Interpretability in Machine Learning: An Overview

 By The Gradient - 2020-11-21

Description

A broad overview of the sub-field of machine learning interpretability; conceptual frameworks, existing research, and future directions.

Summary

  • Interpretability in Machine Learning: transparency as interpretability refers to the model's properties that are useful to understand and can be known before the training begins; By themselves, these weights are hard to interpret.
  • Here, clearly, if the saliency maps look similar, it is more dependent on the input and not the model's parameters.

 

Topics

  1. Machine_Learning (0.23)
  2. NLP (0.19)
  3. Backend (0.08)

Similar Articles

The Model’s Shipped; What Could Possibly go Wrong

By Medium - 2021-02-18

In our last post we took a broad look at model observability and the role it serves in the machine learning workflow. In particular, we discussed the promise of model observability & model monitoring…

pytorch-widedeep: deep learning for tabular data

By Medium - 2021-02-22

This is the third of a series of posts introducing pytorch-widedeepa flexible package to combine tabular data with text and images (that could also be used for “standard” tabular data alone). The…