CNN 101: Interactive Visual Learning for Convolutional Neural Networks

• URL: http://arxiv.org/abs/2001.02004v3
• Date: Thu, 27 Feb 2020 16:38:32 GMT
• Title: CNN 101: Interactive Visual Learning for Convolutional Neural Networks
• Authors: Zijie J. Wang, Robert Turko, Omar Shaikh, Haekyu Park, Nilaksh Das, Fred Hohman, Minsuk Kahng, Duen Horng Chau
• Abstract summary: 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.
• Score: 23.369550871258543
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The success of deep learning solving previously-thought hard problems has inspired many non-experts to learn and understand this exciting technology. However, it is often challenging for learners to take the first steps due to the complexity of deep learning models. We present our ongoing work, CNN 101, an interactive visualization system for explaining and teaching convolutional neural networks. Through tightly integrated interactive views, CNN 101 offers both overview and detailed descriptions of how a model works. Built using modern web technologies, CNN 101 runs locally in users' web browsers without requiring specialized hardware, broadening the public's education access to modern deep learning techniques.

Related papers

• Deep Learning with CNNs: A Compact Holistic Tutorial with Focus on Supervised Regression (Preprint) [0.0]
  This tutorial focuses on Convolutional Neural Networks (CNNs) and supervised regression. It not only summarizes the most relevant concepts but also provides an in-depth exploration of each, offering a complete yet agile set of ideas. We aim for this tutorial to serve as an optimal resource for students, professors, and anyone interested in understanding the foundations of Deep Learning.
  arXiv  Detail & Related papers  (2024-08-22T11:34:34Z)
• Mechanistic Neural Networks for Scientific Machine Learning [58.99592521721158]
  We present Mechanistic Neural Networks, a neural network design for machine learning applications in the sciences. It incorporates a new Mechanistic Block in standard architectures to explicitly learn governing differential equations as representations. Central to our approach is a novel Relaxed Linear Programming solver (NeuRLP) inspired by a technique that reduces solving linear ODEs to solving linear programs.
  arXiv  Detail & Related papers  (2024-02-20T15:23:24Z)
• Are Deep Neural Networks SMARTer than Second Graders? [85.60342335636341]
  We evaluate the abstraction, deduction, and generalization abilities of neural networks in solving visuo-linguistic puzzles designed for children in the 6--8 age group. Our dataset consists of 101 unique puzzles; each puzzle comprises a picture question, and their solution needs a mix of several elementary skills, including arithmetic, algebra, and spatial reasoning. Experiments reveal that while powerful deep models offer reasonable performances on puzzles in a supervised setting, they are not better than random accuracy when analyzed for generalization.
  arXiv  Detail & Related papers  (2022-12-20T04:33:32Z)
• Continual Learning, Fast and Slow [75.53144246169346]
  According to the Complementary Learning Systems theory, humans do effective emphcontinual learning through two complementary systems. We propose emphDualNets (for Dual Networks), a general continual learning framework comprising a fast learning system for supervised learning of specific tasks and a slow learning system for representation learning of task-agnostic general representation via Self-Supervised Learning (SSL) We demonstrate the promising results of DualNets on a wide range of continual learning protocols, ranging from the standard offline, task-aware setting to the challenging online, task-free scenario.
  arXiv  Detail & Related papers  (2022-09-06T10:48:45Z)
• 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)
• Draw your Neural Networks [0.0]
  We present Sketch framework, that uses this GUI-based approach to design and modify the neural networks. The system provides popular layers and operations out-of-the-box and could import any supported pre-trained model.
  arXiv  Detail & Related papers  (2020-12-12T09:44:03Z)
• 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)
• CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization [23.369550871258543]
  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.
  arXiv  Detail & Related papers  (2020-04-30T17:49:44Z)
• 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)

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.