Next, the latent representations for the succeeding instants obtained through non-linear transformations of these context vectors, are contrasted with the latent representations of the encoder for the multi-variables such that the density for the positive pair is maximized.
Each subset consists of network segments, that can be combined and shared across specific tasks.
Knowledge tracing is the task of predicting a learner's future performance based on the history of the learner's performance.
Several techniques for multivariate time series anomaly detection have been proposed recently, but a systematic comparison on a common set of datasets and metrics is lacking.
Deep neural networks have shown promise in several domains, and the learned data (task) specific information is implicitly stored in the network parameters.
Real-world clinical time series data sets exhibit a high prevalence of missing values.
2 code implementations • • Felipe Oviedo, Zekun Ren, Shijing Sun, Charles Settens, Zhe Liu, Noor Titan Putri Hartono, Savitha Ramasamy, Brian L. DeCost, Siyu I. P. Tian, Giuseppe Romano, Aaron Gilad Kusne, Tonio Buonassisi
We overcome the scarce data problem intrinsic to novel materials development by coupling a supervised machine learning approach with a model-agnostic, physics-informed data augmentation strategy using simulated data from the Inorganic Crystal Structure Database (ICSD) and experimental data.
The performance of SEF-M is evaluated against state-of-the-art spiking neural network learning algorithms on 10 benchmark datasets from UCI machine learning repository.
no code implementations • • Zhengyuan Liu, Hazel Lim, Nur Farah Ain Binte Suhaimi, Shao Chuen Tong, Sharon Ong, Angela Ng, Sheldon Lee, Michael R. Macdonald, Savitha Ramasamy, Pavitra Krishnaswamy, Wai Leng Chow, Nancy F. Chen
Data for human-human spoken dialogues for research and development are currently very limited in quantity, variety, and sources; such data are even scarcer in healthcare.
A set of FSFs corresponding to each output class represents the extracted knowledge from the classifier.
We introduce the use of Crystal Graph Convolutional Neural Networks (CGCNN), Fully Connected Neural Networks (FCNN) and XGBoost to predict thermoelectric properties.
The generative learning phase of Autoencoder (AE) and its successor Denosing Autoencoder (DAE) enhances the flexibility of data stream method in exploiting unlabelled samples.
The online generative training begins with zero neurons in the hidden layer, adds and updates the neurons to adapt to statistics of streaming data in a single pass unsupervised manner, resulting in a feature representation best suited to the data.