Researcher
Patrick Haffner
Current role not listed
Haffner co-authored the landmark 1998 paper that demonstrated convolutional neural networks in a practical system for reading handwritten checks.[1] The work helped establish the architecture that later transformed computer vision. He also co-created DjVu, a format for compressing scanned documents.[2]
Career & education
Amazon Web Services2021-Aug 2025
AT&T
École Polytechnique
Télécom ParisWork and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Selected contributions
Gradient-Based Learning Applied to Document Recognition
Showed how neural networks could learn to read handwritten characters for document processing.
References
- Gradient Based Learning Applied to Document Recognitionleon.bottou.org
Coauthor-hosted original 1998 paper credits Patrick Haffner and describes convolutional character recognition in a commercially deployed bank-check reader.
- High Quality Document Image Compression with DjVuleon.bottou.org
Original 1998 DjVu paper lists Haffner as coauthor and introduces compression for high-resolution scanned color documents.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 8, 2026 · Checked for accuracy and new information.