Learning Inductive Biases with Simple Neural Networks

Understand

People use rich prior knowledge about the world in order to efficiently learn new concepts.

• These priors - also known as "inductive biases" - pertain to the space of internal models considered by a learner, and they help the learner make inferences that go beyond the observed data.
• A recent study found that deep neural networks optimized for object recognition develop the shape bias (Ritter et al., 2017), an inductive bias possessed by children that plays an important role in early word learning.
• However, these networks use unrealistically large quantities of training data, and the conditions required for these biases to develop are not well understood.