Back Propagation (BP) is commonly used algorithm that optimize the performance of network for training multilayer feed-forward artificial neural networks. However, BP is inherently slow in learning and it sometimes gets trapped at local minima. These problems occur mailnly due to a constant and non-optimum learning rate (a fixed step size) in which the fixed value of learning rate is set to an initial starting value before training patterns for an input layer and an output layer. This fixed learning rate often leads the BP network towrds failure during steepest descent. Therefore to overcome the limitations of BP, this paper introduces an improvement to back propagation gradient descent with adapative learning rate (BPGD-AL) by changing the values of learning rate locally during the learning process. The simulation results on selected benchmark datasets show that the adaptive learning rate significantly improves the learning efficiency of the Back Propagation Algorithm.

The purpose of this paper is to impart interesting facts about an online vocabulary game namely OnVac, which can be used to learn engineering and technology vocabulary. E-mail interviews conducted with 32 students on a voluntary basis in a public university in Malaysia revealed positive perceptions of OnVac as an interesting tool to learn engineering and technology vocabulary. It implied that online games such as OnVac could facilitate university students to enrich their engineering and technical vocabulary. Since the vocabularies are selected from their core engineering and technical reference books, it seemed that OnVac was able to facilitate the students in understanding of their core subjects better. The study also showed evidence that OnVac enabled them to retain the engineering and technology vocabulary for both short- and long-term recalls.