Rupesh Kumar Srivastava

Rupesh Kumar Srivastava has 3 papers in our library, in 2015–2016; often with Jurgen Schmidhuber, Jan Koutnik, Klaus Greff.

3 papers in our library · 2015–2016

No OpenAlex profile matched yet.

The profile is the library's match of the name; two people with one name are not always told apart.

Fields, topics and concepts

Of its works in our library, with the number of works on each.

The most cited first (OpenAlex and our library).

LSTM: A Search Space Odyssey (2015 · 7,008 citations)
Since its introduction in the mid-1990s, LSTM has accumulated many architectural modifications, but no one had systematically tested which of its parts actually matter.
Highway Networks (2015 · 680 citations)
Deeper neural networks tend to perform better, but plain feedforward stacks get much harder to train with gradient descent as layers are added, even with careful variance-preserving initialization.
Recurrent Highway Networks (2016 · 147 citations)
Recurrent networks usually update their hidden state with a single nonlinear step per time step. Making this step-to-step transition deeper should add modeling power, but such models have very long gradient paths and are hard to train, even when built from LSTM cells. Zilly et al. study this problem using Geršgorin's…

3 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 356 times (of the 149,439 papers whose bibliographies we read); 57 citing papers with a page here →.

Updated 2 November 2026