Cost aware Integration Process Modeling in Multiclouds

Integration as a service (INTaaS) is the centrepiece of current corporate,cloud and device integration processes . We propose a design-time placement for processes in multicloudsthat is cost-optimal for INTaaS problem sizes . The process modeler’s perspective is investigated based on a new cost-aware modeling process, featuring the interaction between the user and the INTaa’s vendor through ad-hoc cost calculation and correctness-preserving, process cost reduction proposals .…

Constant congestion brambles in directed graphs

The Directed Grid Theorem was a conjecture for nearly 20 years . Kawarabayashi and Kreutzer proved it in 2015 . The function $f$ obtained in the proof is very fast growing . In this work, we show that if one relaxes directed grid to bramble of congestion, one can obtain a polynomial bound .…

AngryBERT Joint Learning Target and Emotion for Hate Speech Detection

Most of the existing methods adopt asupervised approach that depended heavily on the annotated hate speechdatasets, which are imbalanced and often lack training samples for hateful content . This paper addresses the research gaps by proposing a novel multitasklearning-based model, AngryBERT, which jointly learns hate speech detection with sentiment classification and target identification as secondary relevanttasks .…

ICFP 2020 Post Conference Report

This document describes the ICFP 2020 virtual conference, including the planning process and the criteria that informed its design, plus feedback from the post-conference survey . It is intended to provide a record of the event and advice to future organizers of virtual conferences .…

Is Medical Chest X ray Data Anonymous

Medical data contains sensitive patient-related information and is usually anonymized by removing patient identifiers, e.g., patient names before publication . We are the first to show that awell-trained deep learning system is able to recover the patient identity fromchest X-ray data .…

A Study of Automatic Metrics for the Evaluation of Natural Language Explanations

As transparency becomes key for robotics and AI, it will be necessary toevaluate the methods through which transparency is provided . Here, we exploreparallels between the generation of such explanations and evaluation of Natural Language Generation . We find that embedding-based automatic NLG evaluationmethods, such as BERTScore and BLEURT, have a higher correlation with humanratings, compared to word-overlap metrics, like BLEU and ROUGE .…

Siamese Network Features for Endoscopy Image and Video Localization

Conventional endoscopy and Wireless Capsule Endoscopy (WCE) are knowntools for diagnosing gastrointestinal (GI) tract disorders . Localizing frames can provide valuable information about the anomaly location and also can helpclinicians determine a more appropriate treatment plan . The proposed method can be used in frame localization, which can help in video summarization and anomaly detection, and showed better results .…

Neural Networks and Denotation

We introduce a framework for reasoning about what meaning is captured by theneurons in a trained neural network . We identify important properties captured decisively in trained neural networks . We observe that the label proportion of a property denoted by a neuronis dependent on the depth of a network; we analyze thesedependencies, and provide an interpretation of them .…

Flexible FOND Planning with Explicit Fairness Assumptions

We consider the problem of reaching a propositional goal condition infully-observable non-deterministic (FOND) planning under a general class offairness assumptions that are given explicitly . The fairness assumptions are of the form A/B and say that state trajectories that contain infinite occurrences of an action a from A in a state s and finite occurrence of actions from B, must also contain infinite occurrence of each one of the possible outcomes .…

Probabilistic Grammatical Evolution

Probabilistic Grammatical Evolution (PGE) is one of the most popular Genetic Programming variants . It has been used with success in several problem domains . PGE has a better performance than GE, with statistically significant differences, and achieved similar performance whencomparing with SGE .…

Sample efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model

Curiosity Contrastive Forward Dynamics Model (CCFDM) uses contrastive learning to train its deepconvolutional neural network-based image encoder . CCFDM provides intrinsic rewards, produced based on FDM prediction error, encourages the curiosity of the RL agent to improveexploration . The diverge and less-repetitive observations provide by both ourexploration strategy and data augmentation available in contrastive learnimprove not only the sample efficiency but also the generalization.…

