13 datasets found

The dataset used in this paper is a collection of sequences of discrete symbols from the alphabet {a, b}.

We present a technique for providing feedback on syntax errors that uses Recurrent neural networks (RNNs) to model syntactically valid token sequences.

The Character Level Penn Treebank dataset is a benchmark for evaluating the ability of RNNs to model language.

The bAbI Question Answering dataset is a benchmark for evaluating the ability of RNNs to answer questions.

The Associative Recall Task is a benchmark for evaluating the ability of RNNs to recall information from memory.

The dataset used in the paper is the copying memory task, which consists in remembering a sequence of letters from some alphabet A = {ak}N k=1.

A dataset used for training a recurrent neural network (RNN) to infer positional uncertainties for a model predictive control (MPC) algorithm.

Long short-term memory

The dataset used in this paper is a collection of phonetically and phonologically local allophonic distribution in English, where voiceless stops surface as aspirated...

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used various tasks such as Associative Retrieval Task, Maze Exploration, Atari...

Real data recorded from the primary somatosensory cortex of macaques.

Synthetic data generated from a synthetic (teacher) RNN with random parameters. The data is recorded from the primary somatosensory cortex of macaques.

The Long Short-Term Memory (LSTM) dataset is a dataset used for training LSTM models.