What does it mean to understand a neural network?
This is an incremental conceptual analysis for AI and neuroscience researchers.
The paper argues that neural networks are easier to understand through their code than their trained properties like weights, drawing an analogy to neuroscience to suggest a focus on learning and development.
We can define a neural network that can learn to recognize objects in less than 100 lines of code. However, after training, it is characterized by millions of weights that contain the knowledge about many object types across visual scenes. Such networks are thus dramatically easier to understand in terms of the code that makes them than the resulting properties, such as tuning or connections. In analogy, we conjecture that rules for development and learning in brains may be far easier to understand than their resulting properties. The analogy suggests that neuroscience would benefit from a focus on learning and development.