4 papers
Inverting Non-Injective Functions with Twin Neural Network Regression
Sebastian J. Wetzel
Non-injective functions are not globally invertible. However, they can often be restricted to locally injective subdomains where the inversion is well-defined. In many settings a p…
Closed-Form Interpretation of Neural Network Latent Spaces with Symbolic Gradients
Sebastian J. Wetzel, Zakaria Patel
It has been demonstrated that artificial neural networks like autoencoders or Siamese networks encode meaningful concepts in their latent spaces. However, there does not exist a co…
Interpretable Machine Learning in Physics: A Review
Sebastian Johann Wetzel, Seungwoong Ha, Raban Iten +2
Machine learning is increasingly transforming various scientific fields, enabled by advancements in computational power and access to large data sets from experiments and simulatio…
Closed-Form Interpretation of Neural Network Classifiers with Symbolic Gradients
Sebastian Johann Wetzel
I introduce a unified framework for finding a closed-form interpretation of any single neuron in an artificial neural network. Using this framework I demonstrate how to interpret n…