
Pretraining with Nonexpert Human Demonstration for Deep Reinforcement Learning
Deep reinforcement learning (deep RL) has achieved superior performance ...
read it

Adversarial Transfer Learning
There is a recent large and growing interest in generative adversarial n...
read it

Deep Learning of HighOrder Interactions for Protein Interface Prediction
Protein interactions are important in a broad range of biological proces...
read it

Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey
Reinforcement learning (RL) is a popular paradigm for addressing sequent...
read it

Adapting Auxiliary Losses Using Gradient Similarity
One approach to deal with the statistical inefficiency of neural network...
read it

Interactive Learning of Environment Dynamics for Sequential Tasks
In order for robots and other artificial agents to efficiently learn to ...
read it

ResourceEfficient Computing in Wearable Systems
We propose two optimization techniques to minimize memory usage and comp...
read it

Towards a NetworksofNetworks Framework for Cyber Security
Networksofnetworks (NoN) is a graphtheoretic model of interdependent ...
read it

Efficient and Invariant Convolutional Neural Networks for Dense Prediction
Convolutional neural networks have shown great success on feature extrac...
read it

Dense Transformer Networks
The key idea of current deep learning methods for dense prediction is to...
read it

Learning Convolutional Text Representations for Visual Question Answering
Visual question answering is a recently proposed artificial intelligence...
read it

Spatial Variational AutoEncoding via MatrixVariate Normal Distributions
The key idea of variational autoencoders (VAEs) resembles that of tradi...
read it

Pixel Deconvolutional Networks
Deconvolutional layers have been widely used in a variety of deep models...
read it

Autonomous Extracting a Hierarchical Structure of Tasks in Reinforcement Learning and Multitask Reinforcement Learning
Reinforcement learning (RL), while often powerful, can suffer from slow ...
read it

AttentionBased Models for TextDependent Speaker Verification
Attentionbased models have recently shown great performance on a range ...
read it

Learning to Teach Reinforcement Learning Agents
In this article we study the transfer learning model of action advice un...
read it

MultiStage Variational AutoEncoders for CoarsetoFine Image Generation
Variational autoencoder (VAE) is a powerful unsupervised learning frame...
read it

Trust from the past: Bayesian Personalized Ranking based Link Prediction in Knowledge Graphs
Link prediction, or predicting the likelihood of a link in a knowledge g...
read it

Regularization vs. Relaxation: A conic optimization perspective of statistical variable selection
Variable selection is a fundamental task in statistical data analysis. S...
read it

Interesting Paths in the Mapper
The Mapper produces a compact summary of high dimensional data as a simp...
read it

Learning to Speed Up Query Planning in Graph Databases
Querying graph structured data is a fundamental operation that enables i...
read it

Personalized Human Activity Recognition Using Convolutional Neural Networks
A major barrier to the personalized Human Activity Recognition using wea...
read it

Median Shapes
We introduce and begin to explore the mean and median of finite sets of ...
read it

Towards Cooperation in Sequential Prisoner's Dilemmas: a Deep Multiagent Reinforcement Learning Approach
The Iterated Prisoner's Dilemma has guided research on social dilemmas f...
read it

False discovery rate control for multiple testing based on pvalues with càdlàg distribution functions
For multiple testing based on pvalues with càdlàg distribution function...
read it

PreferenceGuided Planning: An Active Elicitation Approach
Planning with preferences has been employed extensively to quickly gener...
read it

Variable Selection via Adaptive False Negative Control in HighDimensional Regression
In highdimensional regression, variable selection methods have been dev...
read it

Parameter estimation for high dimensional change point regression models without grid search
We propose an L1 regularized estimator for the parameters of a high dime...
read it

Interactive Reinforcement Learning with Dynamic Reuse of Prior Knowledge from Human/Agent's Demonstration
Reinforcement learning has enjoyed multiple successes in recent years. H...
read it

