Many real-world IoT systems comprising various internet-connected sensor...
Concentration of measure has been argued to be the fundamental cause of
...
Deep neural networks have been well-known for their superb performance i...
Time series forecasting is a key component in many industrial and busine...
Potential crowd flow prediction for new planned transportation sites is ...
Video captioning has been a challenging and significant task that descri...
We create a framework for bootstrapping visual representation learning f...
We describe two end-to-end autoencoding models for semi-supervised
graph...
Cross-lingual document search is an information retrieval task in which ...
Estimation of the information content in a neural network model can be
p...
Deep Q-learning algorithms often suffer from poor gradient estimations w...
The last ten years have witnessed fast spreading of massively parallel
c...
Over-parameterized deep neural networks (DNNs) with sufficient capacity ...
The p_0 model is an exponential random graph model for directed networks...
By allowing users to obscure their transactions via including "mixins" (...
In this paper, we study the statistical properties of the kernel k-means...
Starting with Gilmer et al. (2018), several works have demonstrated the
...
Training machine learning models to be robust against adversarial inputs...
Text classification is one of the most important and fundamental tasks i...
An electroencephalogram (EEG) based brain-computer interface (BCI) spell...
Compared to sequential learning models, graph-based neural networks exhi...
A deep neural network (DNN) with piecewise linear activations can partit...
Towards automated retinal screening, this paper makes an endeavor to
sim...
Multiple convolutional neural network (CNN) classifiers have been propos...
In this paper, we introduce Anomaly Contribution Explainer or ACE, a too...
Deep learning has made significant breakthroughs in many fields, includi...
We propose a novel adaptive empirical Bayesian (AEB) method for sparse d...
Almost all existing deep learning approaches for semantic segmentation t...
Detecting surrounding vehicles by low-cost LIDAR has been drawing enormo...
External knowledge is often useful for natural language understanding ta...
Large-scale image databases such as ImageNet have significantly advanced...
Many NLP learning tasks can be decomposed into several distinct sub-task...
Many recent works have shown that adversarial examples that fool classif...
In this paper, we introduce the problem of jointly learning feed-forward...
Cosine-based softmax losses significantly improve the performance of dee...
The cosine-based softmax losses and their variants achieve great success...
Generating diverse yet specific data is the goal of the generative
adver...
Deep learning has been successfully used in numerous applications becaus...
Each UAV is constrained in its energy storage and wireless coverage, and...
We present a single-shot, bottom-up approach for whole image parsing. Wh...
Learning from corpus and learning from supervised NLP tasks both give us...
Several recent works have developed methods for training classifiers tha...
We study the problem of learning one-hidden-layer neural networks with
R...
An Unmanned Aerial Vehicle (UAV) network has emerged as a promising tech...
This short paper describes our solution to the 2018 IEEE World Congress ...
This work proposes an automated algorithm, called NetAdapt, that adapts ...
It is a fundamental, but still elusive question whether methods based on...
We revisit the inductive matrix completion problem that aims to recover ...
Reading and understanding text is one important component in computer ai...
Unmanned Aerial Vehicle (UAV) networks have emerged as a promising techn...