Date:
Location:
Topic: “The Relational Bottleneck and the Emergence of Cognitive Abstractions”
Abstract: Human cognition is characterized by a remarkable ability to transcend the specifics of limited experience to entertain highly general, abstract ideas. Efforts to explain this capacity have long fueled debates between proponents of symbol systems and statistical approaches. In this talk, I will present an approach that suggests a novel reconciliation to this long-standing debate, by exploiting an inductive bias that I term the relational bottleneck. This approach imbues neural networks with key properties of traditional symbol systems, thereby enabling the data-efficient acquisition of cognitive abstractions, without the need for pre-specified symbolic representations. I will also discuss studies of perceptual decision confidence that illustrate the need to ground cognitive theories in the statistics of real-world data, and present evidence for the presence of emergent reasoning capabilities in large-scale deep neural networks (albeit requiring far more training data than is developmentally plausible). Finally, I will discuss the relationship of the relational bottleneck to other inductive biases, such as object-centric visual processing, and consider the potential mechanisms through which this approach may be implemented in the human brain.
Taylor’s work investigates how the brain extracts structured, abstract representations from noisy, high-dimensional perceptual input. He draws on recent advances in AI to build models of cognitive processes that are grounded in naturalistic inputs, and leverages insights from these models to develop AI systems with more human-like capacities.