Latest in cs.ai

total 10520took 0.12s
LOSSGRAD: automatic learning rate in gradient descentFeb 20 2019In this paper, we propose a simple, fast and easy to implement algorithm LOSSGRAD (locally optimal step-size in gradient descent), which automatically modifies the step-size in gradient descent during neural networks training. Given a function $f$, a ... More
Learning efficient haptic shape exploration with a rigid tactile sensor arrayFeb 20 2019Haptic exploration is a key skill for both robots and humans to discriminate and handle unknown or recognize familiar objects. Its active nature is impressively evident in humans which from early on reliably acquire sophisticated sensory-motor capabilites ... More
A Random Subspace Technique That Is Resistant to a Limited Number of Features Corrupted by an AdversaryFeb 19 2019In this paper, we consider batch supervised learning where an adversary is allowed to corrupt instances with arbitrarily large noise. The adversary is allowed to corrupt any $l$ features in each instance and the adversary can change their values in any ... More
A spelling correction model for end-to-end speech recognitionFeb 19 2019Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language model component ... More
Investigating Generalisation in Continuous Deep Reinforcement LearningFeb 19 2019Feb 20 2019Deep Reinforcement Learning has shown great success in a variety of control tasks. However, it is unclear how close we are to the vision of putting Deep RL into practice to solve real world problems. In particular, common practice in the field is to train ... More
Investigating Generalisation in Continuous Deep Reinforcement LearningFeb 19 2019Deep Reinforcement Learning has shown great success in a variety of control tasks. However, it is unclear how close we are to the vision of putting Deep RL into practice to solve real world problems. In particular, common practice in the field is to train ... More
Democratisation of Usable Machine Learning in Computer VisionFeb 18 2019Many industries are now investing heavily in data science and automation to replace manual tasks and/or to help with decision making, especially in the realm of leveraging computer vision to automate many monitoring, inspection, and surveillance tasks. ... More
Using Machine Learning to Guide Cognitive Modeling: A Case Study in Moral ReasoningFeb 18 2019Large-scale behavioral datasets enable researchers to use complex machine learning algorithms to better predict human behavior, yet this increased predictive power does not always lead to a better understanding of the behavior in question. In this paper, ... More
DIViS: Domain Invariant Visual Servoing for Collision-Free Goal ReachingFeb 18 2019Robots should understand both semantics and physics to be functional in the real world. While robot platforms provide means for interacting with the physical world they cannot autonomously acquire object-level semantics without needing human. In this ... More
Message-Dropout: An Efficient Training Method for Multi-Agent Deep Reinforcement LearningFeb 18 2019In this paper, we propose a new learning technique named message-dropout to improve the performance for multi-agent deep reinforcement learning under two application scenarios: 1) classical multi-agent reinforcement learning with direct message communication ... More
Reactive, Proactive, and Inductive Agents: An evolutionary path for biological and artificial spiking networksFeb 18 2019Complex environments provide structured yet variable sensory inputs. To best exploit information from these environments, organisms must evolve the ability to correctly anticipate consequences of unknown stimuli, and act on these predictions. We propose ... More
SCEF: A Support-Confidence-aware Embedding Framework for Knowledge Graph RefinementFeb 18 2019Knowledge graph (KG) refinement mainly aims at KG completion and correction (i.e., error detection). However, most conventional KG embedding models only focus on KG completion with an unreasonable assumption that all facts in KG hold without noises, ignoring ... More
Evolutionary Multitasking for Semantic Web Service CompositionFeb 18 2019Web services are basic functions of a software system to support the concept of service-oriented architecture. They are often composed together to provide added values, known as web service composition. Researchers often employ Evolutionary Computation ... More
Learning to Infer Program SketchesFeb 17 2019Our goal is to build systems which write code automatically from the kinds of specifications humans can most easily provide, such as examples and natural language instruction. The key idea of this work is that a flexible combination of pattern recognition ... More
Limited Lookahead in Imperfect-Information GamesFeb 17 2019Limited lookahead has been studied for decades in complete-information games. We initiate a new direction via two simultaneous deviation points: generalization to incomplete-information games and a game-theoretic approach. We study how one should act ... More
