Algorithm for preventing 'undesirable behavior' works in gender fairness and health tests

November 21, 2019

A new framework for designing machine learning algorithms helps to prevent intelligent machines from exhibiting undesirable behavior, researchers report. The framework, which was tested in a bias and also a health context, achieves this feat by shifting the burden of avoiding the undesirable behavior from the user (most often not a computer scientist) to the algorithm designer. Making "well-behaved" algorithms using the new framework will not only improve machine learning tools broadly but could also pave the way for new opportunities of use, particularly in applications where machine learning was previously considered too risky. From medical diagnoses to financial predictions, machine learning (ML) algorithms are becoming an ever more ubiquitous tool. Given their increasing mastery of various tasks - many of which could directly impact the quality of life - it is critical to ensure that they do not exhibit undesirable behavior, including that which could cause harm to humans. Examples of algorithms exhibiting discriminatory biases or delaying medical diagnoses are known. Standard ML approaches require that users specify and encode constraints on an algorithm to preclude unwanted behavior. However, many users lack the knowledge of ML and statistics required to do so. Because of this, the safe and responsible use of ML can be difficult in some critical applications. To address this problem, Phillip Thomas and colleagues present a framework for designing ML algorithms that shifts the burden from the user to the designer. Instead of the user needing to encode constraints on the algorithm's behavior, work that requires extensive domain knowledge or additional data analysis, Thomas et al.'s approach makes this process one the user can do much more easily, without requiring additional complex data analysis. The authors demonstrate the benefits of their approach by designing ML algorithms and applying them to examples in gender fairness and diabetes management. Their algorithms precluded the dangerous behavior caused by standard machine learning algorithms in these settings, they show.

American Association for the Advancement of Science

Related Behavior Articles from Brightsurf:

Variety in the migratory behavior of blackcaps
The birds have variable migration strategies.

Fishing for a theory of emergent behavior
Researchers at the University of Tsukuba quantified the collective action of small schools of fish using information theory.

How synaptic changes translate to behavior changes
Learning changes behavior by altering many connections between brain cells in a variety of ways all at the same time, according to a study of sea slugs recently published in JNeurosci.

I won't have what he's having: The brain and socially motivated behavior
Monkeys devalue rewards when they anticipate that another monkey will get them instead.

Unlocking animal behavior through motion
Using physics to study different types of animal motion, such as burrowing worms or flying flocks, can reveal how animals behave in different settings.

AI to help monitor behavior
Algorithms based on artificial intelligence do better at supporting educational and clinical decision-making, according to a new study.

Increasing opportunities for sustainable behavior
To mitigate climate change and safeguard ecosystems, we need to make drastic changes in our consumption and transport behaviors.

Predicting a protein's behavior from its appearance
Researchers at EPFL have developed a new way to predict a protein's interactions with other proteins and biomolecules, and its biochemical activity, merely by observing its surface.

Spirituality affects the behavior of mortgagers
According to Olga Miroshnichenko, a Sc.D in Economics, and a Professor at the Department of Economics and Finance, Tyumen State University, morals affect the thinking of mortgage payers and help them avoid past due payments.

Asking if behavior can be changed on climate crisis
One of the more complex problems facing social psychologists today is whether any intervention can move people to change their behavior about climate change and protecting the environment for the sake of future generations.

Read More: Behavior News and Behavior Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to