuri and Alicia D'Anjou and Manuel Gra{\~n}a and Francisco Javier Torrealdea and Carmen Hern{\'a}ndez}, journal={IEEE transactions on neural networks}, year={1995}, volume={6 3}, pages={767-70} }