"information geometry"

Information geometry of turbo and LDPC codes

Turbo and LDPC (low-density parity check) codes are simple and new types of error correction codes which give a powerful and practical performance of error correction. Although experimental results show their efficacy, further theoretical analysis is …

Information Geometry for Turbo Decoding

Turbo codes are known as a class of error-correcting codes which have high error-correcting performance with efficient decoding algorithm. Characteristics of the iterative decoding algorithm have been studied in detail through a variety of numerical …

Stochastic reasoning, free energy, and information geometry

Belief propagation (BP) is a universal method of stochastic reasoning. It gives exact inference for stochastic models with tree interactions and works surprisingly well even if the models have loopy interactions. Its performance has been analyzed …

Information geometry of turbo and low-density parity-check codes

Turbo and LDPC (low-density parity check) codes are simple and new types of error correction codes which give a powerful and practical performance of error correction. Although experimental results show their efficacy, further theoretical analysis is …

Information Geometry and Mean Field Approximation: The α-projection Approach

Information geometry is applied to mean field approximation for elucidating its properties in the spin glass model or the Boltzmann machine. The $α$-divergence is used for approximation, where $α$-geodesic projection plays an important role. The …

Convergence of the Wake-Sleep Algorithm

The W-S (Wake-Sleep) algorithm is a simple learning rule for the models with hidden variables. It is shown that this algorithm can be applied to a factor analysis model which is a linear version of the Helmholtz machine. But even for a factor …