Weak Adaptation Learning Addressing Cross domain Data Insufficiency with Weak Annotator

Data quantity and quality are crucial factors for data-driven learningmethods . In some target problem domains, there are not many data samples available, which could significantly hinder the learning process . We propose a weak adaptationlearning (WAL) approach that leverages unlabeled data from a similar sourcedomain, a low-cost weak annotator that produces labels based on task-specificheuristics, labeling rules, or other methods (albeit with inaccuracy), and asmall amount of labeled data in the target domain .…

Prompt Programming for Large Language Models Beyond the Few Shot Paradigm

In this work, we discuss methods of promptprogramming, emphasizing the usefulness of considering prompts through the lensof natural language . We explore techniques for exploiting the capacity of narrative and cultural anchors to encode nuanced intentions . We suggest that the function of few-shot examples in these cases is better described as locating an already learned task rather than meta-learning .…

A Simple Deep Equilibrium Model Converges to Global Optima with Weight Tying

A deep equilibrium linear model is implicitly defined through an equilibriumpoint of an infinite sequence of computation . It avoids any explicitcomputation of the infinite sequence by finding an equilibrium point directly . Despite non-convexity, convergence to globaloptimum at a linear rate is guaranteed without any assumption on the width of the models, allowing the width to be smaller than the output dimension and thenumber of data points .…

OntoZSL Ontology enhanced Zero shot Learning

Zero-shot Learning (ZSL) aims to predict for those classes that havenever appeared in the training data . The key of implementing ZSL is to leverage the prior knowledge of classes which buildsthe semantic relationship between classes and enables the transfer of the learned models (e.g.,…

AI Ethics Needs Good Data

In this chapter we argue that discourses on AI must transcend the language of’ethics’ and engage with power and political economy in order to constitute’Good Data’ In particular, we must move beyond the depoliticised language of ‘ethics’, currently deployed (Wagner 2018) in determining whether AI is ‘good’ given the limitations of ethics as a frame through which AI issues can be viewed .…

Cross modal Adversarial Reprogramming

Recent works onadversarial reprogramming have shown that it is possible to repurpose neuralnetworks for alternate tasks without modifying the network architecture or parameters . In this work, we broaden the scope of adversarialreprogramming beyond the data modality of the original task .…

Efficient solvers for shallow water Saint Venant equations and debris transportation deposition models

This research is aimed at achieving an efficient digital infrastructure forevaluating risks and damages caused by tsunami flooding . Rather than using complex multiphase debris models, werather use an empirical transportation and deposition model that takes into account the interaction with the main water flow, friction/contact with the ground but also debris interaction .…

Multimodal Mobility Systems Joint Optimization of Transit Network Design and Pricing

The performance of multimodal mobility systems relies on the seamlessintegration of conventional mass transit services and the advent ofMobility-on-Demand (MoD) services . A primal-dual approach, inspired by the market literature, yields a compact mixed integer linear programming (MILP)formulation . We provide atractable solution approach through a decomposition scheme and approximational algorithm that accelerates the computation and enables optimization of large-scale problem instances .…

On Ray Shooting for Triangles in 3 Space and Related Problems

We consider several problems that involve lines in three dimensions, and present improved algorithms for solving them . Our approach is based on the polynomial partitioning technique . For example, our ray-shooting algorithm processes a set of $n$ triangles in $R^3$ into a data structure for answering ray shooting queries amid the giventriangles .…

DOBF A Deobfuscation Pre Training Objective for Programming Languages

Recent advances in self-supervised learning have dramatically improved the state of the art on a wide variety of tasks . However, research in languagemodel pre-training has mostly focused on natural languages . In this paper, we introduce a new objective, DOBF, that leverages the structural aspect of programming languages and pre-trains a model to recover the original version of obfuscated source code .…

MAPGN MAsked Pointer Generator network for sequence to sequence pre training

Spoken-text normalization that converts spoken-style text into style normalized text is becoming an important technology for improving subsequent processing such as machine translation andsummarization . MAsked Pointer-Generator Network(MAPGN) is a novel self-supervised learning method . MAPGN is more effective for pointer-generatornetworks than the conventional methods in twospoken text normalization tasks .…

