Human-to-AI Coach: Improving Human Inputs to AI Systems

TL;DR

This paper proposes a method to modify human inputs to AI systems to reduce misinterpretation and improve efficiency, using a conditional autoencoder to generate altered inputs that are similar to originals but more effective.

Contribution

It introduces a novel approach using a conditional convolutional autoencoder to optimize human inputs for better AI interpretation while maintaining input similarity.

Findings

Generated inputs often reduce error rates

Altered inputs require less effort to produce

Modified inputs remain similar to original samples

Abstract

Humans increasingly interact with Artificial intelligence(AI) systems. AI systems are optimized for objectives such as minimum computation or minimum error rate in recognizing and interpreting inputs from humans. In contrast, inputs created by humans are often treated as a given. We investigate how inputs of humans can be altered to reduce misinterpretation by the AI system and to improve efficiency of input generation for the human while altered inputs should remain as similar as possible to the original inputs. These objectives result in trade-offs that are analyzed for a deep learning system classifying handwritten digits. To create examples that serve as demonstrations for humans to improve, we develop a model based on a conditional convolutional autoencoder (CCAE). Our quantitative and qualitative evaluation shows that in many occasions the generated proposals lead to lower error rates, require less effort to create and differ only modestly from the original samples.