AN ADAPTIVE MOMENTUM BACK-PROPAGATION (AMBP)

An algorithm for fast minimum search is proposed, which achieves very satisfying performance harmonising the Vogl's and the Conjugate Gradient algorithms. Such effectiveness is achieved by making adaptive, in a very simple and satisfactory way, both the rate and the term, and by momentum and corrections both on the possible cost function increase and on moves opposite to the direction of the negative of the gradient. Thanks to these improvements, we can obtain a good scaling relationship in learning. As regards the real world context, a musical application showed favourable results: besides the good convergence speed, a high generalisation capability has been achieved, as confirmed both by subjective musical evaluations and by objective tests.