Beyond ANN Exploiting Structural Knowledge for Efficient Place Recognition

Many approaches in the literature perform computationally inefficient full image comparisons between queries and all database images . In this paper, we propose a novel fast sequence-based method for efficient place recognition that can be applied online . It uses relocalization to recover from sequence losses, and exploits usually available but often unused intra-database similarities for potential detection of all matching database images for each query in case of loops or stops in the database .…

Learning Frequency aware Dynamic Network for Efficient Super Resolution

Deep learning based methods, especially convolutional neural networks (CNNs) have been successfully applied in the field of single image super-resolution(SISR) To obtain better fidelity and visual quality, most of existing networksare of heavy design with massive computation . To this end, this paper explores a novel frequency-awaredynamic network for dividing input into multiple parts according to itscoefficients in the discrete cosine transform (DCT) domain .…

Uncertainty Based Biological Age Estimation of Brain MRI Scans

Current BA estimation approaches are restricted to skeletal images or rely on non-imaging modalities that yield a whole-body BA assessment . Various organ systems may exhibit different aging characteristics due to lifestyle and genetic factors . In thisinitial study, we propose a new framework for organ-specific BA estimation using 3D magnetic resonance image (MRI) scans .…

Efficient Intrusion Detection Using Evidence Theory

Intrusion Detection Systems (IDS) are now an essential element when it comesto securing computers and networks . Despite the huge research efforts done inthe field, handling sources’ reliability remains an open issue . To address thisproblem, this paper proposes a novel contextual discounting method based on reliability and their distinguishing ability between normal andnormal behavior .…

Reasoning about the garden of forking paths

Lazy evaluation is a powerful tool for functional programmers . It enables the expression of on-demand computation and compositionality . However, the stateful nature of lazy evaluation makes it hard to analyze a program’s computational cost . In this work, we present a novel and simple framework for formally reasoning about lazy computation costs .…

Multi view Subword Regularization

Multilingual pretrained representations generally rely on subwordsegmentation algorithms to create a shared multilingual vocabulary . Standard heuristic algorithms often lead to sub-optimal segmentation, especially for languages with limited amounts of data . We propose Multi-view Subword Subword Regularization (MVR), a method that enforces the consistencybetween predictions of using inputs tokenized by the standard and probabilisticsegmentations .…

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 .…

Towards HPC simulations of Billion cell Reservoirs by Multiscale Mixed Methods

A three-dimensional parallel implementation of Multiscale Mixed Methods is proposed for multi-corecomputers . The proposed implementation relies on direct solvers for both local problems and the interface coupling system . We find good weak and strong scalalability ascompared against a state-of-the-art global fine grid solver based on AlgebricMultigrid preconditioning in single and two-phase flow problems .…

Gathering of seven autonomous mobile robots on triangular grids

In this paper, we consider the gathering problem of seven autonomous mobilerobots on triangular grids . The gathering problem requires that, starting fromany connected initial configuration where a subgraph induced by all robot nodes constitutes one connected graph, robots reach aconfiguration such that the maximum distance between two robots is minimized .…

Neural Motion Prediction for In flight Uneven Object Catching

In-flight objects capture is extremely challenging . The robot is required to complete trajectory prediction, interception position calculation and motionplanning in sequence within tens of milliseconds . We introduce the Neural Acceleration Estimator (NAE) that estimates the varyingacceleration by observing a small fragment of previous deflected trajectory .…

Representation Theorem for Matrix Product States

In this work, we investigate the universal representation capacity of theMatrix Product States (MPS) from the perspective of boolean functions andcontinuous functions . We show that MPS can accurately realize arbitrary boolean functions by providing a construction method of the corresponding MPS structure for an arbitrarily given gate .…

A new interpretation of Tikhonov regularization

Tikhonov regularization with square-norm penalty for linear forward operators has been studied extensively in the literature . However, the results onconvergence theory are based on technical proofs and difficult to interpret . In this paper we present a new strategy to study theproperties of a regularization method .…

