## A model for traffic incident prediction using emergency braking data

A Random Forest model trained on artificially balanced (under-sampled) data provided the highest classification accuracy of 85% on the originalimbalanced data . We present a prototype implementing a traffic incident prediction model for Germany based on emergency braking data from Mercedes-Benz vehicles as well as weather, traffic and road data, respectively .…

## From System Level Synthesis to Robust Closed loop Data enabled Predictive Control

The Willem’s fundamental lemma and the system level synthesis characterizetrajectories generated by a linear system . While the former method is valid fordeterministic LTI systems, the latter one is further effective for stochasticlinear time varying systems . A causal feedback structure is further derived, leading to an computational cost similar to standard robust MPC with full statemeasurements .…

## Transformer Language Models with LSTM based Cross utterance Information Representation

The effective incorporation of cross-utterance information has the potential to improve language models (LMs) for automatic speech recognition (ASR) The R-TLM uses hidden states in a long short-term memory (LSTM) LM to encode the information . The proposed system was evaluated on the AMI meeting corpus, theEval2000 and the RT03 telephone conversation evaluation sets .…

## Multiversal views on language models

The virtuosity of language models like GPT-3 opens a new world of possibility for human-AI collaboration in writing . In this paper, we present a framework inwhich generative language models are conceptualized as multiverse generators . We call for exploration into this commonality through new formsof interfaces which allow humans to couple their imagination to AI to write,explore, and understand non-linear fiction .…

## The Structure of Minimum Vertex Cuts

In this paper we continue a long line of work on representing the cutstructure of graphs . We classify the types minimum vertex cuts, and the possible relationships between multiple minimum vertices . We exhibit a simple $O(\kappan)-space data structure that can quickly answer pairwise$(\kappa+1)-connectivity queries in a $kappa$-connected graph .…

## Understanding the attitudes knowledge sharing behaviors and task performance of core developers A longitudinal study

Prior research has established that a few individuals generallydominate project communication and source code changes during softwaredevelopment . Core developers’ attitudes and knowledge sharing behaviors were linked to their involvement in actual software development and the demands of their wider teams .…

## Physics Informed Graphical Neural Network for Parameter State Estimations in Power Systems

Parameter Estimation and State Estimation (SE) are the most wide-spread engineering tasks in the system engineering . Deep Learning (DL) holds the promise oftackling the challenge, however in so far, it did not win trust of the system operators because of the lack of the physics of electricity based, interpretations .…

## Leveraging Artificial Intelligence to Analyze Citizens Opinions on Urban Green Space

The quality of urban green space has been measured by expertassessments, including in-situ observations, surveys, and remote sensinganalyses . Location data platforms, such as TripAdvisor, can provide people’sopinion on many destinations and experiences, including UGS . Such an application can support local authorities andstakeholders in their understanding of and justification for future investments in urban green spaces, says the author of a new paper on the subject of urban greenspace quality assessments .…

## A more accurate view of the Flat Wall Theorem

We introduce a supporting combinatorial framework for the Flat Wall Theorem . We suggest two variants of the theorem and introduce a new,more versatile, concept of wall homogeneity as well as the notion of regularity in flat walls . All proposed concepts and results aim at facilitating the use of the irrelevant vertex technique in future algorithmic applications .…

## A hybrid variance reduced method for decentralized stochastic non convex optimization

This paper considers decentralized stochastic optimization over a network of~$n$ nodes . Each node possesses a smooth non-convex local cost function . The goal of the networked nodes is to find an~$\epsilon$-accurate first-order stationary point of the sum of the local costs .…

## Differences in the spatial landscape of urban mobility gender and socioeconomic perspectives

In society, many of our routines and activities are linked to our ability to travel . Gender-centred issues can amplify other sources of mobility disadvantages . This is unevenly affecting the pool of opportunities men and women have access to .…

## A Little Pretraining Goes a Long Way A Case Study on Dependency Parsing Task for Low resource Morphologically Rich Languages

The bottleneck of massive labeled data limits the effectiveness of these approaches for low resource languages . We perform experiments on 10 MRLs in low-resource settings to measure the efficacy of our proposed pretraining method . We observe an average absolute gain of 2 points (UAS) and 3.6 points (LAS) Code and data available at:https://://://github.com/jivnesh/LCM.LCM…

## Improving Zero shot Neural Machine Translation on Language specific Encoders Decoders

Recently, universal neural machine translation (NMT) with sharedencoder-decoder gained good performance on zero-shot translation . Unlike universal NMT, jointly trained language-specific encoders-decoders aim toachieve universal representation across non-shared modules, each of which isfor a language or language family . We propose to generalizethe non-shottranslation architecture by differentiating theTransformer layers between language-Specific and interlingua .…

## ReLU Neural Networks for Exact Maximum Flow Computation

Understanding the great empirical success of artificial neural networks is currently one of the hottest research topics in computer science . In this paper we study the expressive power of NNswith rectified linear units from a combinatorial optimization perspective . We show that, given a directed graph with $n$ nodes and $m$ arcs,there exists an NN of polynomial size that computes a maximum flow from any possible real-valued arc capacities as input .…

