Related papers: Inductive Dual-Polarity Modeling via Static-Dynami…

The memorization effect of deep neural network (DNN) plays a pivotal role in many state-of-the-art label-noise learning methods. To exploit this property, the early stopping trick, which stops the optimization at the early stage of…

State of the art Deep Neural Networks (DNN) can now achieve above human level accuracy on image classification tasks. However their outstanding performances come along with a complex inference mechanism making them arduously interpretable…

Since many real world networks are evolving over time, such as social networks and user-item networks, there are increasing research efforts on dynamic network embedding in recent years. They learn node representations from a sequence of…

Recently, methods have been developed to accurately predict the testing performance of a Deep Neural Network (DNN) on a particular task, given statistics of its underlying topological structure. However, further leveraging this newly found…

Understanding Deep Neural Network (DNN) performance in changing conditions is essential for deploying DNNs in safety critical applications with unconstrained environments, e.g., perception for self-driving vehicles or medical image…

Deep neural networks (DNNs) have recently been applied to inverse scattering problems (ISPs) due to their strong nonlinear mapping capabilities. However, supervised DNN solvers require large-scale datasets, which limits their generalization…

We present a deep neural network (DNN) that uses both sensor data (gyroscope) and image content (optical flow) to stabilize videos through unsupervised learning. The network fuses optical flow with real/virtual camera pose histories into a…

Although deep neural network (DNN)-based controllers are popularly used to control uncertain nonlinear dynamic systems, most results use DNNs that are pretrained offline and the corresponding controller is implemented post-training. Recent…

Social recommendation leverages social network to complement user-item interaction data for recommendation task, aiming to mitigate the data sparsity issue in recommender systems. However, existing social recommendation methods encounter…

Transient stability prediction is critically essential to the fast online assessment and maintaining the stable operation in power systems. The wide deployment of phasor measurement units (PMUs) promotes the development of data-driven…

In this paper, we propose the Deep Structured self-Driving Network (DSDNet), which performs object detection, motion prediction, and motion planning with a single neural network. Towards this goal, we develop a deep structured energy based…

Deep Neural Networks (DNN) have been successful in en- hancing noisy speech signals. Enhancement is achieved by learning a nonlinear mapping function from the features of the corrupted speech signal to that of the reference clean speech…

Deep image prior (DIP) proposed in recent research has revealed the inherent trait of convolutional neural networks (CNN) for capturing substantial low-level image statistics priors. This framework efficiently addresses the inverse problems…

Real-world dynamic graphs are often directed, with source and destination nodes exhibiting asymmetrical behavioral patterns and temporal dynamics. However, existing dynamic graph architectures largely rely on shared parameters for…

Dynamic nuclear polarisation (DNP) refers to a class of techniques used to increase the signal in nuclear magnetic resonance measurements by transferring spin polarisation from ensembles of highly polarised electrons to target nuclear…

We introduce a method to reconstruct the kinematics of neutral-current deep inelastic scattering (DIS) using a deep neural network (DNN). Unlike traditional methods, it exploits the full kinematic information of both the scattered electron…

Dynamic Nuclear Polarization (DNP) is to date the most effective technique to increase the nuclear polarization up to a factor $100,000$ opening disruptive perspectives for medical applications. In DNP, the nuclear spins are driven to an -…

Dynamic state estimation (DSE) is becoming increasingly important for monitoring inverter-dominated power systems. Due to their cascading control structures, inverter-based resources (IBRs) exhibit multi-timescale dynamics, leading to stiff…

We introduce the Deep Symbolic Network (DSN) model, which aims at becoming the white-box version of Deep Neural Networks (DNN). The DSN model provides a simple, universal yet powerful structure, similar to DNN, to represent any knowledge of…

In this paper, we present DSN (Deep Serial Number), a simple yet effective watermarking algorithm designed specifically for deep neural networks (DNNs). Unlike traditional methods that incorporate identification signals into DNNs, our…