A new Potential-Based Reward Shaping for Reinforcement Learning AgentFeb 17 2019Potential-based reward shaping (PBRS) is a particular category of machine learning methods which aims to improve the learning speed of a reinforcement learning agent by extracting and utilizing extra knowledge while performing a task. There are two steps ... More
Iterated Belief Base Revision: A Dynamic Epistemic Logic ApproachFeb 17 2019AGM's belief revision is one of the main paradigms in the study of belief change operations. In this context, belief bases (prioritised bases) have been largely used to specify the agent's belief state - whether representing the agent's `explicit beliefs' ... More
Timeline-based planning: Expressiveness and ComplexityFeb 16 2019Timeline-based planning is an approach originally developed in the context of space mission planning and scheduling, where problem domains are modelled as systems made of a number of independent but interacting components, whose behaviour over time, the ... More
Re-determinizing Information Set Monte Carlo Tree Search in HanabiFeb 16 2019This technical report documents the winner of the Computational Intelligence in Games(CIG) 2018 Hanabi competition. We introduce Re-determinizing IS-MCTS, a novel extension of Information Set Monte Carlo Tree Search (IS-MCTS) \cite{IS-MCTS} that prevents ... More
ProLoNets: Neural-encoding Human Experts' Domain Knowledge to Warm Start Reinforcement LearningFeb 15 2019Deep reinforcement learning has seen great success across a breadth of tasks such as in game playing and robotic manipulation. However, the modern practice of attempting to learn tabula rasa disregards the logical structure of many domains and the wealth ... More
Improving Semantic Parsing for Task Oriented DialogFeb 15 2019Semantic parsing using hierarchical representations has recently been proposed for task oriented dialog with promising results [Gupta et al 2018]. In this paper, we present three different improvements to the model: contextualized embeddings, ensembling, ... More
On resampling vs. adjusting probabilistic graphical models in estimation of distribution algorithmsFeb 15 2019The Bayesian Optimisation Algorithm (BOA) is an Estimation of Distribution Algorithm (EDA) that uses a Bayesian network as probabilistic graphical model (PGM). Determining the optimal Bayesian network structure given a solution sample is an NP-hard problem. ... More
Privacy of Existence of Secrets: Introducing Steganographic DCOPs and Revisiting DCOP FrameworksFeb 15 2019Here we identify a type of privacy concern in Distributed Constraint Optimization (DCOPs) not previously addressed in literature, despite its importance and impact on the application field: the privacy of existence of secrets. Science only starts where ... More
Unsupervised shape and motion analysis of 3822 cardiac 4D MRIs of UK BiobankFeb 15 2019We perform unsupervised analysis of image-derived shape and motion features extracted from 3822 cardiac 4D MRIs of the UK Biobank. First, with a feature extraction method previously published based on deep learning models, we extract from each case 9 ... More
Robust Reinforcement Learning in POMDPs with Incomplete and Noisy ObservationsFeb 15 2019In real-world scenarios, the observation data for reinforcement learning with continuous control is commonly noisy and part of it may be dynamically missing over time, which violates the assumption of many current methods developed for this. We addressed ... More
Deep Reinforcement Learning Based High-level Driving Behavior Decision-making Model in Heterogeneous TrafficFeb 15 2019High-level driving behavior decision-making is an open-challenging problem for connected vehicle technology, especially in heterogeneous traffic scenarios. In this paper, a deep reinforcement learning based high-level driving behavior decision-making ... More
Dynamic Layer Aggregation for Neural Machine Translation with Routing-by-AgreementFeb 15 2019With the promising progress of deep neural networks, layer aggregation has been used to fuse information across layers in various fields, such as computer vision and machine translation. However, most of the previous methods combine layers in a static ... More
Shepherding Hordes of Markov ChainsFeb 15 2019This paper considers large families of Markov chains (MCs) that are defined over a set of parameters with finite discrete domains. Such families occur in software product lines, planning under partial observability, and sketching of probabilistic programs. ... More
Generating Natural Language Explanations for Visual Question Answering using Scene Graphs and Visual AttentionFeb 15 2019In this paper, we present a novel approach for the task of eXplainable Question Answering (XQA), i.e., generating natural language (NL) explanations for the Visual Question Answering (VQA) problem. We generate NL explanations comprising of the evidence ... More
