Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Haque, Mirazul"'
Autor:
Haque, Mirazul, Yang, Wei
Deep Neural Networks (DNNs) have been used to solve different day-to-day problems. Recently, DNNs have been deployed in real-time systems, and lowering the energy consumption and response time has become the need of the hour. To address this scenario
Externí odkaz:
http://arxiv.org/abs/2308.08709
Autor:
Zheng, Jiangrui, Liu, Xueqing, Yang, Guanqun, Haque, Mirazul, Qian, Xing, Rathnasuriya, Ravishka, Yang, Wei, Budhrani, Girish
To protect users from massive hateful content, existing works studied automated hate speech detection. Despite the existing efforts, one question remains: do automated hate speech detectors conform to social media content policies? A platform's conte
Externí odkaz:
http://arxiv.org/abs/2307.12418
Deep Learning (DL) models have been popular nowadays to execute different speech-related tasks, including automatic speech recognition (ASR). As ASR is being used in different real-time scenarios, it is important that the ASR model remains efficient
Externí odkaz:
http://arxiv.org/abs/2306.00794
The recently proposed capability-based NLP testing allows model developers to test the functional capabilities of NLP models, revealing functional failures that cannot be detected by the traditional heldout mechanism. However, existing work on capabi
Externí odkaz:
http://arxiv.org/abs/2210.08097
Today, an increasing number of Adaptive Deep Neural Networks (AdNNs) are being used on resource-constrained embedded devices. We observe that, similar to traditional software, redundant computation exists in AdNNs, resulting in considerable performan
Externí odkaz:
http://arxiv.org/abs/2210.05370
Because of the increasing accuracy of Deep Neural Networks (DNNs) on different tasks, a lot of real times systems are utilizing DNNs. These DNNs are vulnerable to adversarial perturbations and corruptions. Specifically, natural corruptions like fog,
Externí odkaz:
http://arxiv.org/abs/2204.08623
Neural image caption generation (NICG) models have received massive attention from the research community due to their excellent performance in visual understanding. Existing work focuses on improving NICG model accuracy while efficiency is less expl
Externí odkaz:
http://arxiv.org/abs/2203.15859
Recently, various Deep Neural Network (DNN) models have been proposed for environments like embedded systems with stringent energy constraints. The fundamental problem of determining the robustness of a DNN with respect to its energy consumption (ene
Externí odkaz:
http://arxiv.org/abs/2202.06084
Publikováno v:
Proceedings of the 44th International Conference on Software Engineering.
Recently, various Deep Neural Network (DNN) models have been proposed for environments like embedded systems with stringent energy constraints. The fundamental problem of determining the robustness of a DNN with respect to its energy consumption (ene
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8f0d068a2495f299d713399e7cfa43fd
https://doi.org/10.1145/3510003.3510088
https://doi.org/10.1145/3510003.3510088
Neural Machine Translation (NMT) systems have received much recent attention due to their human-level accuracy. While existing works mostly focus on either improving accuracy or testing accuracy robustness, the computation efficiency of NMT systems,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bf3ac79bcf9db77582140e807de7c062