conftrace_

Isha Garg

4 papers · 2021–2024 · 4 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 · Bronze 🌉 Interdisciplinary Bridge · Bronze

Venues

CVPR (1) ICCV (1) ICLR (1) ICML (1)

Top co-authors

Kaushik Roy (4) Sayeed Shafayet Chowdhury (1) Deepak Ravikumar (1) Gobinda Saha (1)

Research topics

Machine Learning (4) Optimization & Theory (3) Deep Learning (2) Architectures (2) Learning Types (2) Artificial Intelligence (1) Computer Vision (1) Analysis (1) Core AI (1) Core Methods (1)

Keywords

image classification (1) continual learning (1) temporal coding (1) coreset selection (1) gradient descent (1) singular value decomposition (1) second-order optimization (1) curvature (1) spiking neural network (1) deep neural network (1) loss function (1) data efficiency (1) surrogate gradient (1) discrete cosine transform (1) loss curvature (1) weight consolidation (1) neural network (1) training sample (1) orthogonal gradient (1) memorization (1)

Papers

Memorization Through the Lens of Curvature of Loss Function Around Samples ICML 2024 Samples With Low Loss Curvature Improve Data Efficiency CVPR 2023 DCT-SNN: Using DCT To Distribute Spatial Information Over Time for Low-Latency Spiking Neural Networks ICCV 2021 Gradient Projection Memory for Continual Learning ICLR 2021