Search Results for author:
Found 4 papers, 0 papers with code
Functorial String Diagrams for Reverse-Mode Automatic Differentiation
We enhance the calculus of string diagrams for monoidal categories with hierarchical features in order to capture closed monoidal (and cartesian closed) structure.
Reparametrizing gradient descent
Our algorithm can also be compared to quasi-Newton methods, but we seek roots rather than stationary points.
Differentiable Causal Computations via Delayed Trace
When $C$ is equipped with a Cartesian differential operator, we construct a differential operator for $St(C)$ using an abstract version of backpropagation through time, a technique from machine learning based on unrolling of functions.
Neural Nets via Forward State Transformation and Backward Loss Transformation
We illustrate this perspective by training a simple instance of a neural network.
