Dissonance Between Human and Machine Understanding

01/18/2021
by   Zijian Zhang, et al.
11

Complex machine learning models are deployed in several critical domains including healthcare and autonomous vehicles nowadays, albeit as functional black boxes. Consequently, there has been a recent surge in interpreting decisions of such complex models in order to explain their actions to humans. Models that correspond to human interpretation of a task are more desirable in certain contexts and can help attribute liability, build trust, expose biases and in turn build better models. It is, therefore, crucial to understand how and which models conform to human understanding of tasks. In this paper, we present a large-scale crowdsourcing study that reveals and quantifies the dissonance between human and machine understanding, through the lens of an image classification task. In particular, we seek to answer the following questions: Which (well-performing) complex ML models are closer to humans in their use of features to make accurate predictions? How does task difficulty affect the feature selection capability of machines in comparison to humans? Are humans consistently better at selecting features that make image recognition more accurate? Our findings have important implications on human-machine collaboration, considering that a long term goal in the field of artificial intelligence is to make machines capable of learning and reasoning like humans.

READ FULL TEXT

page 3

page 8

page 13

page 14

page 17

research
10/08/2019

Can We Distinguish Machine Learning from Human Learning?

What makes a task relatively more or less difficult for a machine compar...
research
08/03/2022

On the independence between phenomenal consciousness and computational intelligence

Consciousness and intelligence are properties commonly understood as dep...
research
05/07/2021

Finding the unicorn: Predicting early stage startup success through a hybrid intelligence method

Artificial intelligence is an emerging topic and will soon be able to pe...
research
04/20/2023

Towards a Benchmark for Scientific Understanding in Humans and Machines

Scientific understanding is a fundamental goal of science, allowing us t...
research
12/10/2020

Artificial Intelligence Cooperation

The rise of Artificial Intelligence (AI) will bring with it an ever-incr...
research
08/23/2023

A Theory of Intelligences: Concepts, Models, Implications

Intelligence is a human construct to represent the ability to achieve go...
research
07/18/2021

A pattern recognition approach for distinguishing between prose and poetry

Poetry and prose are written artistic expressions that help us to apprec...

Please sign up or login with your details

Forgot password? Click here to reset