neural networks - Alta Cognita

Sign in Subscribe

neural networks

A collection of 6 posts

Robust Attribution Regularization

adversarial Featured

Robust Attribution Regularization

Recent work on training neural networks to have robust attributions, to improve their trustworthiness and resilience to adversarial attacks.

Probing Deep Network Behavior with Internal Influence

Probing Deep Network Behavior with Internal Influence

In recent work with my colleagues at CMU, we focus on bringing greater transparency to these mysterious, yet effective, machine learning techniques.

Explainability in Neural Networks, Part 4: Path Methods for Feature Attribution

deep learning Featured

Explainability in Neural Networks, Part 4: Path Methods for Feature Attribution

This post will delve deeper into Path Integrated Gradient Methods for Feature Attribution in Neural Networks.

Explainability in Neural Networks, Part 3: The Axioms of Attribution

deep learning Featured

Explainability in Neural Networks, Part 3: The Axioms of Attribution

In this third post of the series on Explainability in Neural Networks, we present Axioms of Attribution, which are a set of desirable properties that any reasonable feature-attribution method should have.

Explainability in Neural Networks, Part 2: Limitations of Simple Feature Attribution Methods

deep learning Featured

Explainability in Neural Networks, Part 2: Limitations of Simple Feature Attribution Methods

We examine some simple, intuitive methods to explain the output of a neural network (based on perturbations and gradients), and see how they produce non-sensical results for non-linear functions.

Explainability in Deep Neural Networks

deep learning Featured

Explainability in Deep Neural Networks

The wild success of Deep Neural Network (DNN) models in a variety of domains has created considerable excitement in the machine learning community. Despite this success, a deep understanding of why DNNs perform so well, and whether their performance is somehow brittle, has been lacking.