SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1711.02085 · 2017

Neural Speed Reading via Skim-RNN

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 0 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.

RepositoryRoleRan
ht1221/leap-lstm pwc_unofficial 0 of 4
FunctionStatusWhere it lives
gumbel_softmax_sample Not yet run ht1221/leap-lstm/skiplstm.py
code served (permissive licence) · get_code("e7121edc84f532e9")
sample_gumbel Not yet run ht1221/leap-lstm/skiplstm.py
code served (permissive licence) · get_code("35b3d781fb8b197b")
update_best_acc Not yet run ht1221/leap-lstm/train_classifier_yelp.py
code served (permissive licence) · get_code("287ebfa206000646")
xavier_weights_variable Not yet run ht1221/leap-lstm/skiplstm.py
code served (permissive licence) · get_code("26b33751bf044c3a")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Inspired by the principles of speed reading, we introduce Skim-RNN, a recurrent neural network (RNN) that dynamically decides to update only a small fraction of the hidden state for relatively unimportant input tokens. Skim-RNN gives computational advantage over an RNN that always updates the entire hidden state. Skim-RNN uses the same input and output interfaces as a standard RNN and can be easily used instead of RNNs in existing models. In our experiments, we show that Skim-RNN can achieve significantly reduced computational cost without losing accuracy compared to standard RNNs across five different natural language tasks. In addition, we demonstrate that the trade-off between accuracy and speed of Skim-RNN can be dynamically controlled during inference time in a stable manner. Our analysis also shows that Skim-RNN running on a single CPU offers lower latency compared to standard RNNs on GPUs.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1711.02085")
get_code_for_paper("1711.02085")
have("1711.02085")

Connect an agent — have() is free.