Leveraging Acoustic and Linguistic Embeddings from Pretrained speech and language Models for Intent Classification

An intent classification system is usually implemented as a pipeline process, with aspeech recognition module followed by text processing that classifies theintents . Such systems don’t take advantage of relevant linguistic information, and suffer from limited training data . In this work, we propose a novel intent classification framework that uses acoustic features extracted from a speech recognition system and linguistic features learned from a pretrained language model .…

MATCH Metadata Aware Text Classification in A Large Hierarchy

Multi-label text classification refers to the problem of assigning each givendocument its most relevant labels from the label set . We present the MATCH solution — an end-to-end framework that leverages both metadata andhierarchy information . Extensive experiments on twomassive text datasets with large-scale label hierarchies demonstrate the effectiveness of MATCH over state-of-the-art deep learning baselines .…

Genomic Data Sharing under Dependent Local Differential Privacy

Privacy-preserving genomic data sharing is prominent to increase the pace ofgenomic research, and hence to pave the way towards personalized genomicmedicine . The proposed mechanism considers the correlations in data during data sharing,eliminates statistically unlikely data values beforehand, and adjusts theprobability distributions for each shared data point accordingly .…

Translational Equivariance in Kernelizable Attention

Transformer architectures have show remarkable success, they are boundto the computation of all pairwise interactions of input elements and thussuffer from limited scalability . Recent work has been successful by avoidingthe computation of the complete attention matrix, yet leads to problems downthe line .…

RMS Net Regression and Masking for Soccer Event Spotting

The proposed action spotting task consists in finding the exacttimestamp in which an event occurs . This task fits particularly well for soccervideos, where events correspond to salient actions strictly defined by soccer rules . We enrich our model with two training strategies: the first for data balancing and uniform sampling, the second for maskingambiguous frames and keeping the most discriminative visual cues .…

Spatio temporal Graph RNN for Point Cloud Prediction

In this paper, we propose an end-to-end learning network aim at predicting future PC frames, based on point-based RNN network . As main novelty, an initiallayer learns topological information of point clouds as geometric features and then uses the learned features to form representative spatio-temporalneighborhoods .…

Holographic Cell Stiffness Mapping Using Acoustic Stimulation

Cell stiffness is one of the fundamental mechanical properties of the cell and is greatly affected by the intracellular tensional forces, cytoskeletalprestress, and cytoskeleton structure . Accurate assessment of stiffness distribution is essential due to the critical role of single cell mechanobiology in the regulation of many vital processes such as proliferation, adhesion, migration, and motility .…

OmniDet Surround View Cameras based Multi task Visual Perception Network for Autonomous Driving

Surround View fisheye cameras are commonly deployed in automated driving for360\deg{} near-field sensing around the vehicle . This work presents amulti-task visual perception network . It consists of six primarytasks necessary for an autonomous driving system: depth estimation, visualodometry, semantic segmentation, motion segmentation and object detection, and lens soiling detection .…

Generation for adaption a Gan based approach for 3D Domain Adaption inPoint Cloud

Recent deep networks have achieved good performance on a variety of 3d points classification tasks . However, these models often face challenges in “wildtasks” Unsupervised domain adaptation (UDA) seeks to overcome such a problem without target domain labels . Instead of aligning features betweensource data and target data, we propose a method that use a Generativeadversarial network to generate synthetic data from the source domain so that the output is close to the target domain .…

Maximizing Joint Entropy for Batch Mode Active Learning of Perceptual Metrics

Active metric learning is the problem of incrementally selecting batches of training data (typically, ordered triplets) to annotate, in order toprogressively improve a learned model of a metric over some input domain asrapidly as possible . Standard approaches, which independently select eachtriplet in a batch, are susceptible to highly correlated batches with many redundant triplets and hence low overall utility .…

Capturing Detailed Deformations of Moving Human Bodies

New method to capture detailed human motion, sampling more than1000 unique points on the body . Our method outputs highly accurate 4D(spatio-temporal) point coordinates and, crucially, automatically assigns aunique label to each of the points . The locations and unique labels of thepoints are inferred from individual 2D input images only, without relying on any human body shape or skeletal kinematics models .…