Výsledky vyhledávání - "Tayyaba Azim"

Akademický článek

Risk Factors Leading to Meconium Aspiration Syndrome in Meconium-Stained Amniotic Fluid

Autor: Rukhsana Karim, Robina Akhtar, Nasreen Kishwar, Sadia Ali, Fatima Imran, Shamshad Begum, Tayyaba Azim

Publikováno v: Journal of Gandhara Medical and Dental Sciences, Vol 10, Iss 1 (2023)

OBJECTIVES This study aimed to find out the risk factors leading to meconium aspiration syndrome in patients having meconium-stained amniotic fluid. METHODOLOGY This comparative study was conducted in the department of Obstetrics and Gynaecolog

Externí odkaz: https://doaj.org/article/4c97e19172664a7b938692270a653646

Zobrazit plný text záznamu

Akademický článek

Diversified Fisher kernel: encoding discrimination in Fisher features to compete deep neural models for visual classification task

Autor: Sarah Ahmed, Tayyaba Azim

Publikováno v: IET Computer Vision, Vol 14, Iss 8, Pp 658-664 (2020)

Fisher kernels derived from stochastic probabilistic models such as restricted and deep Boltzmann machines have shown competitive visual classification results in comparison to widely popular deep discriminative models. This genre of Fisher kernels b

Externí odkaz: https://doaj.org/article/ad8f08910cc24cb5bfd2655e2d2c06ae

Zobrazit plný text záznamu

Akademický článek

Knowledge Based Recommender System for Academia Using Machine Learning: A Case Study on Higher Education Landscape of Pakistan

Autor: Huma Samin, Tayyaba Azim

Publikováno v: IEEE Access, Vol 7, Pp 67081-67093 (2019)

Allocation of courses and research students based on faculty's subject specialization and area of interest has always remained a challenging task for university administration due to the presence of academics' cross-domain interests, stale faculty re

Externí odkaz: https://doaj.org/article/971aa811679d407f96758204095915e9

Zobrazit plný text záznamu

Akademický článek

SCANCPECLENS: A Framework for Automatic Lexicon Generation and Sentiment Analysis of Micro Blogging Data on China Pakistan Economic Corridor

Autor: Bibi Amina, Tayyaba Azim

Publikováno v: IEEE Access, Vol 7, Pp 133876-133887 (2019)

With the growing availability of internet and opinion rich resources such as social networks and personal blogs, the task of mining public opinion and exploring facts has become more popular than ever before during the last decade. The latest trend h

Externí odkaz: https://doaj.org/article/5a0577b03264496c98f3dd1c58a4c13e

Zobrazit plný text záznamu

Akademický článek

Introspective analysis of convolutional neural networks for improving discrimination performance and feature visualisation

Autor: Shakeel Shafiq, Tayyaba Azim

Publikováno v: PeerJ Computer Science, Vol 7, p e497 (2021)

Deep neural networks have been widely explored and utilised as a useful tool for feature extraction in computer vision and machine learning. It is often observed that the last fully connected (FC) layers of convolutional neural network possess higher

Externí odkaz: https://doaj.org/article/8da53e04e9a74ce18494bc4bf4e6df3a

Zobrazit plný text záznamu

Detecting moments of change and suicidal risks in longitudinal user texts using multi-task learning

Autor: Tayyaba Azim, Loitongbam Singh, Stuart Middleton

This work describes the classification system proposed for the Computational Linguistics and Clinical Psychology (CLPsych) Shared Task 2022. We propose the use of multitask learning approach with a bidirectional long-short term memory (Bi-LSTM) model

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::14f6c61069c939e049fd5596cabfbf42
https://aclanthology.org/2022.clpsych-1.19/

Zobrazit plný text záznamu

Introspective analysis of convolutional neural networks for improving discrimination performance and feature visualisation

Autor: Tayyaba Azim, Shakeel Shafiq

Publikováno v: PeerJ Computer Science
PeerJ Computer Science, Vol 7, p e497 (2021)

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a0a5ec185a8fb89df7cb67b474e6ae65
https://pubmed.ncbi.nlm.nih.gov/34013030

Zobrazit plný text záznamu

Kernel Based Learning: A Pragmatic Approach in the Face of New Challenges

Autor: Sarah Ahmed, Tayyaba Azim

Publikováno v: Composing Fisher Kernels from Deep Neural Models ISBN: 9783319985237

This chapter is not aimed at replacing literature on introduction to kernel methods or Fisher kernels. There are some excellent text books and tutorials on the topic by Scholkopf and Smola (Learning with kernels: support vector machines, regularizati

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::fa9fbaf6fec05cbd260bcb6ee614f9b1
https://doi.org/10.1007/978-3-319-98524-4_1

Zobrazit plný text záznamu

Composing Fisher Kernels from Deep Neural Models

Autor: Tayyaba Azim, Sarah Ahmed

Publikováno v: SpringerBriefs in Computer Science ISBN: 9783319985237

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::bb1ca1ef2e3af97fce467797fa8547d7
https://doi.org/10.1007/978-3-319-98524-4

Zobrazit plný text záznamu

Open Source Knowledge Base for Machine Learning Practitioners

Autor: Sarah Ahmed, Tayyaba Azim

Publikováno v: Composing Fisher Kernels from Deep Neural Models ISBN: 9783319985237

In this chapter, we provide references to some of the most useful resources that could provide practitioners a quick start for learning and implementing a variety of deep learning models, kernel functions, Fisher vector encodings and feature condensa

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b5efd1c7d0b7ea2359027a2c9faa8ce8
https://doi.org/10.1007/978-3-319-98524-4_5

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání