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.
Neural networks are commonly used as models for classification for a wide variety of tasks. Typically, a learned affine transformation is placed at the end of such models, yielding a per-class value used for classification. This classifier can have a vast number of parameters, which grows linearly with the number of possible classes, thus requiring increasingly more resources. In this work we argue that this classifier can be fixed, up to a global scale constant, with little or no loss of accuracy for most tasks, allowing memory and computational benefits. Moreover, we show that by initializing the classifier with a Hadamard matrix we can speed up inference as well. We discuss the implications for current understanding of neural network models.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1801.04540")
get_code_for_paper("1801.04540")
have("1801.04540")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1801.04540.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1801.04540)
Connect an agent — have() is free.