• Publications
  • Influence
Deep learning for time series classification: a review
TLDR
We study the current state-of-the-art performance of deep learning algorithms for TSC by presenting an empirical study of the most recent DNN architectures for time series classification. Expand
InceptionTime: Finding AlexNet for Time Series Classification
TLDR
We present InceptionTime---an ensemble of deep Convolutional Neural Network (CNN) models, inspired by the Inception-v4 architecture. Expand
Dynamic Time Warping Averaging of Time Series Allows Faster and More Accurate Classification
TLDR
We show that we can exploit a recent result to allow meaningful averaging of 'warped' times series, and that this result allows us to create ultra-efficient Nearest 'Centroid' classifiers that are at least as accurate as their more lethargic Nearest Neighbor cousins. Expand
Faster and more accurate classification of time series by exploiting a novel dynamic time warping averaging algorithm
TLDR
A concerted research effort over the past two decades has heralded significant improvements in both the efficiency and effectiveness of time series classification. Expand
Adversarial Attacks on Deep Neural Networks for Time Series Classification
TLDR
We introduced the concept of adversarial attacks on deep learning models for time series classification. Expand
Knowledge-based region labeling for remote sensing image interpretation
TLDR
The increasing availability of High Spatial Resolution (HSR) satellite images is an opportunity to characterize and identify urban objects. Expand
Transfer learning for time series classification
TLDR
Transfer learning for deep neural networks is the process of first training a base network on a source dataset and then transferring the learned features (the network’s weights) to a second network to be trained on a target dataset. Expand
Generating Synthetic Time Series to Augment Sparse Datasets
TLDR
We propose new data augmentation techniques specifically designed for time series classification, where the space in which they are embedded is induced by Dynamic Time Warping. Expand
Data augmentation using synthetic data for time series classification with deep residual networks
TLDR
Data augmentation in deep neural networks is the process of generating artificial data in order to reduce variance of the classifier with the goal to reduce the number of errors. Expand
Evaluating surgical skills from kinematic data using convolutional neural networks
TLDR
The need for automatic surgical skills assessment is increasing, especially because manual feedback from senior surgeons observing junior surgeons is prone to subjectivity and time consuming. Expand
...
1
2
3
4
5
...