Artificial intelligence continues to increase in popularity. As a result, several new approaches to AI education have emerged in recent years. Many existing interactive techniques utilize camera and microphone sensors to engage students with educational activities focused on machine learning and AI. However, the use of physiological sensors for AI/ML education activities is significantly unexplored. This paper presents findings from a study exploring students’ experiences learning basic machine learning concepts while using physiological sensors to control an interactive game. In particular, the sensors measured electrical activity generated from students’ arm muscles. We also discuss PhysioML, a web-based software program that guides students through understanding ML and physiological data via a visual interface. Results from our study suggest that activities featuring physiological sensors significantly improved students’ knowledge of AI/ML concepts. However, we did not observe significant differences in students’ knowledge during activities involving traditional data types. Our performance-based assessment did not show a significant overall difference between physiological sensors and image-based activities. While students’ AI/ML self-efficacy increased in both conditions, they seemed more curious about the technology after working with the physiological sensor due to its novelty. We discuss these findings and reflect on ways physiological sensors may be used to augment traditional data types during classroom activities focused on AI and machine learning.