We study the problem of efficiently scaling ensemble-based deep neural networks for time series (TS) forecasting on a large set of time series.
Our work focuses on the development of a learnable neural representation of human pose for advanced AI assisted animation tooling.
Regularization, also known in radar literature as sample covariance loading, can be used to combat both ill conditioning of the original problem and contamination of the empirical covariance by the desired signal for the adaptive algorithms based on sample covariance matrix inversion.
Adaptive algorithms based on sample matrix inversion belong to an important class of algorithms used in radar target detection to overcome prior uncertainty of interference covariance.
This paper presents an approach to fast image registration through probabilistic pixel sampling.
This paper presents a novel probabilistic voxel selection strategy for medical image registration in time-sensitive contexts, where the goal is aggressive voxel sampling (e. g. using less than 1% of the total number) while maintaining registration accuracy and low failure rate.
We show that our proposed deep neural network modeling approach based on the deep neural architecture is effective at solving the mid-term electricity load forecasting problem.
Forecasting of multivariate time-series is an important problem that has applications in traffic management, cellular network configuration, and quantitative finance.
Can meta-learning discover generic ways of processing time series (TS) from a diverse dataset so as to greatly improve generalization on new TS coming from different datasets?
Our results show that few-shot segmentation benefits from utilizing word embeddings, and that we are able to perform few-shot segmentation using stacked joint visual semantic processing with weak image-level labels.
Conventional few-shot object segmentation methods learn object segmentation from a few labelled support images with strongly labelled segmentation masks.
We address the problem of learning fine-grained cross-modal representations.
We focus on solving the univariate times series point forecasting problem using deep learning.
Through a series of experiments, we show that by this adaptive combination of the two modalities, our model outperforms current uni-modality few-shot learning methods and modality-alignment methods by a large margin on all benchmarks and few-shot scenarios tested.
We further propose a simple and effective way of conditioning a learner on the task sample set, resulting in learning a task-dependent metric space.