Improving the Classification Efficiency of an ANN Utilizing a New Training Methodology
Journal Title: Informatics - Year 2019, Vol 6, Issue 1
Abstract
In this work, a new approach for training artificial neural networks is presented which utilises techniques for solving the constraint optimisation problem. More specifically, this study converts the training of a neural network into a constraint optimisation problem. Furthermore, we propose a new neural network training algorithm based on the L-BFGS-B method. Our numerical experiments illustrate the classification efficiency of the proposed algorithm and of our proposed methodology, leading to more efficient, stable and robust predictive models.
Authors and Affiliations
Ioannis E. Livieris
Keywords
Related Articles
- EP ID EP44175
- DOI https://doi.org/10.3390/informatics6010001
- Views 271
- Downloads 0
The Effect of Evidence Transfer on Latent Feature Relevance for Clustering
Evidence transfer for clustering is a deep learning method that manipulates the latent representations of an autoencoder according to external categorical evidence with the effect of improving a clustering outcome. Evi...
digiMe: An Online Portal to Support Connectivity through E-Learning in Medical Education
Connectivity is intrinsic to all aspects of our life today, be it political, economic, technological, scientific, or personal. Higher education is also transcending the previous paradigm of technology enabled content d...
The Experience of Learning in “The Cube”: Queensland University of Technology’s Giant Interactive Multimedia Environment
In this paper we report findings of the first phase of an investigation, which explored the experience of learning amongst high-level managers, project leaders and visitors in Queensland University of Technology’s (QUT...
Reinforcement Learning for Predictive Analytics in Smart Cities
The digitization of our lives cause a shift in the data production as well as in the required data management. Numerous nodes are capable of producing huge volumes of data in our everyday activities. Sensors, personal...
Opening up the Black Box of Sensor Processing Algorithms through New Visualizations
Vehicles and platforms with multiple sensors connect people in multiple roles with different responsibilities to scenes of interest. For many of these human–sensor systems there are a variety of algorithms that transfo...