Can Explanations Be Useful for Calibrating Black Box Models

Aims to improve a black box model’s performance on a new domain given examples from the new domain . We show that thecalibration features transfer to some extent between tasks and shed light on how to effectively use them . We experiment with our method on two tasks, extractive questionanswering and natural language inference, covering adaptation from severalpairs of domains .…

Socially assistive robots deployment in healthcare settings a global perspective

Social robots are finding their place in societyis for healthcare-related applications . Yet, very little research has mapped the deployment of socially assistive robots in real settings . Using adocumentary research method, we were able to trace back 279 experiences of SARsdeployments in hospitals, elderly care centers, occupational health centers, private homes, and educational institutions worldwide .…

Domain Adaptation on Semantic Segmentation with Separate Affine Transformation in Batch Normalization

In recent years, unsupervised domain adaptation (UDA) for semanticsegmentation has brought many researchers’attention . The proposed SEAT is simple, easily implemented and easy to integrate into existing adversarial learning based UDA methods . We introduce multi level adaptation by adding thelower-level features to the higher-level ones before feeding them to the discriminator, without adding extra discriminator like others.…

A more direct and better variant of New Q Newton s method Backtracking for m equations in m variables

In this paper we propose a variant of New Q-Newton’s method Backtracking . The update rule of our method is $x\mapsto x-\gamma (x)w(x)$. Good theoretical guarantees are proven, in particular for systems ofpolynomial equations . In “generic situations”, we will also discuss a way to avoid that the limit of the constructed sequence is a solution of $H(x), but not of $F(x)=0$ The limit is a .…

Sub word Level Lip Reading With Visual Attention

The goal of this paper is to learn strong lip reading models that can recognise speech in silent videos . We use sub-word units for lip reading for the first time to better model the ambiguities of the task . Our best lip reading model achieves 22.6% word error rate on the LRS2 dataset, a performanceunprecedented for lip-reading models, significantly reducing the performance gap between lip reading and automatic speech recognition .…

DeepOrder Deep Learning for Test Case Prioritization in Continuous Integration Testing

DeepOrder is a deep learning-based model that works on thebasis of regression machine learning . DeepOrder learns failed test cases based on multiple factors including theduration and execution status of test cases . The results show that DeepOrder outperforms the industry practice and state-of-the-art test prioritization approaches in terms of time-effectiveness and fault detection effectiveness of the DeepOrder approach .…

Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement

Reinforcement learning (RL) is a powerful data-driven control method that has been largely explored in autonomous driving tasks . However, conventional RLapproaches learn control policies through trial-and-error interactions with theenvironment . Offline RL has recently emerged as a promisingframework to learn effective policies from previously-collected, staticdatasets without the requirement of active interactions, making it especially appealing for autonomous driving applications .…

DeepSSM A Blueprint for Image to Shape Deep Learning Models

Statistical shape modeling (SSM) characterizes anatomical variations in apopulation of shapes generated from medical images . SSM requires consistentshape representation across samples in shape cohort . Theseshape representations are then used to extract low-dimensional shapedescriptors that facilitate subsequent analyses in different applications .…

P Adapters Robustly Extracting Factual Information from Language Models with Diverse Prompts

P-Adapters are lightweight models that sit between the embedding layer and first attention layer of Large Language Models . They take LLM embeddings as input and output continuous prompts that are used to query the LLM . They showbetween 12-26% absolute improvement in precision and 36-50% absoluteimprovement in consistency over a baseline of only using natural languagequeries .…

On the Sample Complexity of Decentralized Linear Quadratic Regulator with Partially Nested Information Structure

We study the problem of control policy design for decentralized state-feedback linear quadratic control with a partially nested information structure . We propose a model-based learningsolution, which consists of two steps . We show that thesuboptimality gap between our control policy and the optimal decentralizedcontrol policy scaleslinearly with the estimation error of the system model .…

Sign and Relevance learning

Standard models of biologically realistic, or inspired, reinforcementlearning employ a global error signal which implies shallow networks . Deep networks could offer a drastically superior performance by feeding the error signal backwards through such a network which in turn is not biologically realistic as it requires symmetric weights between top-down and bottom-uppathways .…

A Framework for Risk Assessment and Optimal Line Upgrade Selection to Mitigate Wildfire Risk

As wildfires in the United States are becoming more frequent and severe,mitigating wildfire ignition risk from power line faults is an increasingly crucial effort . Long-term ignition prevention strategies, especially convertingoverhead lines to underground cables, are expensive . Thus, it is important toprioritize upgrades on lines that will reduce ignition risk the most .…

