Author or contributor
Publication year

Algebraic Machine Learning

Resource type
Algebraic Machine Learning
Machine learning algorithms use error function minimization to fit a large set of parameters in a preexisting model. However, error minimization eventually leads to a memorization of the training dataset, losing the ability to generalize to other datasets. To achieve generalization something else is needed, for example a regularization method or stopping the training when error in a validation dataset is minimal. Here we propose a different approach to learning and generalization that is parameter-free, fully discrete and that does not use function minimization. We use the training data to find an algebraic representation with minimal size and maximal freedom, explicitly expressed as a product of irreducible components. This algebraic representation is shown to directly generalize, giving high accuracy in test data, more so the smaller the representation. We prove that the number of generalizing representations can be very large and the algebra only needs to find one. We also derive and test a relationship between compression and error rate. We give results for a simple problem solved step by step, hand-written character recognition, and the Queens Completion problem as an example of unsupervised learning. As an alternative to statistical learning, algebraic learning may offer advantages in combining bottom-up and top-down information, formal concept derivation from data and large-scale parallelization.
arXiv:1803.05252 [cs, math]
Library Catalog
arXiv: 1803.05252
Comment: In v2 Figures 10 and 12 are images (v1 used latex commands), so all queens on board are now visible
Martin-Maroto, F., & de Polavieja, G. G. (2018). Algebraic Machine Learning. ArXiv:1803.05252 [Cs, Math]. Retrieved from
Processing time: 0.02 seconds

Graph of references

(from Zotero to Gephi via Zotnet with this script)
Graph of references