سیدصالحی, سیده زهره

[ 1 ] - روش پیش‌تعلیم سریع بر مبنای کمینه‌سازی خطا برای همگرائی یادگیری شبکه‌های‌ عصبی با ساختار عمیق

In this paper, we propose efficient method for pre-training of deep bottleneck neural network (DBNN). Pre-training is used for initial value of network weights convergence of DBNN is difficult because of different local minimums. While with efficient initial value for network weights can avoided some local minimums. This method divides DBNN to multi single hidden layer and adjusts them, then we...