Direct-Manipulation Visualization of Deep Networks

Abstract

The recent successes of deep learning have led to a wave of interest from non-experts. Gaining an understanding of this technology, however, is difficult. While the theory is important, it is also helpful for novices to develop an intuitive feel for the effect of different hyperparameters and structural variations. We describe TensorFlow Playground, an interactive, open sourced visualization that allows users to experiment via direct manipulation rather than coding, enabling them to quickly build an intuition about neural nets.

References in corpus (1)

• Object Detectors Emerge in Deep Scene CNNs

Cited by in corpus (30)

• CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization
• RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records
• explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning
• Human Factors in Model Interpretability: Industry Practices, Challenges, and Needs
• GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation
• Do Convolutional Neural Networks Learn Class Hierarchy?
• TensorFlow.js: Machine Learning for the Web and Beyond
• Net2Vis -- A Visual Grammar for Automatically Generating Publication-Tailored CNN Architecture Visualizations
• ConfusionFlow: A model-agnostic visualization for temporal analysis of classifier confusion
• Augmented Math: Authoring AR-Based Explorable Explanations by Augmenting Static Math Textbooks
• HyperTendril: Visual Analytics for User-Driven Hyperparameter Optimization of Deep Neural Networks
• CNNComparator: Comparative Analytics of Convolutional Neural Networks
• How do Mixture Density RNNs Predict the Future?
• GAM Coach: Towards Interactive and User-centered Algorithmic Recourse
• AIive: Interactive Visualization and Sonification of Neural Networks in Virtual Reality
• Under the Hood of Neural Networks: Characterizing Learned Representations by Functional Neuron Populations and Network Ablations
• M2Lens: Visualizing and Explaining Multimodal Models for Sentiment Analysis
• Quantum Machine Learning Playground
• exploRNN: Understanding Recurrent Neural Networks through Visual Exploration
• Model-agnostic interpretation by visualization of feature perturbations
• On the Evolution of Neuron Communities in a Deep Learning Architecture
• A Game-Based Approach for Helping Designers Learn Machine Learning Concepts
• Sampling for Deep Learning Model Diagnosis (Technical Report)
• DeepVA: Bridging Cognition and Computation through Semantic Interaction and Deep Learning
• Single-Photon Image Classification
• Interactive Visual Study of Multiple Attributes Learning Model of X-Ray Scattering Images
• LossPlot: A Better Way to Visualize Loss Landscapes
• PREVIS -- A Combined Machine Learning and Visual Interpolation Approach for Interactive Reverse Engineering in Assembly Quality Control
• Diagnostic Visualization for Deep Neural Networks Using Stochastic Gradient Langevin Dynamics
• Scientific Calculator for Designing Trojan Detectors in Neural Networks