A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
CN-DPM model tackles task-free continual learning for neural networks.
GMED edits stored examples to improve continual learning.
Graph-based rehearsal improves continual learning performance.
Prototype-based generative replay framework for online continual regression.
This work tackles online memory selection in continual learning using information theory.
Methods proposed in the literature towards continual deep learning typically operate in a task-based sequential learning setup. A sequence of tasks is learned, one at a time, with all data of current task available but not of previous or future tasks. Task boundaries and identities are known at all times. This setup, h…