Probabilistic Relational Agent-based ModelsFeb 15 2019PRAM puts agent-based models on a sound probabilistic footing as a basis for integrating agent-based and probabilistic models. It extends the themes of probabilistic relational models and lifted inference to incorporate dynamical models and simulation. ... More
Active Perception in Adversarial Scenarios using Maximum Entropy Deep Reinforcement LearningFeb 14 2019We pose an active perception problem where an autonomous agent actively interacts with a second agent with potentially adversarial behaviors. Given the uncertainty in the intent of the other agent, the objective is to collect further evidence to help ... More
Verifiably Safe Off-Model Reinforcement LearningFeb 14 2019The desire to use reinforcement learning in safety-critical settings has inspired a recent interest in formal methods for learning algorithms. Existing formal methods for learning and optimization primarily consider the problem of constrained learning ... More
Learning to Control Self-Assembling Morphologies: A Study of Generalization via ModularityFeb 14 2019Contemporary sensorimotor learning approaches typically start with an existing complex agent (e.g., a robotic arm), which they learn to control. In contrast, this paper investigates a modular co-evolution strategy: a collection of primitive agents learns ... More
Superposition of many models into oneFeb 14 2019We present a method for storing multiple models within a single set of parameters. Models can coexist in superposition and still be retrieved individually. In experiments with neural networks, we show that a surprisingly large number of models can be ... More
Procrastinating with Confidence: Near-Optimal, Anytime, Adaptive Algorithm ConfigurationFeb 14 2019Algorithm configuration methods optimize the performance of a parameterized heuristic algorithm on a given distribution of problem instances. Recent work introduced an algorithm configuration procedure ('Structured Procrastination') that provably achieves ... More
Learn a Prior for RHEA for Better Online PlanningFeb 14 2019Rolling Horizon Evolutionary Algorithms (RHEA) are a class of online planning methods for real-time game playing; their performance is closely related to the planning horizon and the search time allowed. In this paper, we propose to learn a prior for ... More
Stable-Predictive Optimistic Counterfactual Regret MinimizationFeb 13 2019The CFR framework has been a powerful tool for solving large-scale extensive-form games in practice. However, the theoretical rate at which past CFR-based algorithms converge to the Nash equilibrium is on the order of $O(T^{-1/2})$, where $T$ is the number ... More
Federated Machine Learning: Concept and ApplicationsFeb 13 2019Today's AI still faces two major challenges. One is that in most industries, data exists in the form of isolated islands. The other is the strengthening of data privacy and security. We propose a possible solution to these challenges: secure federated ... More
Optimization problems with low SWaP tactical ComputingFeb 13 2019In a resource-constrained, contested environment, computing resources need to be aware of possible size, weight, and power (SWaP) restrictions. SWaP-aware computational efficiency depends upon optimization of computational resources and intelligent time ... More
Relative rationality: Is machine rationality subjective?Feb 13 2019Rational decision making in its linguistic description means making logical decisions. In essence, a rational agent optimally processes all relevant information to achieve its goal. Rationality has two elements and these are the use of relevant information ... More
Stable multi-instance learning visa causal inferenceFeb 13 2019Multi-instance learning (MIL) deals with tasks where each example is represented by a bag of instances. Unlike traditional supervised learning, only the bag labels are observed whereas the label for each instance in the bags is not available. Previous ... More
Identity Crisis: Memorization and Generalization under Extreme OverparameterizationFeb 13 2019We study the interplay between memorization and generalization of overparametrized networks in the extreme case of a single training example. The learning task is to predict an output which is as similar as possible to the input. We examine both fully-connected ... More
Time-aware Test Case Execution Scheduling for Cyber-Physical SystemsFeb 12 2019Testing cyber-physical systems involves the execution of test cases on target-machines equipped with the latest release of a software control system. When testing industrial robots, it is common that the target machines need to share some common resources, ... More
ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement LearningFeb 12 2019Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failed experience to a successful one by relabeling the goals. Despite its effectiveness, ... More
ELF OpenGo: An Analysis and Open Reimplementation of AlphaZeroFeb 12 2019Feb 13 2019The AlphaGo, AlphaGo Zero, and AlphaZero series of algorithms are a remarkable demonstration of deep reinforcement learning's capabilities, achieving superhuman performance in the complex game of Go with progressively increasing autonomy. However, many ... More
ELF OpenGo: An Analysis and Open Reimplementation of AlphaZeroFeb 12 2019The AlphaGo, AlphaGo Zero, and AlphaZero series of algorithms are a remarkable demonstration of deep reinforcement learning's capabilities, achieving superhuman performance in the complex game of Go with progressively increasing autonomy. However, many ... More
RTbust: Exploiting Temporal Patterns for Botnet Detection on TwitterFeb 12 2019Within OSNs, many of our supposedly online friends may instead be fake accounts called social bots, part of large groups that purposely re-share targeted content. Here, we study retweeting behaviors on Twitter, with the ultimate goal of detecting retweeting ... More
Examining Adversarial Learning against Graph-based IoT Malware Detection SystemsFeb 12 2019The main goal of this study is to investigate the robustness of graph-based Deep Learning (DL) models used for Internet of Things (IoT) malware classification against Adversarial Learning (AL). We designed two approaches to craft adversarial IoT software, ... More
Guiding Neuroevolution with Structural ObjectivesFeb 12 2019Feb 13 2019The structure and performance of neural networks are intimately connected, and by use of evolutionary algorithms, neural network structures optimally adapted to a given task can be explored. Guiding such neuroevolution with additional objectives related ... More
Guiding Neuroevolution with Structural ObjectivesFeb 12 2019The structure and performance of neural networks are intimately connected, and by use of evolutionary algorithms, neural network structures optimally adapted to a given task can be explored. Guiding such neuroevolution with additional objectives related ... More
Towards Self-Supervised High Level Sensor FusionFeb 12 2019In this paper, we present a framework to control a self-driving car by fusing raw information from RGB images and depth maps. A deep neural network architecture is used for mapping the vision and depth information, respectively, to steering commands. ... More
NAIL: A General Interactive Fiction AgentFeb 12 2019Interactive Fiction (IF) games are complex textual decision making problems. This paper introduces NAIL, an autonomous agent for general parser-based IF games. NAIL won the 2018 Text Adventure AI Competition, where it was evaluated on twenty unseen games. ... More
VERIFAI: A Toolkit for the Design and Analysis of Artificial Intelligence-Based SystemsFeb 12 2019We present VERIFAI, a software toolkit for the formal design and analysis of systems that include artificial intelligence (AI) and machine learning (ML) components. VERIFAI particularly seeks to address challenges with applying formal methods to perception ... More
VERIFAI: A Toolkit for the Design and Analysis of Artificial Intelligence-Based SystemsFeb 12 2019Feb 14 2019We present VERIFAI, a software toolkit for the formal design and analysis of systems that include artificial intelligence (AI) and machine learning (ML) components. VERIFAI particularly seeks to address challenges with applying formal methods to perception ... More
Multi-objective Bayesian optimisation with preferences over objectivesFeb 12 2019We present a Bayesian multi-objective optimisation algorithm that allows the user to express preference-order constraints on the objectives of the type `objective A is more important than objective B'. Rather than attempting to find a representative subset ... More
MaCow: Masked Convolutional Generative FlowFeb 12 2019Flow-based generative models, conceptually attractive due to tractability of both the exact log-likelihood computation and latent-variable inference, and efficiency of both training and sampling, has led to a number of impressive empirical successes and ... More
Preferences Implicit in the State of the WorldFeb 12 2019Reinforcement learning (RL) agents optimize only the features specified in a reward function and are indifferent to anything left out inadvertently. This means that we must not only specify what to do, but also the much larger space of what not to do. ... More
LS-Tree: Model Interpretation When the Data Are LinguisticFeb 11 2019We study the problem of interpreting trained classification models in the setting of linguistic data sets. Leveraging a parse tree, we propose to assign least-squares based importance scores to each word of an instance by exploiting syntactic constituency ... More