## Optimizing Inference Performance of Transformers on CPUs

The Transformer architecture revolutionized the field of natural languageprocessing (NLP) Transformers-based models (e.g., BERT) power many importantWeb services, such as search, translation, question-answering, etc. The optimizations are evaluated using theinference benchmark from HuggingFace, and are shown to achieve the speedup of up to x2.36 .…

## VARA TTS Non Autoregressive Text to Speech Synthesis based on Very Deep VAE with Residual Attention

This paper proposes VARA-TTS, a non-autoregressive (non-AR) text-to-speech(TTS) model . It uses a very deep Variational Autoencoder (VDVAE) with ResidualAttention mechanism, which refines the textual-to.-acoustic alignmentlayer-wisely . An utterance-level speaking speed factor is computed by a jointly-trained speaking speed predictor, which takes the mean-pooled latent variables of the coarsest layer as input, to determine number of acousticframes at inference .…

## Fair Robust Assignment using Redundancy

We study the consideration of fairness in redundant assignment formulti-agent task allocation . Solving this problem optimally is NP-hard . We exploit properties ofsupermodularity to propose a polynomial-time, near-optimal solution . Empirically, our algorithm outperforms benchmarks, scales to large problems, and provides improvements in both fairness and average utility.…

## Supporting search engines with knowledge and context

We aim to support search engines in leveraging knowledge while accounting for context . We study how to make structured knowledge moreaccessible to the user when the search engine proactively provides such knowledge as context to enrich search results . We propose to model query resolution as a term classification task and propose a method to address it .…

## Two Training Strategies for Improving Relation Extraction over Universal Graph

This paper explores how the Distantly Supervised Relation Extraction (DS-RE) can benefit from the use of a Universal Graph (UG) The UG is the combination of a Knowledge Graph (KG) and a large-scale text collection . We propose two training strategies: Path Type Adaptive Pretraining and Complexity Ranking Guided Attention .…

## From perspective maps to epigraphical projections

The projection onto the epigraph or a level set of a closed proper convexfunction can be achieved by finding a root of a scalar equation . The approach is based on the variational-analytic properties of general convexoptimization problems that are (partial) infimal projections of the sum of the function in question and the perspective map of a convex kernel .…

## Do as I mean not as I say Sequence Loss Training for Spoken Language Understanding

Spoken language understanding (SLU) systems extract transcriptions, as well as semantics of intent or named entities from speech . We propose non-differentiable sequence losses based on SLU metrics as a proxy for semantic error . We show that custom sequence loss training is the state-of-the-art on open SLU datasets and leads to 6% relative improvement in both ASR and NLU performance metrics on large proprietary datasets .…

## Deep Reinforcement Learning for Backup Strategies against Adversaries

We aim towards mathematically modeling the underlying threat models and decision problems . By formulating backup strategies in the language of stochastic processes, we can translate the challenge of findingoptimal defenses into a reinforcement learning problem . This enables us totrain autonomous agents that learn to optimally support planning of defenseprocesses.…

## Well posedness theory for nonlinear scalar conservation laws on networks

We consider nonlinear scalar conservation laws posed on a network . We establish $L^1$ stability, and thus uniqueness, for weak solutions satisfying the entropy condition . We demonstrate themethod’s properties through several numerical experiments . In one important case — for monotone fluxes with an upwinddifference scheme — we show that the set of (discrete) stationary solutions is sufficiently large to suit our general theory .…

## Potential Singularity Formation of 3D Axisymmetric Navier Stokes Equations with Degenerate Variable Diffusion Coefficients

An important feature of this potential singularity is that the solution develops a two-scaletraveling wave that travels towards the origin . The driving mechanism is due to twoantisymmetric vortex dipoles that generate a strong shearing layer in both theradial and axial velocity fields .…

## Contrastive Unsupervised Learning for Speech Emotion Recognition

Speech emotion recognition (SER) has long suffered from a lack of large-scale labeled datasets . We show that the contrastive predictive coding (CPC) method can learn salientrepresentations from unlabeled datasets . In our experiments, this method achieved state-of-the-art correlation coefficient (CCC) performance for all emotionprimitives (activation, valence, and dominance) on IEMOCAP.…

## Feasibility Study of Microsecond Pulsed Microwave Ablation using a Minimally Invasive Antenna

A thin floating-sleevedipole ablation probe can withstand pulsed power delivery with peak powers as high as 25 kW, with pulse widths on the order of 1 us . Pulsed microwave ablation (MWA) is an alternative to continuous wave continuous wave (CW) MWA .…

## DEEPF0 End To End Fundamental Frequency Estimation for Music and Speech Signals

F0 estimation is important in various speech processing and information retrieval applications . Existing deep learning models for pitch estimations have relatively limited learning capabilities due to their shallow receptive field . The proposed model addresses this issue by extending the receptive field of a network by introducing the dilated convolutionalblocks into the network .…