CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization

• URL: http://arxiv.org/abs/2004.15004v3
• Date: Fri, 28 Aug 2020 18:42:23 GMT
• Title: CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization
• Authors: Zijie J. Wang, Robert Turko, Omar Shaikh, Haekyu Park, Nilaksh Das, Fred Hohman, Minsuk Kahng, Duen Horng Chau
• Abstract summary: We present CNN Explainer, an interactive visualization tool designed for non-experts to learn and examine convolutional neural networks (CNNs) 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 helps users more easily understand the inner workings of CNNs, and is engaging and enjoyable to use.
• Score: 23.369550871258543
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends [5.76466022747257]
  Convolutional Neural Networks (CNNs) are used for various computer vision tasks such as image classification, object detection, and image segmentation. There are numerous types of CNNs designed to meet specific needs and requirements, including 1D, 2D, and 3D CNNs. It's crucial to gain a thorough understanding and perform a comparative analysis of these different CNN types to understand their strengths and weaknesses.
  arXiv  Detail & Related papers  (2024-02-23T18:28:57Z)
• Transferability of Convolutional Neural Networks in Stationary Learning Tasks [96.00428692404354]
  We introduce a novel framework for efficient training of convolutional neural networks (CNNs) for large-scale spatial problems. We show that a CNN trained on small windows of such signals achieves a nearly performance on much larger windows without retraining. Our results show that the CNN is able to tackle problems with many hundreds of agents after being trained with fewer than ten.
  arXiv  Detail & Related papers  (2023-07-21T13:51:45Z)
• Deeply Explain CNN via Hierarchical Decomposition [75.01251659472584]
  In computer vision, some attribution methods for explaining CNNs attempt to study how the intermediate features affect the network prediction. This paper introduces a hierarchical decomposition framework to explain CNN's decision-making process in a top-down manner.
  arXiv  Detail & Related papers  (2022-01-23T07:56:04Z)
• Assessing learned features of Deep Learning applied to EEG [0.0]
  We use 3 different methods to extract EEG-relevant features from a CNN trained on raw EEG data. We show that visualization of a CNN model can reveal interesting EEG results.
  arXiv  Detail & Related papers  (2021-11-08T07:43:40Z)
• Explainability via Interactivity? Supporting Nonexperts' Sensemaking of Pretrained CNN by Interacting with Their Daily Surroundings [7.455054065013047]
  We present a mobile application to support nonexperts to interactively make sense of Convolutional Neural Networks (CNN) It allows users to play with a pretrained CNN by taking pictures of their surrounding objects. We use an up-to-date XAI technique (Class Activation Map) to intuitively visualize the model's decision.
  arXiv  Detail & Related papers  (2021-05-31T19:22:53Z)
• Learning Contact Dynamics using Physically Structured Neural Networks [81.73947303886753]
  We use connections between deep neural networks and differential equations to design a family of deep network architectures for representing contact dynamics between objects. We show that these networks can learn discontinuous contact events in a data-efficient manner from noisy observations. Our results indicate that an idealised form of touch feedback is a key component of making this learning problem tractable.
  arXiv  Detail & Related papers  (2021-02-22T17:33:51Z)
• The Mind's Eye: Visualizing Class-Agnostic Features of CNNs [92.39082696657874]
  We propose an approach to visually interpret CNN features given a set of images by creating corresponding images that depict the most informative features of a specific layer. Our method uses a dual-objective activation and distance loss, without requiring a generator network nor modifications to the original model.
  arXiv  Detail & Related papers  (2021-01-29T07:46:39Z)
• Understanding the Role of Individual Units in a Deep Neural Network [85.23117441162772]
  We present an analytic framework to systematically identify hidden units within image classification and image generation networks. First, we analyze a convolutional neural network (CNN) trained on scene classification and discover units that match a diverse set of object concepts. Second, we use a similar analytic method to analyze a generative adversarial network (GAN) model trained to generate scenes.
  arXiv  Detail & Related papers  (2020-09-10T17:59:10Z)
• An Information-theoretic Visual Analysis Framework for Convolutional Neural Networks [11.15523311079383]
  We introduce a data model to organize the data that can be extracted from CNN models. We then propose two ways to calculate entropy under different circumstances. We develop a visual analysis system, CNNSlicer, to interactively explore the amount of information changes inside the model.
  arXiv  Detail & Related papers  (2020-05-02T21:36:50Z)
• Curriculum By Smoothing [52.08553521577014]
  Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation. We propose an elegant curriculum based scheme that smoothes the feature embedding of a CNN using anti-aliasing or low-pass filters. As the amount of information in the feature maps increases during training, the network is able to progressively learn better representations of the data.
  arXiv  Detail & Related papers  (2020-03-03T07:27:44Z)
• CNN 101: Interactive Visual Learning for Convolutional Neural Networks [23.369550871258543]
  CNN 101 is an interactive visualization system for explaining and teaching convolutional neural networks. Built using modern web technologies, CNN 101 runs locally in users' web browsers without requiring specialized hardware.
  arXiv  Detail & Related papers  (2020-01-07T12:46:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.