Combinatorial Resultants in the Algebraic Rigidity Matroid

We develop algorithm for computing circuit polynomials in the algebraicrigidity matroid associated to the Cayley-Menger ideal for $n$ points in 2D . We show that every rigidity circuit has a construction tree based on this operation . Our algorithm performs an algebraicelimination guided by the construction tree, and uses classical resultants,factorization and ideal membership .…

Improving reproducibility in synchrotron tomography using implementation adapted filters

For reconstructing large tomographic datasets fast, filteredbackprojection-type or Fourier-based algorithms are still the method of choice . We propose a way to reduce differences by optimising the filter used in analytical algorithms . These filters can be computed using awrapper routine around a black-box implementation of a reconstructionalgorithm, and lead to quantitatively similar reconstructions .…

Mobile Teleoperation Evaluation of Wireless Wearable Sensing of the Operator s Arm Motion

Teleoperation platforms often require the user to be situated at a fixed location to both visualize and control the movement of the robot . This creates a barrier between doctors and patients that does not exist in normal surgery . We propose a mobile telesurgery solution where surgeons are nolonger mechanically limited to control consoles and are able to teleoperate therobots from the patient bedside, using their arms equipped with wirelesssensors and viewing the endoscope video via optical see-through HMDs .…

Improving Generalization of Transfer Learning Across Domains Using Spatio Temporal Features in Autonomous Driving

Training vision-based autonomous driving in the real world can be inefficient and impractical . Vehicle simulation can be used to learn in the virtual world,and the acquired skills can be transferred to handle real-world scenarios more effectively . We propose a CNN+LSTM transfer learning framework to extract the spatio-temporal featuresrepresenting vehicle dynamics from scenes .…

Improving scalability and reliability of MPI agnostic transparent checkpointing for production workloads at NERSC

Checkpoint/restart (C/R) provides fault-tolerant computing capability,enables long running applications, and provides scheduling flexibility forcomputing centers to support diverse workloads . MANA was not ready to use with NERSC’s diverseproduction workloads, which are dominated by MPI and hybrid MPI+OpenMP applications . The lessons learned from making MANAproduction-ready for HPC applications will be useful for C/R tool developers, supercomputing center and HPC end-users alike.…

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 .…

Quantum Private Distributed Learning Through Blind Quantum Computing

Private distributed learning studies the problem of how multiple distributedentities collaboratively train a shared deep network with their private data . With the security provided by the protocols of blind quantumcomputation, the cooperation between quantum physics and machine learning maylead to unparalleled prospect for solving private distributed learning tasks .…

BLOFF A Blockchain based Forensic Model in IoT

Cybercriminals of today have the tools and the technology to deploy millions of sophisticated attacks . Digital forensics comes into play, but it is not easy to conduct a forensic investigation in IoT systems because of the heterogeneous nature of the IoT environment .…

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 .…

Return Oriented Programming on RISC V

This paper provides the first analysis on the feasibility of Return-OrientedProgramming (ROP) on RISC-V . We show the existence of a new class of gadgets, usingseveral Linear Code Sequences And Jumps (LCSAJ) undetected by currentGalileo-based ROP gadget searching tools . We argue that this class is rich enough on Risc-V to mount complex ROP attacks, bypassing traditionalmitigation like DEP, ASLR, stack canaries, G-Free, as well as somecompiler-based backward-edge CFI, by jumping over any guard inserted by acompiler to protect indirect jump instructions .…

Instantaneous SED coding over a DMC

In this paper, we propose a novel code for transmitting a sequence of $n$message bits in real time over a discrete-memoryless channel . The message bits stream into the encoder one by one at random time instants . The code adopts the SED rule to apply to the evolving message alphabet that contains all the possible variable-length strings that the source could have emitted up to that time .…

Construction D Lattices for Power Constrained Communications

Two encoding methods and a decoding algorithm for Construction D’ codinglattices that can be used with shaping lattices for power-constrained channels are given . Tail-biting convolutional codes have higher shaping gain than that of zero-tailed codes . Rate 1/3 codes provide a more favorable performance-complexity trade-off than rate 1/2 codes .…

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 .…

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 .…