Hybrid learning process for neural networks, e.g. for pattern recognition in speech processing - uses combination of stochastic and deterministic processes for optimising system

摘要

The stochastic process is used in an initial attempt to optimise the weighting coefficients of the network. This is followed by the deterministic approach in which an error back propagation method is used to achieve a local optimisation. The resulting learning process based upon a multiprocessor system is accelerated. The first phase may use a genetic or metropolis algorithm. The second phase is initiated, pref. , when a value corresp. to the learning progress has dropped below a predetermined threshold value. ADVANTAGE - Reduced processing time required, can handle large amount of variables.