Riemannian joint dimensionality reduction and dictionary learning on symmetric positive definite manifoldFeb 11 2019Dictionary leaning (DL) and dimensionality reduction (DR) are powerful tools to analyze high-dimensional noisy signals. This paper presents a proposal of a novel Riemannian joint dimensionality reduction and dictionary learning (R-JDRDL) on symmetric ... More
Nearest Neighbor Median Shift Clustering for Binary DataFeb 11 2019We describe in this paper the theory and practice behind a new modal clustering method for binary data. Our approach (BinNNMS) is based on the nearest neighbor median shift. The median shift is an extension of the well-known mean shift, which was designed ... More
Performance Dynamics and Termination Errors in Reinforcement Learning: A Unifying PerspectiveFeb 11 2019In reinforcement learning, a decision needs to be made at some point as to whether it is worthwhile to carry on with the learning process or to terminate it. In many such situations, stochastic elements are often present which govern the occurrence of ... More
Stochastic Reinforcement LearningFeb 11 2019In reinforcement learning episodes, the rewards and punishments are often non-deterministic, and there are invariably stochastic elements governing the underlying situation. Such stochastic elements are often numerous and cannot be known in advance, and ... More
Synthesizing New Retinal Symptom Images by Multiple Generative ModelsFeb 11 2019Age-Related Macular Degeneration (AMD) is an asymptomatic retinal disease which may result in loss of vision. There is limited access to high-quality relevant retinal images and poor understanding of the features defining sub-classes of this disease. ... More
Improving Generalization and Stability of Generative Adversarial NetworksFeb 11 2019Generative Adversarial Networks (GANs) are one of the most popular tools for learning complex high dimensional distributions. However, generalization properties of GANs have not been well understood. In this paper, we analyze the generalization of GANs ... More
Cyclical Stochastic Gradient MCMC for Bayesian Deep LearningFeb 11 2019The posteriors over neural network weights are high dimensional and multimodal. Each mode typically characterizes a meaningfully different representation of the data. We develop Cyclical Stochastic Gradient MCMC (SG-MCMC) to automatically explore such ... More
A Distributed and Approximated Nearest Neighbors Algorithm for an Efficient Large Scale Mean Shift ClusteringFeb 11 2019In this paper we target the class of modal clustering methods where clusters are defined in terms of the local modes of the probability density function which generates the data. The most well-known modal clustering method is the k-means clustering. Mean ... More
Semantic Label Reduction Techniques for Autonomous DrivingFeb 11 2019Semantic segmentation maps can be used as input to models for maneuvering the controls of a car. However, not all labels may be necessary for making the control decision. One would expect that certain labels such as road lanes or sidewalks would be more ... More
Latent Space Reinforcement Learning for Steering Angle PredictionFeb 11 2019Model-free reinforcement learning has recently been shown to successfully learn navigation policies from raw sensor data. In this work, we address the problem of learning driving policies for an autonomous agent in a high-fidelity simulator. Building ... More
Discrimination in the Age of AlgorithmsFeb 11 2019The law forbids discrimination. But the ambiguity of human decision-making often makes it extraordinarily hard for the legal system to know whether anyone has actually discriminated. To understand how algorithms affect discrimination, we must therefore ... More
Learning Best Response Strategies for Agents in Ad ExchangesFeb 10 2019Ad exchanges are widely used in platforms for online display advertising. Autonomous agents operating in these exchanges must learn policies for interacting profitably with a diverse, continually changing, but unknown market. We consider this problem ... More
EvalAI: Towards Better Evaluation Systems for AI AgentsFeb 10 2019We introduce EvalAI, an open source platform for evaluating and comparing machine learning (ML) and artificial intelligence algorithms (AI) at scale. EvalAI is built to provide a scalable solution to the research community to fulfill the critical need ... More
Task2Vec: Task Embedding for Meta-LearningFeb 10 2019We introduce a method to provide vectorial representations of visual classification tasks which can be used to reason about the nature of those tasks and their relations. Given a dataset with ground-truth labels and a loss function defined over those ... More
The Omniglot Challenge: A 3-Year Progress ReportFeb 09 2019Three years ago, we released the Omniglot dataset for developing more human-like learning algorithms. Omniglot is a one-shot learning challenge, inspired by how people can learn a new concept from just one or a few examples. Along with the dataset, we ... More
