Michael C. Mozer

5 papers · 2020–2024 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🗺️ Taxonomy Completionist (19) 🐣 Hot Topic Early Bird 📈 Trend Setter

Venues

AISTATS (1) CVPR (1) ICCV (1) ICLR (1) NeurIPS (1)

Top co-authors

Rebecca Roelofs (1) Moritz Hardt (1) Samy Bengio (1) Yanlai Yang (1) Mengye Ren (1) Tyler R. Scott (1) Jonathon Shlens (1) Matt Jones (1) Andrew C. Gallagher (1) Nicholas Cain (1)

Research topics

Machine Learning (5) Optimization & Theory (3) Artificial Intelligence (2) Deep Learning (2) Architectures (2) Core AI (2) Core Methods (2) Learning Types · Machine Learning (2) Learning Paradigms (1) Learning Types · Deep Learning (1) Models (1)

Keywords

continual learning (2) catastrophic forgetting (2) multi-task learning (1) transfer learning (1) image retrieval (1) confidence calibration (1) visual classification (1) classification loss (1) convolutional network (1) inductive bia (1) catastrophic interference (1) structured training (1) knowledge recovery (1) model reliability (1) calibration error (1) von mises-fisher distribution (1) parameter scaling (1) sequential training (1) statistical bia (1) softmax classifier (1)

Papers

Reawakening knowledge: Anticipatory recovery from catastrophic interference via structured training NeurIPS 2024 Mitigating Bias in Calibration Error Estimation AISTATS 2022 von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning ICCV 2021 Identity Crisis: Memorization and Generalization Under Extreme Overparameterization ICLR 2020 Sequential Mastery of Multiple Visual Tasks: Networks Naturally Learn to Learn and Forget to Forget CVPR 2020