CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization

TLDR

Deep learning’s success has spurred widespread interest, yet beginners often struggle to grasp its concepts because of its inherent complexity. The authors introduce CNN Explainer, an interactive visualization tool that enables non‑experts to learn and explore convolutional neural networks. CNN Explainer addresses novices’ challenges by offering a model overview and dynamic visual explanations that smoothly transition between low‑level operations and high‑level structures, and it runs locally in web browsers without installation. A qualitative user study found that CNN Explainer improves users’ understanding of CNNs while being engaging and enjoyable, and the authors extracted several design lessons.

Abstract

Deep learning's great success motivates many practitioners and students to learn about this exciting technology. However, it is often challenging for beginners to take their first step due to the complexity of understanding and applying deep learning. We present CNN Explainer, an interactive visualization tool designed for non-experts to learn and examine convolutional neural networks (CNNs), a foundational deep learning model architecture. Our tool addresses key challenges that novices face while learning about CNNs, which we identify from interviews with instructors and a survey with past students. CNN Explainer tightly integrates a model overview that summarizes a CNN's structure, and on-demand, dynamic visual explanation views that help users understand the underlying components of CNNs. Through smooth transitions across levels of abstraction, our tool enables users to inspect the interplay between low-level mathematical operations and high-level model structures. A qualitative user study shows that CNN Explainer helps users more easily understand the inner workings of CNNs, and is engaging and enjoyable to use. We also derive design lessons from our study. Developed using modern web technologies, CNN Explainer runs locally in users' web browsers without the need for installation or specialized hardware, broadening the public's education access to modern deep learning techniques.