3 papers
cs.CL2023
Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networks
Yingji Zhang, Danilo S. Carvalho, André Freitas
Disentangled latent spaces usually have better semantic separability and geometrical properties, which leads to better interpretability and more controllable data generation. While…
cs.HC2021
Why scholars are diagramming neural network models
Guy Clarke Marshall, Caroline Jay, Andre Freitas
Complex models, such as neural networks (NNs), are comprised of many interrelated components. In order to represent these models, eliciting and characterising the relations between…
cs.HC2020
A Framework for Improving Scholarly Neural Network Diagrams
Guy Clarke Marshall, André Freitas, Caroline Jay
Neural networks are a prevalent and effective machine learning component, and their application is leading to significant scientific progress in many domains. As the field of neura…