Active Imitation Learning with Noisy Guidance

LEAQI learns a differenceifier that predicts when the expert is likely to disagree with the heuristic, and queries the expert only when necessary . We apply the algorithm to threesequence labeling tasks, demonstrating significantly fewer queries to the expert and comparable (or better) accuracies over a passive approach .…

Good Counterfactuals and Where to Find Them A Case Based Technique for Generating Counterfactuals for Explainable AI XAI

Counterfactual cases can begenerated by permuting problem-features until a class change is found . Psychologically, they are much more causally informative than factualexplanations . They are more likely to be GDPR-compliant than factual explanations . We propose a newcase based approach for generating counterfactuals using novel ideas about thecounterfactual potential and explanatory coverage of a case-base .…

Active Measure Reinforcement Learning for Observation Cost Minimization

Standard reinforcement learning algorithms assume that the observation of the next state comes instantaneously and at no cost . Multiple classes of state observations are possible, each of which has an associated cost . We propose the active measure RL framework(Amrl) as an initial solution to this problem where the agent learns tomaximize the costed return, which we define as the discounted sum of rewards minus the sum of observation costs .…

Is your chatbot GDPR compliant Open issues in agent design

Conversational agents open the world to new opportunities for human interaction and ubiquitous engagement . As their conversational abilities and knowledge has improved, these agents have begun to have access to an increasingvariety of personally identifiable information and intimate details on their user base .…

On the Causes and Consequences of Deviations from Rational Behavior

This paper presents novel evidence for the prevalence of deviations from rational behavior in human decision making . The analysis is based on move-by-move data from chesstournaments and an identification strategy that compares behavior of professional chess players to a rational behavioral benchmark that is constructed using modern chess engines .…

Learning Whole Body Human Robot Haptic Interaction in Social Contexts

This paper presents a learning-from-demonstration (LfD) framework for teaching human-robot social interactions that involve whole-body hapticinteraction . Using a teleoperated bimanual robotequipped with 61 force sensors, we experimentally demonstrate that a modeltrained with 121 sample hugs from 4 participants generalizes well to unseen input and human partners .…

History Aware Question Answering in a Blocks World Dialogue System

It is essential for dialogue-based spatial reasoning systems to maintain memory of historical states of the world . Referring to historical states may be crucial for enabling collaborative planning (e.g., for planning to return to a previous state, or diagnosing a past misstep) In thispaper, we approach the problem of spatial memory in a multi-modal spokendialogue system capable of answering questions about interaction history in a physical blocks world setting .…

Experimental evaluation of quantum Bayesian networks on IBM QX hardware

A Quantum Bayesian Network (QBN) is a quantum version of the Bayesian network that utilizes the principles of quantum mechanical systems to improve the computational performance of various analyses . We construct a quantum circuit to represent the 4-node BN using Qiskit, and run the circuit on nineIBM quantum devices: Yorktown, Vigo, Ourense, Essex, Burlington, London, Rome,Athens and Melbourne .…

How the planned V0 railway line would increase the resilience of the railway network of Hungary against attacks

The spatial distribution of the railway crossings on the river Danube in Hungary is very uneven . There is only one electrified and double-tracked bridge in the country, the Southern Railway Bridge in Budapest . The long-planned V0 railway line that is to be cross the Danube approximatelyhalfway between Budapest and Baja would not only help to redistribute the total flow which currently passes through almost exclusively the Southernbridge .…

Structural Reductions Revisited

Structural reductions are a powerful class of techniques that reason on aspecification with the goal to reduce it before attempting to explore its behaviour . In this paper we present new structural reduction rules forverification of deadlock freedom and safety properties of Petri nets .…

Survey Machine Learning in Production Rendering

This survey summarizes several of the most dramatic improvements in using deep neural networks over traditionalrendering methods . This survey covers the fundamental principles of machine learning and its applications, such as denoising, path guiding, and other notoriously difficult light transportsituations .…

Haptic Rendering of Thin Deformable Objects with Spatially Varying Stiffness

A novel approach to render thin, deformable objects having spatially varyingstiffness (inhomogeneous material) We use the classical Kirchhoff thin platetheory to compute the deformation . The method wasvalidated through user experiments and was found to be realistic . We use an area-preserving mapping technique – Gall-Peters mapping – to approximate the 3D surface locally by a 2D plane .…

Eye Gaze Controlled Robotic Arm for Persons with SSMI

People with severe speech and motor impairment (SSMI) often uses a technique called eye pointing to communicate with outside world . We aimed to automate the eye tracking process electronically byusing commercially available tablet, computer or laptop . The eye gaze tracker is used todevelop a video see through based AR (augmented reality) display that controls a robotic device with eye gaze and deployed for a fabric printing task .…

Differentials and distances in probabilistic coherence spaces extended version

In probabilistic coherence spaces, morphisms are analytic and therefore smooth . We explore two related applications of the corresponding derivatives . We show howderivatives allow to compute the expectation of execution time in the weak headreduction of probabilism PCF . Next we apply a general notion of”local” differential of morphisms to the proof of a Lipschitz property of these morphisms .…

