Hypertransfer in Neural Networks

Abstract

The Osgood surface for transfer in human associative learning is introduced (Osgood, 1949). It describes the relationship between stimulus and response similarities and transfer of learning. In this paradigm, first a list A is learned, then a list B, followed by retesting on list A. Simulation results indicate that three-layer networks with backpropagation do not only show 'catastrophic interference' but also 'hypertransfer'. Two-layer networks do not suffer from this. Hypertransfer is explained with reference to hidden-layer representations formed during learning. Since it cannot account for this very general trait of human behavior, backpropagation's role as a tool for models of human memory must be watched very carefully.

Keywords:

• Hypertransfer
• Catastrophic Interference
• Backpropagation
• Human Memory
• Sequential Learning
• Osgood Surface
• Transfer Of Learning