3D Hand Shape and Pose from Images in the WildFeb 09 2019We present in this work the first end-to-end deep learning based method that predicts both 3D hand shape and pose from RGB images in the wild. Our network consists of the concatenation of a deep convolutional encoder, and a fixed model-based decoder. ... More
Yes, we GAN: Applying Adversarial Techniques for Autonomous DrivingFeb 09 2019Generative Adversarial Networks (GAN) have gained a lot of popularity from their introduction in 2014 till present. Research on GAN is rapidly growing and there are many variants of the original GAN focusing on various aspects of deep learning. GAN are ... More
Improved Knowledge Distillation via Teacher Assistant: Bridging the Gap Between Student and TeacherFeb 09 2019Despite the fact that deep neural networks are powerful models and achieve appealing results on many tasks, they are too gigantic to be deployed on edge devices like smart-phones or embedded sensor nodes. There has been efforts to compress these networks, ... More
Generative Moment Matching Network-based Random Modulation Post-filter for DNN-based Singing Voice Synthesis and Neural Double-trackingFeb 09 2019This paper proposes a generative moment matching network (GMMN)-based post-filter that provides inter-utterance pitch variation for deep neural network (DNN)-based singing voice synthesis. The natural pitch variation of a human singing voice leads to ... More
When Causal Intervention Meets Image Masking and Adversarial Perturbation for Deep Neural NetworksFeb 09 2019Feb 13 2019Discovering and exploiting the causality in deep neural networks (DNNs) are crucial challenges for understanding and reasoning causal effects (CE) on an explainable visual model. "Intervention" has been widely used for recognizing a causal relation ontologically. ... More
When Causal Intervention Meets Image Masking and Adversarial Perturbation for Deep Neural NetworksFeb 09 2019Discovering and exploiting the causality in deep neural networks (DNNs) are crucial challenges for understanding and reasoning causal effects (CE) on an explainable visual model. "Intervention" has been widely used for recognizing a causal relation ontologically. ... More
Measuring Patient Similarities via a Deep Architecture with Medical Concept EmbeddingFeb 09 2019Evaluating the clinical similarities between pairwise patients is a fundamental problem in healthcare informatics. A proper patient similarity measure enables various downstream applications, such as cohort study and treatment comparative effectiveness ... More
Photorealistic Image Synthesis for Object Instance DetectionFeb 09 2019We present an approach to synthesize highly photorealistic images of 3D object models, which we use to train a convolutional neural network for detecting the objects in real images. The proposed approach has three key ingredients: (1) 3D object models ... More
Learning Ontologies with Epistemic Reasoning: The EL CaseFeb 08 2019We investigate the problem of learning description logic ontologies from entailments via queries, using epistemic reasoning. We introduce a new learning model consisting of epistemic membership and example queries and show that polynomial learnability ... More
Does the "Artificial Intelligence Clinician" learn optimal treatment strategies for sepsis in intensive care?Feb 08 2019From 2017 to 2018 the number of scientific publications found via PubMed search using the keyword "Machine Learning" increased by 46% (4,317 to 6,307). The results of studies involving machine learning, artificial intelligence (AI), and big data have ... More
FSNet: Compression of Deep Convolutional Neural Networks by Filter SummaryFeb 08 2019We present a novel method of compression of deep Convolutional Neural Networks (CNNs). The proposed method reduces the number of parameters of each convolutional layer by learning a 3D tensor termed Filter Summary (FS). The convolutional filters are extracted ... More
Invariant-equivariant representation learning for multi-class dataFeb 08 2019Representations learnt through deep neural networks tend to be highly informative, but opaque in terms of what information they learn to encode. We introduce an approach to probabilistic modelling that learns to represent data with two separate deep representations: ... More
Ask Not What AI Can Do, But What AI Should Do: Towards a Framework of Task DelegabilityFeb 08 2019Although artificial intelligence holds promise for addressing societal challenges, issues of exactly which tasks to automate and the extent to do so remain understudied. We approach the problem of task delegability from a human-centered perspective by ... More
