
A Robot that Learns Connect Four Using Game Theory and Demonstrations
Teaching robots new skills using minimal time and effort has long been a...
read it

Longitudinal Deep Kernel Gaussian Process Regression
We consider the problem of learning predictive models from longitudinal ...
read it

Selfsupervised Learning on Graphs: Deep Insights and New Direction
The success of deep learning notoriously requires larger amounts of cost...
read it

Minimal Variance Sampling with Provable Guarantees for Fast Training of Graph Neural Networks
Sampling methods (e.g., nodewise, layerwise, or subgraph) has become a...
read it

LMLFM: Longitudinal MultiLevel Factorization Machines
Selecting important variables and learning predictive models from highd...
read it

How Relevant is the Turing Test in the Age of Sophisbots?
Popular culture has contemplated societies of thinking machines for gene...
read it

Learning from Multiple Cities: A MetaLearning Approach for SpatialTemporal Prediction
Spatialtemporal prediction is a fundamental problem for constructing sm...
read it

Constrained Linear Datafeature Mapping for Image Classification
In this paper, we propose a constrained linear datafeature mapping mode...
read it

Algorithmic Bias in Recidivism Prediction: A Causal Perspective
ProPublica's analysis of recidivism predictions produced by Correctional...
read it

Foot Pressure from Video: A Deep Learning Approach to Predict Dynamics from Kinematics
Human gait stability analysis is a key to understanding locomotion and c...
read it

TopNRank: A Scalable Listwise Ranking Method for Recommender Systems
We propose TopNRank, a novel family of listwise LearningtoRank mode...
read it

An Algorithm Unrolling Approach to Deep Blind Image Deblurring
Blind image deblurring remains a topic of enduring interest. Learning ba...
read it

Gain with no Pain: Efficient KernelPCA by Nyström Sampling
In this paper, we propose and study a Nyström based approach to efficien...
read it

Transferable Neural Processes for Hyperparameter Optimization
Automated machine learning aims to automate the whole process of machine...
read it

The Dynamical Gaussian Process Latent Variable Model in the Longitudinal Scenario
The Dynamical Gaussian Process Latent Variable Models provide an elegant...
read it

From Kinematics To Dynamics: Estimating Center of Pressure and Base of Support from Video Frames of Human Motion
To gain an understanding of the relation between a given human pose imag...
read it

Lifelong Neural Predictive Coding: Sparsity Yields Less Forgetting when Learning Cumulatively
In lifelong learning systems, especially those based on artificial neura...
read it

PaDNet: PanDensity Crowd Counting
Crowd counting in varying density scenes is a challenging problem in art...
read it

Scene Graph Generation via Conditional Random Fields
Despite the great success object detection and segmentation models have ...
read it

On the bias of Hscores for comparing biclusters, and how to correct it
In the last two decades several biclustering methods have been developed...
read it

Automated Relational Metalearning
In order to efficiently learn with small amount of data on new tasks, me...
read it

Superpixel Segmentation with Fully Convolutional Networks
In computer vision, superpixels have been widely used as an effective wa...
read it

Graph Structure Learning for Robust Graph Neural Networks
Graph Neural Networks (GNNs) are powerful tools in representation learni...
read it

SingleImage Piecewise Planar 3D Reconstruction via Associative Embedding
Singleimage piecewise planar 3D reconstruction aims to simultaneously ...
read it

Node Injection Attacks on Graphs via Reinforcement Learning
Realworld graph applications, such as advertisements and product recomm...
read it

No Peeking through My Windows: Conserving Privacy in Personal Drones
The drone technology has been increasingly used by many techsavvy consu...
read it

RISE Video Dataset: Recognizing Industrial Smoke Emissions
Industrial smoke emissions pose a significant concern to human health. P...
read it

A Neural Temporal Model for Human Motion Prediction
We propose novel neural temporal models for shortterm motion prediction...
read it

Improving Image Captioning by Leveraging Knowledge Graphs
We explore the use of a knowledge graphs, that capture general or common...
read it

Modelfree Feature Screening and FDR Control with Knockoff Features
This paper proposes a modelfree and dataadaptive feature screening met...
read it

Revealing Backdoors, PostTraining, in DNN Classifiers via Novel Inference on Optimized Perturbations Inducing Group Misclassification
Recently, a special type of data poisoning (DP) attack targeting Deep Ne...
read it

The Neural State Pushdown Automata
In order to learn complex grammars, recurrent neural networks (RNNs) req...
read it

Reducing the Computational Burden of Deep Learning with Recursive Local Representation Alignment
Training deep neural networks on largescale datasets requires significa...
read it

Transferability in Machine Learning: from Phenomena to BlackBox Attacks using Adversarial Samples
Many machine learning models are vulnerable to adversarial examples: inp...
read it

Practical BlackBox Attacks against Machine Learning
Machine learning (ML) models, e.g., deep neural networks (DNNs), are vul...
read it

Semisupervised Knowledge Transfer for Deep Learning from Private Training Data
Some machine learning applications involve training data that is sensiti...
read it

cleverhans v2.0.0: an adversarial machine learning library
cleverhans is a software library that provides standardized reference im...
read it

Adversarial Perturbations Against Deep Neural Networks for Malware Classification
Deep neural networks, like many other machine learning models, have rece...
read it

Practical Finegrained Privilege Separation in Multithreaded Applications
An inherent security limitation with the classic multithreaded programmi...
read it

TrustShadow: Secure Execution of Unmodified Applications with ARM TrustZone
The rapid evolution of InternetofThings (IoT) technologies has led to ...
read it

Blind Image Deblurring Using RowColumn Sparse Representations
Blind image deblurring is a particularly challenging inverse problem whe...
read it

Symbolic Analysisbased Reduced Order Markov Modeling of Time Series Data
This paper presents a technique for reducedorder Markov modeling for co...
read it

Characteristic and Universal Tensor Product Kernels
Kernel mean embeddings provide a versatile and powerful nonparametric re...
read it

Crafting Adversarial Input Sequences for Recurrent Neural Networks
Machine learning models are frequently used to solve complex security pr...
read it

Prolongation of SMAP to Spatiotemporally Seamless Coverage of Continental US Using a Deep Learning Neural Network
The Soil Moisture Active Passive (SMAP) mission has delivered valuable s...
read it

The Limitations of Deep Learning in Adversarial Settings
Deep learning takes advantage of large datasets and computationally effi...
read it

Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
Deep learning algorithms have been shown to perform extremely well on ma...
read it

Dimension of Marginals of Kronecker Product Models
A Kronecker product model is the set of visible marginal probability dis...
read it

Statistical Consistency of Kernel PCA with Random Features
Kernel methods are powerful learning methodologies that provide a simple...
read it

Information, Privacy and Stability in Adaptive Data Analysis
Traditional statistical theory assumes that the analysis to be performed...
read it
Penn State University
The Pennsylvania State University is a staterelated, landgrant, doctoral university with campuses and facilities throughout Pennsylvania.