Learning on Arbitrary Graph Topologies via Predictive Coding.
Tommaso Salvatori, Luca Pinchetti, Beren Millidge, Yuhang Song, Tian-Yi Bao, Rafał Bogacz, Thomas Lukasiewicz
Abstract
, can be used to flexibly perform different tasks with the same network by simply stimulating specific neurons. This enables the model to be queried on stimuli with different structures, such as partial images, images with labels, or images without labels. We conclude by investigating how the topology of the graph influences the final performance, and comparing against simple baselines trained with BP.
Topics & Concepts
Computer scienceNetwork topologyInferenceBackpropagationArtificial intelligenceNeocortexArtificial neural networkCoding (social sciences)GraphMachine learningTheoretical computer sciencePattern recognition (psychology)AlgorithmMathematicsOperating systemBiologyStatisticsNeuroscienceFunctional Brain Connectivity StudiesNeural dynamics and brain functionFace Recognition and Perception