Understanding The Impact of Partner Choice on Cooperation and Social Norms by means of Multi-agent Reinforcement LearningFeb 08 2019Feb 13 2019The human ability to coordinate and cooperate has been vital to the development of societies for thousands of years. While it is not fully clear how this behavior arises, social norms are thought to be a key factor in this development. In contrast to ... More
Understanding The Impact of Partner Choice on Cooperation and Social Norms by means of Multi-agent Reinforcement LearningFeb 08 2019The human ability to coordinate and cooperate has been vital to the development of societies for thousands of years. While it is not fully clear how this behavior arises, social norms are thought to be a key factor in this development. In contrast to ... More
BINet: Multi-perspective Business Process Anomaly ClassificationFeb 08 2019In this paper, we introduce BINet, a neural network architecture for real-time multi-perspective anomaly detection in business process event logs. BINet is designed to handle both the control flow and the data perspective of a business process. Additionally, ... More
Novelty Search for Deep Reinforcement Learning Policy Network Weights by Action Sequence Edit Metric DistanceFeb 08 2019Reinforcement learning (RL) problems often feature deceptive local optima, and learning methods that optimize purely for reward signal often fail to learn strategies for overcoming them. Deep neuroevolution and novelty search have been proposed as effective ... More
Bounded Fuzzy Possibilistic MethodFeb 08 2019This paper introduces Bounded Fuzzy Possibilistic Method (BFPM) by addressing several issues that previous clustering/classification methods have not considered. In fuzzy clustering, object's membership values should sum to 1. Hence, any object may obtain ... More
Progressive Focus Search for the Static and Stochastic VRPTW with both Random Customers and Reveal TimesFeb 08 2019Static stochastic VRPs aim at modeling real-life VRPs by considering uncertainty on data. In particular, the SS-VRPTW-CR considers stochastic customers with time windows and does not make any assumption on their reveal times, which are stochastic as well. ... More
Beyond Least-Squares: Fast Rates for Regularized Empirical Risk Minimization through Self-ConcordanceFeb 08 2019We consider learning methods based on the regularization of a convex empirical risk by a squared Hilbertian norm, a setting that includes linear predictors and non-linear predictors through positive-definite kernels. In order to go beyond the generic ... More
Expressive mechanisms for equitable rent division on a budgetFeb 08 2019We design envy-free mechanisms for the allocation of rooms and rent payments among roommates. We achieve four objectives: (1) each agent is allowed to make a report that expresses her preference about violating her budget constraint, a feature not achieved ... More
Source Traces for Temporal Difference LearningFeb 08 2019This paper motivates and develops source traces for temporal difference (TD) learning in the tabular setting. Source traces are like eligibility traces, but model potential histories rather than immediate ones. This allows TD errors to be propagated to ... More
Mobile Artificial Intelligence Technology for Detecting Macula Edema and Subretinal Fluid on OCT Scans: Initial Results from the DATUM alpha StudyFeb 08 2019Feb 12 2019Artificial Intelligence (AI) is necessary to address the large and growing deficit in retina and healthcare access globally. And mobile AI diagnostic platforms running in the Cloud may effectively and efficiently distribute such AI capability. Here we ... More
Modeling Heterogeneity in Mode-Switching Behavior Under a Mobility-on-Demand Transit System: An Interpretable Machine Learning ApproachFeb 08 2019Recent years have witnessed an increased focus on interpretability and the use of machine learning to inform policy analysis and decision making. This paper applies machine learning to examine travel behavior and, in particular, on modeling changes in ... More
Rethinking the Discount Factor in Reinforcement Learning: A Decision Theoretic ApproachFeb 08 2019Reinforcement learning (RL) agents have traditionally been tasked with maximizing the value function of a Markov decision process (MDP), either in continuous settings, with fixed discount factor $\gamma < 1$, or in episodic settings, with $\gamma = 1$. ... More
Deep execution monitor for robot assistive tasksFeb 07 2019We consider a novel approach to high-level robot task execution for a robot assistive task. In this work we explore the problem of learning to predict the next subtask by introducing a deep model for both sequencing goals and for visually evaluating the ... More
Visual search and recognition for robot task execution and monitoringFeb 07 2019Visual search of relevant targets in the environment is a crucial robot skill. We propose a preliminary framework for the execution monitor of a robot task, taking care of the robot attitude to visually searching the environment for targets involved in ... More