Vector Field Neural Networks
This work introduces a novel neural network interpretation and architecture, potentially advancing interpretability and performance in machine learning, though it appears incremental as it builds on existing geometrical formalizations.
The authors proposed Vector Field Neural Networks (VFNN), a new architecture based on interpreting neural networks as implicit vector fields moving data particles, and demonstrated that VFNN achieves comparable or better results than basic models like Naive Bayes, Feed Forward Neural Networks, and SVMs on various datasets.
This work begins by establishing a mathematical formalization between different geometrical interpretations of Neural Networks, providing a first contribution. From this starting point, a new interpretation is explored, using the idea of implicit vector fields moving data as particles in a flow. A new architecture, Vector Fields Neural Networks(VFNN), is proposed based on this interpretation, with the vector field becoming explicit. A specific implementation of the VFNN using Euler's method to solve ordinary differential equations (ODEs) and gaussian vector fields is tested. The first experiments present visual results remarking the important features of the new architecture and providing another contribution with the geometrically interpretable regularization of model parameters. Then, the new architecture is evaluated for different hyperparameters and inputs, with the objective of evaluating the influence on model performance, computational time, and complexity. The VFNN model is compared against the known basic models Naive Bayes, Feed Forward Neural Networks, and Support Vector Machines(SVM), showing comparable, or better, results for different datasets. Finally, the conclusion provides many new questions and ideas for improvement of the model that can be used to increase model performance.