Special Issue on Deep Neural Information Processing
摘要截稿:
全文截稿: 2019-02-01
影响因子: 4.438
期刊难度:
CCF分类: C类
中科院JCR分区:
• 大类 : 计算机科学 - 2区
• 小类 : 计算机:人工智能 - 2区
Overview
With the resurgence of deep learning architectures and learning methods, neural information processing has been applied to a variety of disciplines and proved highly successful in a vast class of applications. For instance, in the pattern recognition field, deep neural networks achieved human-like performance in recognizing, labeling and sorting images, e.g., on the ImageNet benchmark. Moreover, DeepMind’s AlphaGo Zero, trained by self-play reinforcement learning, achieved superhuman performance in the game of Go. On the hardware architecture side, advanced neuromorphic processors have been designed to mimic human functions of perception, motor control and multisensory integration.
Researchers with varying backgrounds in computer and cognitive science, mathematics, physics and computational neuroscience are very active in this field, that is booming and expects to change the world. As such, this is the right time to collect and disseminate latest discoveries and results on deep neural information processing in a Special Issue of Neurocomputing. The special issue goes in this direction by soliciting original, high-quality, contributions in all aspects of deep neural information processing.
The list of possible topics includes, but is not limited to,:
- Novel deep neural network architectures;
- Deep learning theory and learning methodologies;
- Advanced supervised/unsupervised/reinforcement deep learning;
- Deep neural networks for data mining, pattern recognition and signal processing;
- Deep neural networks for intelligent control and decision-making;
- Deep neural networks for emerging applications such as smart healthcare, transportation and business intelligence;
- Graph-based deep neural information processing;
- Emerging brain-like deep neural network techniques;
- Neuromorphic engineering and hardware implementation of neural networks.