Learning Data Driven Representations from Large Collections of Multidimensional Patterns with Minimal Supervision

Abstract

Traditionally, taking experimental measurements of a physical or biological phenomenon was an expensive, laborious and very slow process. However, significant advances in device technologies and computational techniques have sharply reduced the costs of data collection. Capturing thousands of images of developing biological organisms, or recording enormous amounts of video footage from a network of cameras monitoring an observation space, or obtaining a large number of neural measurements of brain signal patterns via non-invasive devices are some of the examples of such data proliferation. Analyzing such large volumes of multi-dimensional data through expert supervision is neither scalable nor cost-effective. In this context, there is a need for systems that complement the expert user by learning meaningful and compact representations from large collections of multidimensional data (images, videos etc.) with minimal supervision. In this dissertation, we present minimally supervised solutions to two such scenarios generally encountered.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 04, 2008
Accession Number
ADA518662

Entities

People

  • Parvez Ahammad

Organizations

  • University of California, Berkeley

Tags

Communities of Interest

  • Biomedical

DTIC Thesaurus Topics

  • Brain
  • Computational Science
  • Computer Vision
  • Data Mining
  • Detectors
  • Diagnostic Imaging
  • Dna Microarrays
  • Electrical Engineering
  • Gaussian Distributions
  • Health Services
  • Information Processing
  • Information Science
  • Pattern Recognition
  • Probability Distributions
  • Signal Processing
  • Supervised Machine Learning
  • Three Dimensional

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Economics
  • Geodesy

Technology Areas

  • Space