Download
This package represents a community effort to centralize the definition and implementation of loss functions in Julia. As such, it is a part of the JuliaML ecosystem. The sole purpose of this package is to provide an efficient and extensible implementation of various loss functions used throughout Machine Learning (ML). It is thus intended to serve as a special purpose back-end for other ML libraries that require losses to accomplish their tasks. To that end we provide a considerable amount of carefully implemented loss functions, as well as an API to query their properties (e.g. convexity). Furthermore, we expose methods to compute their values, derivatives, and second derivatives for single observations as well as arbitrarily sized arrays of observations. In the case of arrays a user additionally has the ability to define if and how element-wise results are averaged or summed over.
Features
- From an end-user's perspective one normally does not need to import this package directly
- Documentation available
- This code is free to use under the terms of the MIT license
- This package provides a considerable amount of carefully implemented loss functions
- We expose methods to compute their values, derivatives, and second derivatives for single observations
- Julia package that provides efficient and well-tested implementations for a diverse set of loss function
Project Samples
