Context sequence theory: a common explanation for multiple types of learning
This work addresses the fundamental problem of bridging neuroscience and machine learning for researchers in both fields, but it appears incremental as it builds on existing neuroscience advances without demonstrating concrete applications.
The authors tackled the gap between machine learning and mammalian learning by proposing the context sequence theory, which aims to provide a common explanation for multiple types of learning in mammals, with the result being a theoretical framework intended to offer new insights for constructing machine learning models.
Although principles of neuroscience like reinforcement learning, visual perception and attention have been applied in machine learning models, there is a huge gap between machine learning and mammalian learning. Based on the advances in neuroscience, we propose the context sequence theory to give a common explanation for multiple types of learning in mammals and hope that can provide a new insight into the construct of machine learning models.