## Picking BERT s Brain Probing for Linguistic Dependencies in Contextualized Embeddings Using Representational Similarity Analysis

Contextualized representations of language are typically motivated by their ability to encode context . We introduce an approach to address this question using Representational Similarity Analysis (RSA) In all cases, we show that BERT’s contextualized embeddings reflect thelinguistic dependency being studied .…

## The Human Effect Requires Affect Addressing Social Psychological Factors of Climate Change with Machine Learning

Machine learning has the potential to aid in mitigating the human effects of climate change . Previous applications of machine learning to tackle the humaneffects in climate change include informing individuals of their carbon footprint and strategies to reduce it .…

## On the Serverless Nature of Blockchains and Smart Contracts

Serverless architecture is more frequently associated with the architectural style for developing cloud-native applications . Blockchains are distributed systems designed to enable collaborative scenarios involving untrusted parties . The decentralizedpeer-to-peer nature of blockchains makes it interesting to consider them inserverless architectures, since resource allocation and management tasks are not required to be performed by users .…

## Exploring the landscapes of computing digital neuromorphic unconventional and beyond

The acceleration race of digital computing technologies seems to be steeringtoward impasses — technological, economical and environmental — a condition that has spurred research efforts in alternative, “neuromorphic” (brain-like)computing technologies . The idea of exploiting nonlinear physical phenomena “directly” for non-digital computing has been explored under names like “unconventional computing”, “natural computing”,”physical computing”, or “in-materio computing” I stake out how a general concept of “computing” can bedeveloped which comprises digital, neuromorphic, unconventional and possible future paradigms .…

## The Reads From Equivalence for the TSO and PSO Memory Models

The verification of concurrent programs remains an open challenge due to thenon-determinism in inter-process communication . The reads-from (RF) equivalence was recently shownto be coarser than the Mazurkiewicz equivalence, leading to impressivescalability improvements for SMC under SC . For TSO and PSO, the standard equivalence has been Shasha-Snir traces .…

## Non Invertible Element Constacyclic Codes over Finite PIRs

In this paper we introduce the notion of $\lambda$-constacyclic codes overfinite rings $R$ for arbitary element $R$. We study thenon-invertible-element constacyClic codes (NIE-consticclic code) over finiteprincipal ideal rings (PIRs) We determine the algebraic structures of all NIE codes over finite chain rings, give the unique form of thesets of the defining polynomials and obtain their minimum Hamming distances .…

## A DC Autotransformer based Multilevel Inverter for Automotive Applications

This paper proposes a novel multilevel inverter for automotive applications . The topology consists of a modular DCDC converter and a tap selector . The DC-DC converter is capable of self-balancing its modules and thus does not require large capacitors which yields a high power density .…

## Uniform auxiliary space preconditioning for HDG methods for elliptic operators with a parameter dependent low order term

The auxiliary space preconditioning (ASP) technique is applied to the HDGschemes for three different elliptic problems with a parameter dependent loworder term . Uniformpreconditioners are obtained for each case and the general ASP theory by J. Xu[21] is used to prove the optimality with respect to the mesh size and uniformity of the low order parameter .…

## Two Way Neural Machine Translation A Proof of Concept for Bidirectional Translation Modeling using a Two Dimensional Grid

Neural translation models have proven to be effective in capturing sufficient information from a source sentence and generating a high-quality targetsentence . However, it is not easy to get the best effect for bidirectional translation using a single model . This paper proposes to build a single end-to-endbidirectionaltranslation model using a two-dimensional grid .…

## Deep learning based discovery of partial differential equations in integral form from sparse and noisy data

Data-driven discovery of partial differential equations (PDEs) has attracted attention in recent years . For PDEs with high-orderderivatives, the performance of existing methods is unsatisfactory, especially when the data is sparse and noisy . New framework combining deep-learning and integral form is proposed to handle the above-mentionedproblems simultaneously, and improve the accuracy and stability of PDEdiscovery .…

## Dendritic trafficking synaptic scaling and structural plasticity

Neuronal circuits internally regulate electrical signaling via a host of homeostatic mechanisms . Two prominent mechanisms, synaptic scaling andstructural plasticity, are believed to maintain average activity within an operating range . However, both mechanisms operate on relatively slow timescales and thus face fundamental limits due to delays .…

Stochastic sparse adversarial attacks (SSAA) are simple, fast and purely noise-based targeted and untargeted attacks of NNC . SSAA offer new examples of sparse (or $L_0$) attacks for which only few methodshave been proposed previously . These attacks are devised by exploiting asmall-time expansion idea widely used for Markov processes .…

## Health Focused Optimal Power Flow

Health-Focused Optimal Power Flow (HF-OPF) proposed to take into account equipment health in operational and physical constraints . The paper addresses theneed for understanding the relationship between health condition index and theoperational constraints in OPF problems . The results show that health conditioninflicts high cost of generation and can lead to infeasibility even with lesscritical faults .…

## The Cost of Simple Bidding in Combinatorial Auctions

We study the complexity of bidding optimally in one-shot combinatorial auction mechanisms . Prior work has largely assumed that bidders only submit bids on their bundles of interest . We show that a single-minded bidder may lose an exponential amount of utility by playing his optimal simple strategy .…

## Wyner Ziv Estimators Efficient Distributed Mean Estimation with Side Information

distributed mean estimation is an important primitive that arises in many distributed learning and optimization scenarios such as federated learning . We present an alternative Wyner-Ziv estimator that uses correlated sampling . This latter setting offers . perhaps will be of interest in practice when the number of users is large and .…

## The 4 Adic Complexity of A Class of Quaternary Cyclotomic Sequences with Period 2p

In cryptography, we hope a sequence over $m$ with period $N$ having larger $m$-adic complexity . We determine the complexity of thequaternary cyclotomic sequences with period 2$p$ defined in [6] The mainmethod we utilized is a quadratic Gauss sum $G_{p}$ valued in$\mathbb{Z}_{4^N-1}$ which can be seen as a version of classical quadraticallyGauss sum .…

## Reinforced optimal control

Least squares Monte Carlo methods are a popular numerical approximationmethod for solving stochastic control problems . The choice of basis functions is crucial for the accuracy of the method . We extend the reinforced regression method to a generalclass of stochastically control problems, while considerably improving the method’s efficiency .…

## Investigating Emotion Color Association in Deep Neural Networks

It has been found that representations learned by Deep Neural Networks (DNNs)correlate very well to neural responses measured in primates’ brains . Past studies have shown that particular colors can be associated with specific emotion arousal in humans . Do deep neural networks also learn implicitassociations in stimuli, particularly, an emotion-color association betweenimage stimuli?…

## A finite element scheme for an initial value problem

A new Hamilton principle of convolutional type, completely compatible with the initial conditions of an IVP, has been proposed in a recent publicationarXiv:1912.08490v1 [math-ph]. In the present paper the possible use of thisprinciple for the formulation of a FE scheme adjusted to dynamical problems is investigated .…