Výsledky vyhledávání - "KARIMI, MOSTAFA"

Report

Deploying self-supervised learning in the wild for hybrid automatic speech recognition

Autor: Karimi, Mostafa, Liu, Changliang, Kumatani, Kenichi, Qian, Yao, Wu, Tianyu, Wu, Jian

Self-supervised learning (SSL) methods have proven to be very successful in automatic speech recognition (ASR). These great improvements have been reported mostly based on highly curated datasets such as LibriSpeech for non-streaming End-to-End ASR m

Externí odkaz: http://arxiv.org/abs/2205.08598

Zobrazit plný text záznamu

Akademický článek

An analytical solution for hollow cylinders under temporary torsional strain that includes several fractures and an orthotropic coating

Autor: Zhang, Lei, Talebipour, Mostafa, Jasim, Dheyaa J., Karimi, Mostafa, Salahshour, Soheil

Publikováno v: In Thin-Walled Structures October 2024 203

Zobrazit plný text záznamu

Report

Network-principled deep generative models for designing drug combinations as graph sets

Autor: Karimi, Mostafa, Hasanzadeh, Arman, shen, Yang

Combination therapy has shown to improve therapeutic efficacy while reducing side effects. Importantly, it has become an indispensable strategy to overcome resistance in antibiotics, anti-microbials, and anti-cancer drugs. Facing enormous chemical sp

Externí odkaz: http://arxiv.org/abs/2004.07782

Zobrazit plný text záznamu

Report

Directionally Dependent Multi-View Clustering Using Copula Model

Autor: Afrin, Kahkashan, Iquebal, Ashif S., Karimi, Mostafa, Souris, Allyson, Lee, Se Yoon, Mallick, Bani K.

In recent biomedical scientific problems, it is a fundamental issue to integratively cluster a set of objects from multiple sources of datasets. Such problems are mostly encountered in genomics, where data is collected from various sources, and typic

Externí odkaz: http://arxiv.org/abs/2003.07494

Zobrazit plný text záznamu

Report

Explainable Deep Relational Networks for Predicting Compound-Protein Affinities and Contacts

Autor: Karimi, Mostafa, Wu, Di, Wang, Zhangyang, Shen, Yang

Predicting compound-protein affinity is critical for accelerating drug discovery. Recent progress made by machine learning focuses on accuracy but leaves much to be desired for interpretability. Through molecular contacts underlying affinities, our l

Externí odkaz: http://arxiv.org/abs/1912.12553

Zobrazit plný text záznamu

Report

Illegible Text to Readable Text: An Image-to-Image Transformation using Conditional Sliced Wasserstein Adversarial Networks

Autor: Karimi, Mostafa, Veni, Gopalkrishna, Yu, Yen-Yun

Automatic text recognition from ancient handwritten record images is an important problem in the genealogy domain. However, critical challenges such as varying noise conditions, vanishing texts, and variations in handwriting make the recognition task

Externí odkaz: http://arxiv.org/abs/1910.05425

Zobrazit plný text záznamu

Report

DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks

Autor: Karimi, Mostafa, Wu, Di, Wang, Zhangyang, Shen, Yang

Publikováno v: Bioinformatics 35, no. 18 (2019): 3329-3338

Motivation: Drug discovery demands rapid quantification of compound-protein interaction (CPI). However, there is a lack of methods that can predict compound-protein affinity from sequences alone with high applicability, accuracy, and interpretability

Externí odkaz: http://arxiv.org/abs/1806.07537

Zobrazit plný text záznamu