Abstract
Artificial Neural Networks (ANN's) are nowadays a common subject in different curric- ula of graduate and postgraduate studies. Due to the complex algorithms involved and the dynamic nature of ANN's, simulation software has been commonly used to teach this subject. This software has usually been developed specifically for learning purposes, because the existing general pack- ages often lack of a convenient user interface, and are too complex or inadequate for these goals. Since ANN's algorithms, types and applications grow regularly, this solution becomes more and more complex and inefficient. In this paper, we present Visual NNet, a learning-oriented ANN's simulation environment, which overcomes this problem by reusing Matlab Neural Networks Tool- box (MNNT), a well-known, comprehensive and robust ANN implementation. Visual NNet com- bines an on-purpose learning oriented design with the advantages of an ANN's implementation like MNNT. Furthermore, reusing MNNT has done Visual NNet development more cost-effective, fast and reliable.
Highlights
Artificial Neural Networks (ANN’s) are nowadays a well-known data processing method used in a growing range of applications, from pattern recognition to multidimensional data classification
The view and the controller classes are implemented as part of the Visual NNet graphical user interface (GUI); they are in charge of rendering the model in a suitable way for the user to be able to see and to interact with it, and they are responsible of making the pertinent calls to the model in response to user requests and events
In this paper we presented Visual NNet, a learning software environment for simulating ANN’s developed with the aim of offering a learning-oriented user interface but without renouncing to provide robust, complete and state-of-the art ANN features
Summary
Artificial Neural Networks (ANN’s) are nowadays a well-known data processing method used in a growing range of applications, from pattern recognition to multidimensional data classification (see for example research journals like Neural Computing & Applications). Computer-based modeling and simulation environments can be an excellent way to facilitate students to build ANN’s models and to reach both a theoretical and procedural significant understanding of those concerns (Jonassen and Henning, 1999; Jonassen et al, 2007) This approach has been successfully used and reported in many works (see for example García Roselló et al (2003), Gokbulut and Tekin (2006) or Gonzalez et al, (2003)). We explain the way to overcome this problem, in order to develop Visual NNet, a simulation environment that combines a very simple and easy-to-use learning-oriented user interface with the state-of-the-art and well-proven implementation of ANN’s of the MNNT In this way, Visual NNet development was clearly shortened and simplified, since algorithmic complexity relies on MNNT, and, this provides a more robust and comprehensive ANN’s functionality.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
