Files
Abstract
Deep learning has experienced rapid growth and garnered significant attention in recent decades. Simultaneously, neuroscience has remained a challenging and enigmatic field of study. Inspired by the structure and function of the brain, researchers have developed increasingly powerful and sophisticated deep learning models that have achieved remarkable performance in various domains, including computer vision, natural language processing, and medical image analysis. These brain-inspired models have revolutionized the field of artificial intelligence, enabling breakthroughs in tasks such as image recognition, language understanding, and disease diagnosis. In turn, the application of these advanced deep learning models has provided valuable insights into the inner workings of the human brain, revealing temporal and spatial functional brain networks. The symbiotic relationship between artificial intelligence and neuroscience is evident, as they continuously inform and complement each other's progress.
This dissertation presents novel frameworks that integrate deep learning and knowledge from brain science. This research aims to gain insights into the brain and refine deep learning models through brain-inspired principles. The dissertation first discusses how deep learning has been applied to study the brain, focusing on areas such as modeling cortical folding patterns, hierarchical brain structures, and spatial-temporal brain networks. It then discusses how artificial neural networks have drawn inspiration from the brain, using examples like convolutional neural networks, attention mechanisms, and language models. The dissertation’s main contributions are several computational frameworks integrating brain-inspired insights. These include a graph representation neural architecture search method to optimize recurrent neural networks for analyzing spatiotemporal brain networks, a hierarchical semantic tree concept whitening model to disentangle concept representations for image classification, a twin-transformer framework to study gyri and sulci in the cortex, a core-periphery guided vision transformer, and methods leveraging language models to generate data and analyze health narratives. Overall, this dissertation explores how we can understand the brain better using deep learning and ultimately build more efficient, robust, and interpretable artificial neural networks inspired by the brain.
This dissertation presents novel frameworks that integrate deep learning and knowledge from brain science. This research aims to gain insights into the brain and refine deep learning models through brain-inspired principles. The dissertation first discusses how deep learning has been applied to study the brain, focusing on areas such as modeling cortical folding patterns, hierarchical brain structures, and spatial-temporal brain networks. It then discusses how artificial neural networks have drawn inspiration from the brain, using examples like convolutional neural networks, attention mechanisms, and language models. The dissertation’s main contributions are several computational frameworks integrating brain-inspired insights. These include a graph representation neural architecture search method to optimize recurrent neural networks for analyzing spatiotemporal brain networks, a hierarchical semantic tree concept whitening model to disentangle concept representations for image classification, a twin-transformer framework to study gyri and sulci in the cortex, a core-periphery guided vision transformer, and methods leveraging language models to generate data and analyze health narratives. Overall, this dissertation explores how we can understand the brain better using deep learning and ultimately build more efficient, robust, and interpretable artificial neural networks inspired by the brain.