Agent Based Simulation of Collective Cooperation From Experiment to Model

Simulation models of pedestrian dynamics have become an invaluable tool forevacuation planning . Simulated agents avoid collisions through mechanisms that belong to each individual, such as being repelled from each other by imaginaryforces . But classic locomotion models fail when collective cooperation is called for, notably when an agent, say a first-aid attendant, needs to forge apath through a densely packed group .…

Sustainable and resilient strategies for touristic cities against COVID 19 an agent based approach

Touristic cities will suffer from COVID-19 emergency because of its economic impact on their communities . The first emergency phases involved a wide closure of such areas to support “social distancing” measures (i.e. travels limitation;lockdown of (over)crowd-prone activities) In the second phase, individual’srisk-mitigation strategies (facial masks) could be properly linked to “socialdistancing” to ensure re-opening touristic cities to visitors .…

Spoken digit classification using a spin wave delay line active ring reservoir computing

As a test of general applicability, we use the recently proposed spin-wavedelay line active-ring reservoir computer to perform the spoken digitrecognition task . On this, classification accuracy of up to 93% are achieved . The tested device prototype employs improved spin wave transducers (antennas) The resultingSTM and PC capacities reach maximum values of 4.77 and 1.47 respectively .…

Experimental Analysis of Safety Application Reliability in V2V Networks

Vehicle-to-Vehicle (V2V) communication networks enable safety applicationsvia periodic broadcast of Basic Safety Messages . Beacons include time-critical information such as sender vehicle’s location, speed and direction . Vehicle density may be very high in certainscenarios and such V2V networks suffer from channel congestion and undesirablelevel of packet collisions .…

Context Aware Collaborative Intelligence with Spatio Temporal In Sensor Analytics in a Large Area IoT Testbed

A real-time co-optimization algorithm has been developed for minimizing the energy consumption in the network, hencemaximizing the overall battery lifetime of individual nodes . Measurement results show that the proposed ISA consumes ~467X lower energy as compared totraditional Bluetooth Low Energy (BLE) communication, and ~69,500X less energyas compared with Long Range (LoRa) communication .…

Group In Group Inference from Wireless Traces of Mobile Devices

This paper proposes Group-In, a wireless scanning system to detect static or mobile people groups in indoor or outdoor environments . The key problem addressed in this work is to detect not only static groups but also moving groups with a multi-phased approach based only noisy wirelessReceived Signal Strength Indicator (RSSIs) observed by multiple wirelessscanners .…

Blockchain and Fog Computing for Cyberphysical Systems The Case of Smart Industry

Blockchain and fog computing are currently being evaluated as potential support for software and a wide spectrum of applications, ranging from bankingpractices and digital transactions to cyber-physical systems . These systems are designed to work in highly complex, sometimes even adversarial, environments,and to synchronize heterogeneous machines and manufacturing facilities in cybercomputational space .…

Modular WSS based OXCs for Large Scale Optical Networks

The explosive growth of broadband applications calls for large-scale opticalcross-connects (OXCs) However, the classical wavelength selective switch (WSS)based OXC is not scalable in terms of the size of employed WSSs and the cabling complexity . We propose a three-phase approach to construct a modular WSS-based O.XC…

Information transfer based on precision time synchronization via wireless interferometry

The growing demand of high-bandwidth and low-latency information transfer in information and communication technologies such as data centres and in-vehiclenetworks has increased the importance of optical communication networks in recent years . However, complicated arbitration schemes can impose significant overheads in data transfer, which may inhibit the full exploitation of the potential of optical interconnects .…

Autonomous Task Dropping Mechanism to Achieve Robustness in Heterogeneous Computing Systems

Robustness of a distributed computing system is defined as the ability tomaintain its performance in the presence of uncertain parameters . Uncertainty is a key problem in heterogeneous (and even homogeneous) distributed computingsystems that perturbs system robustness . We use probabilisticanalysis to develop an autonomous proactive task dropping mechanism to attainour robustness goal .…

Domain Specific Multi Level IR Rewriting for GPU

Traditional compilers operate on a single generic intermediate representation . These IRs are usually low-level and close to machine instructions . Multi-level rewriting instantiates a hierarchy of dialects (IRs), lowers programs level-by-level, and performs code transformations at the most suitable level .…

On the benefit of 3 tier SOA architecture promoting information sharing among TMS systems and Brazilian e Government Web Services A CT e case study

Service-Oriented Architecture (SOA) has emerged originating new prospects for system integration within organizations and external partners . Brazilian e-Governmentinitiatives has introduced as a national electronic document model known asElectronic Transportation Knowledge (CT-e) This paper proposes an architectural solution to integrate TMS systems with CT-e WebService applying concepts of SOA and N-tier architecture .…

Illuminating a Blind Spot in Digitalization Software Development in Sweden s Private and Public Sector

Three out of ten Swedish firms, across industry sectors, develop software in-house . The corresponding figure for Sweden’s government agencies is four outof ten . The digitalization of society will continue, thus the demand for softwaredevelopers will further increase . Many private firms report that the limitedsupply of software developers in Sweden is directly affecting their expansion plans .…

Selecting third party libraries The practitioners perspective

Selecting the wrong library can severely impact a software project in terms of cost, time, and development effort . The selection of third-party libraries is an essential element of virtuallyany software development project . In practice, the selection of libraries is conducted in an ad-hoc manner, where dozens of factors play aninfluential role in the decision .…