DiscoverNet: adaptive learning environment for designing neural networks

This paper presents the storyboard of a student using our system (DiscoverNet). DiscoverNet provides an adaptive simulation based discovery learning environment to design neural networks. We chose `neural networks´ (NN) as application domain, due to the fact that their study is particularly suitable for an adaptive student level adjusted approach. We embedded in the system also an advice generator module that is responsible for the educational orientation during the design session. The system supports two types of design. student-level design with objects manipulations, and system-level design with predefined architectures that generates a NN model according to the student configuration/parameters specifications