How do we interpret the outputs of a neural network trained on classification?
Name
YudiXie_How_do_we_interpret_the_outputs_of_a_neural_network_trained_on_classification.pdf
Size
2.52 MB
Format
Adobe PDF
Checksum (MD5)
d791dd3d5743fae6e4a255997eed2a35
Author(s)
Xie, Yudi
Date Issued
April 28, 2025
Publisher
International Conference on Learning Representations
Citation
Xie, Yudi. 2025. "How do we interpret the outputs of a neural network trained on classification?."
Version
Author's final manuscript
Abstract
Deep neural networks are widely used for classification tasks, but the interpretation of their output activations is often unclear. This tutorial article explains
how these outputs can be understood as approximations of the Bayesian posterior.
We showed that, in theory, the loss function for classification tasks – derived by
maximum likelihood – is minimized by the Bayesian posterior. We conducted
empirical studies training neural networks to classify synthetic data from a known
generative model. In a simple classification task, the network closely approximates the theoretically derived posterior. However, a few changes in the task can
make accurate approximation much more difficult. The ability of the networks to
approximate the posterior depends on multiple factors, such as the complexity of
the posterior and whether there is sufficient data for learning.
Description
Blogposts Track. ICLR 2025, 24-28 April, Singapore.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Creative Commons Attribution-Noncommercial-ShareAlike
Persistent DSpace Link
