Abstract | The fields of machine learning and cognitive computing have been in the last decade revolutionised with neural-inspired algorithms (e.g., deep ANNs and deep RL) and brain-intelligent systems that assist in many real-world learning tasks from robot monitoring and interaction at home to complex decision-making about emotions and behaviours in humans and animals. While there are remarkable advances in these brain-inspired algorithms and systems, they need to be trained with huge data sets, and their results lack flexibility to adapt to diverse learning tasks and sustainable performance over long periods of time. To address these challenges, it is essential to gain an analytical understanding of the principles that allow biological inspired intelligent systems to leverage knowledge and how they can be translated to hardware for daily assistance and practical applications. This special issue brings researchers from interdesciplinary domains to report their latest research work on algorithms and neural-inspired systems that flexibly adapt to new learning tasks, learn from the environment using multimodal signals (e.g., neural, physiological, and kinematic), and produce autonomous adaptive agencies, which utilise cognitive and affective data, within a social neuroscientific framework. In this special issue, we have selected five papers out of fourteen high-quality papers after a careful reviewing process, which brings the acceptance rate to 35.7 percent. The five papers are representative of the current state-of-the-art in this area. |
---|