
Researcher
Flatiron InstituteVisiting Scholar
🇫🇷 FrenchBorn 1965
Flatiron Institute2026-presentWork and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Showed how neural networks could learn to read handwritten characters for document processing.
Author research overview documents decades of work on stochastic gradient learning, practical large-scale training, and neural-network optimization, with linked original papers and software.
DjVu: Scanned Documents on the Web supports the anchored contribution. Existing stochastic-gradient source and anchor preserved. Author-hosted DjVu design/history and original co-authored publication list verified; existing prose preserved. Unexplained stochastic gradient descent remains 5/10 technical: recommended future wording describes learning from small samples, but references-only request does not authorize flattening contribution.
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 September 5, 2026 · Checked for accuracy and new information.