Filters








2 Hits in 2.6 sec

Backprop as Functor: A compositional perspective on supervised learning [article]

Brendan Fong, David I. Spivak, Rémy Tuyéras
2019 arXiv   pre-print
This provides a structural perspective on backpropagation, as well as a broad generalisation of neural networks.  ...  A supervised learning algorithm searches over a set of functions A → B parametrised by a space P to find the best approximation to some ideal function f A → B.  ...  This paper responds to a need for more structural approaches to machine learning by using categories to provide an algebraic, compositional perspective on learning algorithms and backpropagation.  ... 
arXiv:1711.10455v3 fatcat:m2xi2jtrgrfo7adviem23zopxq

Backprop as Functor: A compositional perspective on supervised learning

Brendan Fong, David Spivak, Remy Tuyeras
2019 2019 34th Annual ACM/IEEE Symposium on Logic in Computer Science (LICS)  
This paper responds to a need for more structural approaches to machine learning by using categories to provide an algebraic, compositional perspective on learning algorithms and backpropagation.  ...  step size, a neural net defines a supervised learning algorithm, and does so in a compositional way.  ... 
doi:10.1109/lics.2019.8785665 dblp:conf/lics/FongST19 fatcat:g7btwbi5frfjliyghc4bkiaakq