Results 21 to 30 of about 1,118 (118)

CoNLL 2017 Shared Task : Multilingual Parsing from Raw Text to Universal Dependencies [PDF]

open access: yes, 2017
The Conference on Computational Natural Language Learning (CoNLL) features a shared task, in which participants train and test their learning systems on the same data sets.
Attia, Mohammed   +61 more
core   +3 more sources

A software approach to defeating side channels in last-level caches

open access: yes, 2016
We present a software approach to mitigate access-driven side-channel attacks that leverage last-level caches (LLCs) shared across cores to leak information between security domains (e.g., tenants in a cloud).
Arcangeli A.   +6 more
core   +1 more source

Six artificial intelligence innovation strategies applied to autism spectrum disorder research: A narrative review

open access: yesPediatric Investigation, Volume 10, Issue 2, Page 182-198, April 2026.
Six artificial intelligence strategies advance autism research from tool optimization to paradigm shift: causal modeling, spatiotemporal networks, multimodal integration, digital twins, social cognition mapping, collaborative learning, and context‐aware interventions for precision care.
Ting Zhang   +3 more
wiley   +1 more source

Revisiting Unreasonable Effectiveness of Data in Deep Learning Era

open access: yes, 2017
The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data.
Gupta, Abhinav   +3 more
core   +1 more source

An efficient confidentiality-preserving Proof of Ownership for deduplication [PDF]

open access: yes, 2015
Data storage in the cloud is becoming widespread. Deduplication is a key mechanism to decrease the operating costs cloud providers face, due to the reduction of replicated data storage.
González Manzano, Lorena   +1 more
core   +1 more source

HoloDetect: Few-Shot Learning for Error Detection

open access: yes, 2019
We introduce a few-shot learning framework for error detection. We show that data augmentation (a form of weak supervision) is key to training high-quality, ML-based error detection models that require minimal human involvement. Our framework consists of
Bengio Yoshua   +9 more
core   +1 more source

Facial expression recognition for emotion perception: A comprehensive science mapping

open access: yesIbrain, Volume 12, Issue 1, Page 38-51, Spring 2026.
Facial expression recognition (FER) has emerged as a pivotal interdisciplinary research domain, bridging computer science, psychology, neuroscience, and medicine. By mapping the FER scientific knowledge graph, the study aimed to explore the technological evolution and forecast future application trends in this field.
Hou‐Ming Kan   +10 more
wiley   +1 more source

RETSim: Resilient and Efficient Text Similarity

open access: yes, 2023
This paper introduces RETSim (Resilient and Efficient Text Similarity), a lightweight, multilingual deep learning model trained to produce robust metric embeddings for near-duplicate text retrieval, clustering, and dataset deduplication tasks.
Bumin, Aysegul   +4 more
core  

Interpretable Machine Learning: A Comprehensive Review of Foundations, Methods, and the Path Forward

open access: yesWIREs Data Mining and Knowledge Discovery, Volume 16, Issue 1, March 2026.
This systematic review of 352 studies establishes a comprehensive taxonomy for Interpretable Machine Learning, transitioning from foundational intrinsic models to advanced deep learning explanations. It reveals a critical paradigm shift toward “mechanistic interpretability” and actionable recourse, emphasizing that future AI systems must be rigorously ...
Shimon Fridkin, Michael Bendersky
wiley   +1 more source

Securing the Unseen: A Comprehensive Exploration Review of AI‐Powered Models for Zero‐Day Attack Detection

open access: yesExpert Systems, Volume 43, Issue 3, March 2026.
ABSTRACT Zero‐day exploits remain challenging to detect because they often appear in unknown distributions of signatures and rules. The article entails a systematic review and cross‐sectional synthesis of four fundamental model families for identifying zero‐day intrusions, namely, convolutional neural networks (CNN), deep neural networks (DNN ...
Abdullah Al Siam   +3 more
wiley   +1 more source

Home - About - Disclaimer - Privacy