Learners' Languages
This provides a theoretical framework for understanding machine learning algorithms through category theory, which is incremental on prior work linking backpropagation to functors.
The paper connects deep learning concepts to category theory by showing that parameterized learners can be interpreted as dynamical systems using polynomial functors, and demonstrates this with gradient descent as an example.
In "Backprop as functor", the authors show that the fundamental elements of deep learning -- gradient descent and backpropagation -- can be conceptualized as a strong monoidal functor Para(Euc)$\to$Learn from the category of parameterized Euclidean spaces to that of learners, a category developed explicitly to capture parameter update and backpropagation. It was soon realized that there is an isomorphism Learn$\cong$Para(Slens), where Slens is the symmetric monoidal category of simple lenses as used in functional programming. In this note, we observe that Slens is a full subcategory of Poly, the category of polynomial functors in one variable, via the functor $A\mapsto Ay^A$. Using the fact that (Poly,$\otimes$) is monoidal closed, we show that a map $A\to B$ in Para(Slens) has a natural interpretation in terms of dynamical systems (more precisely, generalized Moore machines) whose interface is the internal-hom type $[Ay^A,By^B]$. Finally, we review the fact that the category p-Coalg of dynamical systems on any $p \in$ Poly forms a topos, and consider the logical propositions that can be stated in its internal language. We give gradient descent as an example, and we conclude by discussing some directions for future work.