Direct-Manipulation Visualization of Deep Networks

2017/08/12 by Daniel Smilkov, Shan Carter, Smilkov, Daniel +7 · 6 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Anomaly Detection Techniques and Applications #Cell Image Analysis Techniques #Data Visualization and Analytics #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.1708.03788

openalex publication_date 2017/08/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Object Detectors Emerge in Deep Scene CNNs

Cited by

• Quantum Machine Learning Playground
• Scientific Calculator for Designing Trojan Detectors in Neural Networks
• Single-Photon Image Classification
• Under the Hood of Neural Networks: Characterizing Learned Representations by Functional Neuron Populations and Network Ablations
• A Game-Based Approach for Helping Designers Learn Machine Learning Concepts
• LossPlot: A Better Way to Visualize Loss Landscapes

Related

• In situ TensorView: In situ Visualization of Convolutional Neural Networks
• A Tour of TensorFlow
• Brain Decodes Deep Nets
• TensorFlow: A system for large-scale machine learning
• NeuralDivergence: Exploring and Understanding Neural Networks by Comparing Activation Distributions