Longitudinal Characterization and Sustainable Classification of Android Apps via SAD Profiles
Machine learningbased malware detection dominates current security defe...
read it

A Preliminary Study On the Sustainability of Android Malware Detection
Machine learningbased malware detection dominates current security defe...
read it

LargeScale Learnable Graph Convolutional Networks
Convolutional neural networks (CNNs) have achieved great success on grid...
read it

Active Anomaly Detection via Ensembles
In critical applications of anomaly detection including computer securit...
read it

GLAD: GLocalized Anomaly Detection via Active Feature Space Suppression
We propose an algorithm called GLAD (GLocalized Anomaly Detection) that ...
read it

Autonomous Extraction of a Hierarchical Structure of Tasks in Reinforcement Learning, A Sequential Associate Rule Mining Approach
Reinforcement learning (RL) techniques, while often powerful, can suffer...
read it

Euler Transformation of Polyhedral Complexes
We propose an Euler transformation that transforms a given ddimensional...
read it

Enumeration, structural and dimensional synthesis of robotic hands: theory and implementation
Designing robotic hands for specific tasks could help in the creation of...
read it

A Scale Invariant Approach for Sparse Signal Recovery
In this paper, we study the ratio of the L_1 and L_2 norms, denoted as...
read it

Learning Graph Pooling and Hybrid Convolutional Operations for Text Representations
With the development of graph convolutional networks (GCN), deep learnin...
read it

Active Anomaly Detection via Ensembles: Insights, Algorithms, and Interpretability
Anomaly detection (AD) task corresponds to identifying the true anomalie...
read it

Jointly Pretraining with Supervised, Autoencoder, and Value Losses for Deep Reinforcement Learning
Deep Reinforcement Learning (DRL) algorithms are known to be data ineffi...
read it

TDMR Detection System with Local Area Influence Probabilistic a Priori Detector
We propose a threetrack detection system for two dimensional magnetic r...
read it

On BenjaminiHochberg procedure applied to mid pvalues
Multiple testing with discrete pvalues routinely arises in various scie...
read it

Detection and estimation of parameters in high dimensional multiple change point regression models via ℓ_1/ℓ_0 regularization and discrete optimization
Binary segmentation, which is sequential in nature is thus far the most ...
read it

On poleswapping algorithms for the eigenvalue problem
Poleswapping algorithms, which are generalizations of the QZ algorithm ...
read it

Jaccard Filtration and Stable Paths in the Mapper
The contributions of this paper are twofold. We define a new filtration...
read it

Poleswapping algorithms for alternating and palindromic eigenvalue problems
Poleswapping algorithms are generalizations of bulgechasing algorithms...
read it

Uniformly consistently estimating the proportion of false null hypotheses for composite null hypotheses via LebesgueStieltjes integral equations
This is the second part of the series on constructing uniformly consiste...
read it

Activity2Vec: Learning ADL Embeddings from Sensor Data with a SequencetoSequence Model
Recognizing activities of daily living (ADLs) plays an essential role in...
read it

MultiPurposing Domain Adaptation Discriminators for Pseudo Labeling Confidence
Often domain adaptation is performed using a discriminator (domain class...
read it
Washington State University
SUSTAINING HEALTHScientists look for practices to thwart antimicrobial resistanceEfforts focused on Africa, drug resistant tuberculosis and other bacteria. TRANSFORMATIVE EDUCATIONFive graduate students win NSF research fellowshipsThe students were chosen from more than 13,000 applicants nationwide. FOOD PRODUCTIONPlant inner workings point way to more nutritious cropsFindings cap two decades of research. SUSTAINABLE RESOURCESWolcott named to DOE's, USDA's biomass research panelCommittee advises on issues related to advancing bioenergy technologies. ADVANCING HEALTHMechanism triggers spread of prostate cancer to bonesPharmacy professor finds that prostate cancer cells hijack the body's bone maintenance, facilitating the ... » More ...