ML-o-Scope: A Diagnostic Visualization System for Deep Machine Learning Pipelines

Abstract

The recent success of deep learning is driving a trend towards structurally complex computer vision models that combine feature extraction with predictive elements into integrated pipelines. While some of these models have achieved breakthrough results in applications like object recognition, they are difficult to design and tune, impeding progress. We feel that visual analysis can be a powerful tool to aid iterative development of deep model pipelines. Building on feature evaluation work in the computer vision community, we introduce ML-o-scope, an interactive visualization system for exploratory analysis of convolutional neural networks, a prominent type of pipelined model. We present ML-o-scope's time-lapse engine that provides views into model dynamics during training, and evaluate the system as a support for tuning large scale object-classification pipelines.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 16, 2014
Accession Number
ADA605112

Entities

People

  • Daniel Bruckner

Organizations

  • University of California, Berkeley

Tags

Communities of Interest

  • Autonomy
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence Software
  • Automata Theory
  • Computer Science
  • Computer Vision
  • Computers
  • Convolutional Neural Networks
  • Data Sets
  • Deep Learning
  • Dimensionality Reduction
  • Electrical Engineering
  • Feature Extraction
  • Image Processing
  • Information Science
  • Machine Learning
  • Network Science
  • Neural Networks

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Computer Vision.
  • Distributed Systems and Data Platform Development

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks