What does it mean to understand a neural network?

Abstract

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.

9 pages, 2 figures

References in corpus (8)

• Distilling the Knowledge in a Neural Network
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• On the difficulty of training Recurrent Neural Networks
• Understanding Neural Networks Through Deep Visualization
• Synthesizing Robust Adversarial Examples
• Distilling a Neural Network Into a Soft Decision Tree
• Measuring the Intrinsic Dimension of Objective Landscapes
• Binarized Neural Networks on the ImageNet Classification Task

Cited by in corpus (5)

• Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future
• Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency
• The Utility of Decorrelating Colour Spaces in Vector Quantised Variational Autoencoders
• Rebooting Neuromorphic Hardware Design -- A Complexity Engineering Approach
• Causal Abstractions of Neural Networks