We lifted 1 functions out of this paper's own repositories and ran 1 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 |
|---|---|---|
| jiamings/fast-weights | reimplementation | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| get_one_hot | Ran | jiamings/fast-weights/generator.py pointer only (licence: NONE) · get_code("1e3e05f637d7c45d") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Until recently, research on artificial neural networks was largely restricted to systems with only two types of variable: Neural activities that represent the current or recent input and weights that learn to capture regularities among inputs, outputs and payoffs. There is no good reason for this restriction. Synapses have dynamics at many different time-scales and this suggests that artificial neural networks might benefit from variables that change slower than activities but much faster than the standard weights. These "fast weights" can be used to store temporary memories of the recent past and they provide a neurally plausible way of implementing the type of attention to the past that has recently proved very helpful in sequence-to-sequence models. By using fast weights we can avoid the need to store copies of neural activity patterns.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1610.06258")
get_code_for_paper("1610.06258")
have("1610.06258")
Connect an agent — have() is free.