Advances in Machine Learning for Computational Neural Modeling for Visual Recognition
1Massey University, Wellington, New Zealand
2Xidian University, Xi'an, China
3University College Dublin, Dublin, Ireland
Advances in Machine Learning for Computational Neural Modeling for Visual Recognition
Description
In recent years, neurological modeling and simulations have demonstrated great potential in modeling and data processing of various applications, such as face recognition, image processing, voice recognition, medical diagnosis, and signal processing. However, the growing amount of big data presents increasing challenges to the modeling and simulation of neural networks at various levels under diverse boundary conditions. Advanced methodologies and technologies are necessary to generate biological neural parameters from abundant data, in order to better depict and optimize neural network models.
Machine learning (ML) technologies, especially deep learning, have unpreceded capacities in feature extraction and function fitting in visual recognition. They have been utilized to solve many complex problems in object detection and other fields. The ML provides a valid way to recognize complex patterns and carry out regression analysis, eliminating the need for building or solving the underlying physical models. Therefore, the relevant technologies contribute immensely to the construction and optimization of computational neural models for visual recognition.
This Special Issue aims to bring together researchers from ML and computational neuroscience, and stimulate collaboration between them in the visual recognition field. It intends to bridge the gap between neuroscience research of biological models, and the latest studies on computational methodologies and tools for visual recognition, which cover the entire process of modeling and analysis. We welcome original research and review articles from systems/cognitive and computational neuroscience, to neuroimaging and neural signal processing.
Potential topics include but are not limited to the following:
- ML-based computational neural models for visual recognition
- Modeling and optimization of biological neural networks for visual recognition
- Neural network-based ML algorithms for visual recognition
- Novel ML methods to train biological neural networks for visual recognition
- Simulation of computational neural models for visual recognition
- Domain-specific for visual recognition applications of ML-based computational neural modeling