Semi supervised Multi task Learning for Semantics and Depth

Multi-Task Learning (MTL) aims to enhance the model generalization by sharingrepresentations between related tasks for better performance . Typical MTLmethods are jointly trained with the complete multitude of ground-truths forall tasks simultaneously . However, one single dataset may not contain theannotations for each task of interest .…

HAVEN Hierarchical Cooperative Multi Agent Reinforcement Learning with Dual Coordination Mechanism

Multi-agent reinforcement learning often suffers from the exponentially larger action space caused by a large number of agents . We propose a novel value decomposition framework HAVEN based on hierarchicalreinforcement learning for the fully cooperative multi-agent problems . Ourmethod is demonstrated to achieve superior results to many baselines onStarCraft II micromanagement tasks and offers an efficient solution tomulti-agent hierarchical reinforcement learning in fully cooperative scenarios .…

Improving the Robustness to Variations of Objects and Instructions with a Neuro Symbolic Approach for Interactive Instruction Following

An interactive instruction following task has been proposed as a benchmark for learning to map natural language instructions and first-person vision intosequences of actions to interact with objects in a 3D simulated environment . We assume that this problem is due to the high sensitiveness of neural feature extraction to small changes invision and language inputs .…

On the Pitfalls of Analyzing Individual Neurons in Language Models

Many studies have shown that linguistic information is encoded inhidden word representations . Few have studied individual neurons to show how and in which neurons it is encoded . The common approach is to use an external probe to rank neurons according to their relevance to somelinguistic attribute, and to evaluate the obtained ranking using the same probethat produced it .…

Retrieval guided Counterfactual Generation for QA

Deep NLP models have been shown to learn spurious correlations, leaving them brittle to input perturbations . We develop a Retrieve-Generate-Filter-Filter technique to create counterfactualevaluation and training data with minimal human supervision . Using anopen-domain QA framework and question generation model trained on original task data, we create counterfactsuals that are fluent, semantically diverse, andautomatically labeled.…

Floating Isogeometric Analysis

Floating Isogeometric Analysis (FLIGA) extends the conceptsof IGA to Lagrangian extreme deformation analysis . The method is based on anovel tensor-product construction of B-Splines for the update of the basisfunctions in one direction of the parametric space . With basis functions’floating’ deformation-dependently in this direction, mesh distortion is overcome for problems in which extreme deformations occur predominantly along the associated (possibly curved) physical axis .…

Bugs in our Pockets The Risks of Client Side Scanning

Some in industry and government now advocate a new technology to access targeted data: client-side scanning . CSS would enable on-device analysis of data in the clear . CSS by its nature createsserious security and privacy risks for all society while it can provide assistance for law enforcement is at best problematic, authors say .…

MReD A Meta Review Dataset for Controllable Text Generation

Using existing text generation datasets for controllable text summarization, we are facing the problem of not having the domain knowledge and thus the aspects that could be controlled are limited . MReD consists of 7,089 meta-reviews and all its 45k sentences are manually annotated as one of the 9 categories, including abstract, strength, decision, etc.…

Omni Training for Data Efficient Deep Learning

A properlypre-trained model endows an important property: transferability . A highertransferability of the learned representations indicates a bettergeneralizability across domains of different distributions . Transferability has become the key to enable data-efficient deep learning, however, existing pre-training methods focus only on the domaintransferability .…

Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition

Nested entities are observed in many domains due to their compositionality, which cannot be easily recognized by the widely-used sequence labelingframework . A natural solution is to treat the task as a span classificationproblem . To increase performance on span representation and classification, it is crucial to effectively integrate all useful information of differentformats .…

zk Fabric a Polylithic Syntax Zero Knowledge Joint Proof System

zk-Fabric based on partitioned garbled circuits has theadvantage of being versatile and single-use, meaning it can be applied toarbitrary circuits with more comprehensive statements . It can achieve thenon-interactivity among all participants . We also designed a joint zero knowledge proof protocol that uses partitionedgarbled circuits to match thecomprehensive Boolean logical expression with multiple variables, we use the term “polythitic syntax” to refer to the context-based multiple variables in a statement .…

Presenting a Larger Up to date Movie Dataset and Investigating the Effects of Pre released Attributes on Gross Revenue

Movie-making has become one of the most costly and risky endeavors in the entertainment industry . Researchers have been working on finding an optimal strategy to help investors in making the right decisions . We introduce an up-to-date, richer, and larger dataset that we have prepared by scraping IMDb for researchers and data analysts to work with .…

Solving Aspect Category Sentiment Analysis as a Text Generation Task

We consider casting the ACSAtasks into natural language generation tasks, using natural language sentencesto represent the output . Our method allows more direct use of pre-trained knowledge in seq2seq language models by directly following the task setting during pre-training . Experiments on several benchmarks show that our methodgives the best reported results, having large advantages in few-shot and zero-shot settings .…