We lifted 3 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| robertcsordas/dnc | reimplementation | 3 of 3 |
| Function | Status | Where it lives |
|---|---|---|
| get_next_tensor_part | Ran | robertcsordas/dnc/Models/DNC.py pointer only (licence: NONE) · get_code("ebe66795a77923f4") |
| oneplus | Ran | robertcsordas/dnc/Models/DNC.py pointer only (licence: NONE) · get_code("e01e65f9ba6e05c0") |
| split_tensor | Ran | robertcsordas/dnc/Models/DNC.py pointer only (licence: NONE) · get_code("f2182cc8ab206d54") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The Differentiable Neural Computer (DNC) can learn algorithmic and question answering tasks. An analysis of its internal activation patterns reveals three problems: Most importantly, the lack of key-value separation makes the address distribution resulting from content-based look-up noisy and flat, since the value influences the score calculation, although only the key should. Second, DNC's de-allocation of memory results in aliasing, which is a problem for content-based look-up. Thirdly, chaining memory reads with the temporal linkage matrix exponentially degrades the quality of the address distribution. Our proposed fixes of these problems yield improved performance on arithmetic tasks, and also improve the mean error rate on the bAbI question answering dataset by 43%.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1904.10278")
get_code_for_paper("1904.10278")
have("1904.10278")
Connect an agent — have() is free.