-
Synthesizing Obama
A dataset of videos of Barack Obama synthesized using a recurrent neural network. -
Doctor AI: Predicting Clinical Events
The dataset is a longitudinal time-stamped EHR data from 260K patients over 8 years. Encounter records (e.g. diagnosis codes, medication codes or procedure codes) were input to... -
Dialogue state tracking using recurrent neural networks
Dialogue state tracking using recurrent neural networks (RNN) on the standard dialogue state tracking (DST) dataset, DSTC2 -
Character Level Penn Treebank dataset
The Character Level Penn Treebank dataset is a benchmark for evaluating the ability of RNNs to model language. -
bAbI Question Answering dataset
The bAbI Question Answering dataset is a benchmark for evaluating the ability of RNNs to answer questions. -
Associative Recall Task
The Associative Recall Task is a benchmark for evaluating the ability of RNNs to recall information from memory. -
Copying Memory Task
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. -
Rotational Unit of Memory
The Rotational Unit of Memory (RUM) is a novel RNN architecture that combines unitary evolution matrices and associative memory to improve long-term memory capabilities. -
Visual-Inertial Odometry (VIO) dataset
A dataset used for training a recurrent neural network (RNN) to infer positional uncertainties for a model predictive control (MPC) algorithm. -
TIMIT dataset
The dataset used in this paper is a collection of phonetically and phonologically local allophonic distribution in English, where voiceless stops surface as aspirated... -
Training Recurrent Neural Networks via Dynamical Trajectory-Based Optimization
The dataset used in this paper is a recurrent neural network with one hidden layer. The structure of the network is shown in Fig. 1. The input-output relation of the network is... -
Suicidal Ideation from Multiple Source Data
A dataset of Electronic Health Records (EHR) and Ecological Momentary Assessment (EMA) data used to predict suicidal ideation. -
Red Cell Dynamics Dataset
The dataset is used for classification of red cell dynamics with convolutional and recurrent neural networks. -
Somatosensory cortex data
Real data recorded from the primary somatosensory cortex of macaques. -
Synthetic RNN task
Synthetic data generated from a synthetic (teacher) RNN with random parameters. The data is recorded from the primary somatosensory cortex of macaques. -
Diffusion Convolutional Recurrent Neural Network
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting