NeuralArithmetic.jl

Collection of layers that can perform arithmetic operations
Author nmheim
Popularity
3 Stars
Updated Last
11 Months Ago
Started In
January 2020

Neural Arithmetic

Build Status codecov

Collection of layers that can perform arithmetic operations such as addition, subtraction, multiplication, and division in a single layer. Implements NALU, iNALU, NMU & NAU, and NPU.

And additionally FastNAU and FastNPU for use with DiffEqFlux.jl.

Simple Neural Arithmetic

As an example, we can train different layers to learn the function

f(x,y) = (x+y, x*y, 1/x, sqrt(x))

which has two inputs and four outputs. For mo. The figure below plots the error of each layer and arithmetic operation in f for training and testing datapoints. All layers were trained on the input range U(0.1,2). For more details take a look at our paper.

layers

Used By Packages

No packages found.