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.
Continual learning - learning new tasks in sequence while maintaining performance on old tasks - remains particularly challenging for artificial neural networks. Surprisingly, the amount of forgetting does not increase with the dissimilarity between the learned tasks, but appears to be worst in an intermediate similarity regime. In this paper we theoretically analyse both a synthetic teacher-student framework and a real data setup to provide an explanation of this phenomenon that we name Maslow's hammer hypothesis. Our analysis reveals the presence of a trade-off between node activation and node re-use that results in worst forgetting in the intermediate regime. Using this understanding we reinterpret popular algorithmic interventions for catastrophic interference in terms of this trade-off, and identify the regimes in which they are most effective.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2205.09029")
get_code_for_paper("2205.09029")
have("2205.09029")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2205.09029.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2205.09029)
Connect an agent — have() is free.