We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Catastrophic forgetting occurs when a neural network loses the information learned in a previous task after training on subsequent tasks. This problem remains a hurdle for artificial intelligence systems with sequential learning capabilities. In this paper, we propose a task-based hard attention mechanism that preserves previous tasks' information without affecting the current task's learning. A hard attention mask is learned concurrently to every task, through stochastic gradient descent, and previous masks are exploited to condition such learning. We show that the proposed mechanism is effective for reducing catastrophic forgetting, cutting current rates by 45 to 80%. We also show that it is robust to different hyperparameter choices, and that it offers a number of monitoring capabilities. The approach features the possibility to control both the stability and compactness of the learned knowledge, which we believe makes it also attractive for online learning or network compression applications.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1801.01423")
get_code_for_paper("1801.01423")
have("1801.01423")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1801.01423.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1801.01423)
Connect an agent — have() is free.