Boosting ship detection in SAR images with complementary pretraining techniques

Deep learning methods have made significant progress in ship detection insynthetic aperture radar (SAR) images . The proposed method won the sixth place of ship detection in SAR images in 2020Gaofen challenge . We propose an optical shipdetector (OSD) pretraining technique, which transfers the characteristics ofships in earth observations to SAR images from a large-scale aerial imagedataset .…

Geometric Change Detection in Digital Twins using 3D Machine Learning

Digital twins are meant to bridge the gap between real-world physical systems and virtual representations . We demonstrate a novel approach to geometricchange detection in the context of a digital twin . By only storing data associated with a detected change in pose, we minimize necessary storage and bandwidth requirements while still being able to recreate the 3D scene on demand .…

Cloth Manipulation Planning on Basis of Mesh Representations with Incomplete Domain Knowledge and Voxel to Mesh Estimation

We consider the problem of open-goal planning for robotic cloth manipulation . Core of our system is a neural network trained as a forward model of cloth behaviour under manipulation, with planning performed through backpropagation . The system’s mesh estimation, prediction, and planning ability onsimulated cloth for sequences of one to three manipulations.…

Promise Problems Meet Pseudodeterminism

The Acceptance Probability Estimation Problem (APEP) is to additivelyapproximate the acceptance probability of a Boolean circuit . The main conceptual contribution of this work is to establish that theexistence of a pseudodeterministic algorithm for APEP is fundamentallyconnected to the relationship between probabilistic promise classes and the corresponding standard complexity classes .…

Electronic Structure in a Fixed Basis is QMA complete

Finding the ground state energy of electrons subject to an external electricfield is a fundamental problem in computational chemistry . Schuch and Verstraete haveshown hardness for the electronic-structure problem with an additionalsite-specific external magnetic field, but without the restriction to a fixedbasis .…

A novel approach for the efficient modeling of material dissolution in electrochemical machining

This work presents a novel approach to efficiently model anodic dissolution in electrochemical machining . Earlier modeling approaches employ a strict spacediscretization of the anodic surface that is associated with a remeshingprocedure at every time step . This inner variable allows the modeling of the complex dissolution process without the necessity of computationally expensiveremeshing by controlling the effective material parameters .…

Online Learning with Radial Basis Function Networks

We investigate the benefits of feature selection, nonlinear modelling and online learning with forecasting in financial time series . We also find that, in the subset of models we use,sequential learning in time with online Ridge regression, provides the best multi-step ahead forecasts, and continual learning with an online radial basisfunction network .…

An FE DMN method for the multiscale analysis of fiber reinforced plastic components

Each Gauss point of themacroscopic finite element model is equipped with a deep material network (DMN) The DMN is capable of accelerating two-scale simulations significantly, providing possible speed-ups of several magnitudes . Wediscuss how to extend direct direct DMNs to account for varying fiber orientation, and propose a simplified sampling strategy which significantly speeds up the training process .…

Enclosing Depth and other Depth Measures

We study families of depth measures defined by natural sets of axioms . Weshow that any such depth measure is a constant factor approximation of Tukeydepth . We further investigate the dimensions of depth regions, showing that theCascade conjecture, introduced by Kalai for Tverberg depth, holds for all depthmeasures .…

Rectilinear Steiner Trees in Narrow Strips

A rectilinear Steiner tree for a set $P$ of points in $mathbb{R}^2$ is atree that connects the points using horizontal and vertical linesegments . We present an algorithm with running time $n^{O(\sqrt{\delta) n$ for sparse point sets, that is, point sets where each$1\times\delta$ rectangle inside the strip contains $O(1)$ points .…

Get Your Vitamin C Robust Fact Verification with Contrastive Evidence

Typical fact verification models use retrieved written evidence to verify claims . Evidence sources often change over time as more information is gathered and revised . In order to adapt, models must be sensitive to subtledifferences in supporting evidence . We present VitaminC, a benchmark infused with challenging cases that require models to discern and adjust to slight factual changes .…