Search Results for author:
Found 16 papers, 5 papers with code
CompeteSMoE - Effective Training of Sparse Mixture of Experts via Competition
Sparse mixture of experts (SMoE) offers an appealing solution to scale up the model complexity beyond the mean of increasing the network's depth or width.
Dynamic Long-Term Time-Series Forecasting via Meta Transformer Networks
A slow learner tailors suitable representations to fast learners.
HyperRouter: Towards Efficient Training and Inference of Sparse Mixture of Experts
By routing input tokens to only a few split experts, Sparse Mixture-of-Experts has enabled efficient training of large language models.
Contrastive predictive coding for Anomaly Detection in Multi-variate Time Series Data
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.
PaRT: Parallel Learning Towards Robust and Transparent AI
Each subset consists of network segments, that can be combined and shared across specific tasks.
Incremental Knowledge Tracing from Multiple Schools
Knowledge tracing is the task of predicting a learner's future performance based on the history of the learner's performance.
An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Series
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.
Knowledge Capture and Replay for Continual Learning
Deep neural networks have shown promise in several domains, and the learned data (task) specific information is implicitly stored in the network parameters.
Bayesian Recurrent Framework for Missing Data Imputation and Prediction with Clinical Time Series
Real-world clinical time series data sets exhibit a high prevalence of missing values.
Fast classification of small X-ray diffraction datasets using data augmentation and deep neural networks
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.
Efficient single input-output layer spiking neural classifier with time-varying weight model
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.
Fast Prototyping a Dialogue Comprehension System for Nurse-Patient Conversations on Symptom Monitoring
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 novel method for extracting interpretable knowledge from a spiking neural classifier with time-varying synaptic weights
A set of FSFs corresponding to each output class represents the extracted knowledge from the classifier.
Predicting thermoelectric properties from crystal graphs and material descriptors - first application for functional materials
We introduce the use of Crystal Graph Convolutional Neural Networks (CGCNN), Fully Connected Neural Networks (FCNN) and XGBoost to predict thermoelectric properties.
Autonomous Deep Learning: Incremental Learning of Denoising Autoencoder for Evolving Data Streams
The generative learning phase of Autoencoder (AE) and its successor Denosing Autoencoder (DAE) enhances the flexibility of data stream method in exploiting unlabelled samples.
Online Deep Learning: Growing RBM on the fly
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.
