Extensive evaluation over real-world traffic data sets, including normal, encrypted and malicious labels, show that, CGNN improves the prediction accuracy by 23\% to 29\% for application classification, by 2\% to 37\% for malicious traffic classification, and reaches the same accuracy level for encrypted traffic classification.
While recent progress has been made in text-to-image generation, text-to-shape generation remains a challenging problem due to the unavailability of paired text and shape data at a large scale.
Although deep learning models are powerful among various applications, most deep learning models are still a black box, lacking verifiability and interpretability, which means the decision-making process that human beings cannot understand.
This paper describes the winning system for subtask 2 and the second-placed system for subtask 1 in SemEval 2021 Task 4: ReadingComprehension of Abstract Meaning.
In this paper, we present a probabilistic ordinary differential equation (ODE), called STochastic boundaRy ODE (STRODE), that learns both the timings and the dynamics of time series data without requiring any timing annotations during training.
Convolutional neural networks (CNN) have been frequently used to extract subject-invariant features from electroencephalogram (EEG) for classification tasks.
In this paper, we aim to understand how liquidity providers react to market information and how they benefit from providing liquidity in DEXes.
The main challenge of dynamic texture synthesis lies in how to maintain spatial and temporal consistency in synthesized videos.
Despite the remarkable performance of deep learning methods on various tasks, most cutting-edge models rely heavily on large-scale annotated training examples, which are often unavailable for clinical and health care tasks.
We also find that robustness to unseen transformations cannot be brought about merely by extensive data augmentation.
In this research, a novel economic model predictive control (EMPC) framework for real-time management of WDSs is proposed.
Human computer interaction (HCI) involves a multidisciplinary fusion of technologies, through which the control of external devices could be achieved by monitoring physiological status of users.
Recent developments in biosignal processing have enabled users to exploit their physiological status for manipulating devices in a reliable and safe manner.
Network slicing enables multiple virtual networks run on the same physical infrastructure to support various use cases in 5G and beyond.
Robust machine learning formulations have emerged to address the prevalent vulnerability of deep neural networks to adversarial examples.
Furthermore, we define a new continual learning paradigm to simulate the possible continual learning process in the human brain.
Lying at the core of human intelligence, relational thinking is characterized by initially relying on innumerable unconscious percepts pertaining to relations between new sensory signals and prior knowledge, consequently becoming a recognizable concept or object through coupling and transformation of these percepts.
Learning data representations that capture task-related features, but are invariant to nuisance variations remains a key challenge in machine learning.
This is motivated by the rateless property of conventional PCA, where the least important principal components can be discarded to realize variable rate dimensionality reduction that gracefully degrades the distortion.
Recent developments in wearable sensors demonstrate promising results for monitoring physiological status in effective and comfortable ways.
In this paper, we present a novel framework for jointly predicting landmark locations, associated uncertainties of these predicted locations, and landmark visibilities.
Ranked #1 on Face Alignment on MERL-RAV
This is a paper for exploring various different models aiming at developing fake news detection models and we had used certain machine learning algorithms and we had used pretrained algorithms such as TFIDF and CV and W2V as features for processing textual data.
Recently, data-driven approaches motivated by modern deep learning have been applied to optical communications in place of traditional model-based counterparts.
Deep learning methods for person identification based on electroencephalographic (EEG) brain activity encounters the problem of exploiting the temporally correlated structures or recording session specific variability within EEG.
The deep learning trend has recently impacted a variety of fields, including communication systems, where various approaches have explored the application of neural networks in place of traditional designs.
This paper studies a new application of deep learning (DL) for optimizing constellations in two-way relaying with physical-layer network coding (PNC), where deep neural network (DNN)-based modulation and demodulation are employed at each terminal and relay node.
Unsupervised video object segmentation is a crucial application in video analysis without knowing any prior information about the objects.
One is a model-based drone augmentation technique that automatically generates visible drone images with a bounding box label on the drone's location.
We introduce adversarial neural networks for representation learning as a novel approach to transfer learning in brain-computer interfaces (BCIs).
Experimental results on DAVIS and FBMS show that the proposed method outperforms state-of-the-art unsupervised segmentation methods on various benchmark datasets.
In this method, an adversarial network attempts to recover the nuisance variable from the representation, which the VAE is trained to prevent.
Unlike previous unknown nouns tagging task, this is the first attempt to focus on out-of-vocabulary (OOV) lexical evaluation tasks that do not require any prior knowledge.
We propose a data-driven framework for optimizing privacy-preserving data release mechanisms to attain the information-theoretically optimal tradeoff between minimizing distortion of useful data and concealing specific sensitive information.
Recent development in fully convolutional neural network enables efficient end-to-end learning of semantic segmentation.
Current music recommender systems typically act in a greedy fashion by recommending songs with the highest user ratings.