Dual Embodied-Symbolic Concept Representations for Deep Learning
This work addresses the integration of deep learning and symbolic AI, which is a foundational challenge in AI, but it appears incremental as it builds on existing cognitive science findings.
The paper tackles the problem of integrating deep learning with symbolic AI by proposing dual embodied-symbolic concept representations, demonstrating their value through use cases like few-shot class incremental learning and image-text matching, though no concrete numbers are provided for results.
Motivated by recent findings from cognitive neural science, we advocate the use of a dual-level model for concept representations: the embodied level consists of concept-oriented feature representations, and the symbolic level consists of concept graphs. Embodied concept representations are modality specific and exist in the form of feature vectors in a feature space. Symbolic concept representations, on the other hand, are amodal and language specific, and exist in the form of word / knowledge-graph embeddings in a concept / knowledge space. The human conceptual system comprises both embodied representations and symbolic representations, which typically interact to drive conceptual processing. As such, we further advocate the use of dual embodied-symbolic concept representations for deep learning. To demonstrate their usage and value, we discuss two important use cases: embodied-symbolic knowledge distillation for few-shot class incremental learning, and embodied-symbolic fused representation for image-text matching. Dual embodied-symbolic concept representations are the foundation for deep learning and symbolic AI integration. We discuss two important examples of such integration: scene graph generation with knowledge graph bridging, and multimodal knowledge graphs.