A survey of deep active learning

P Ren, Y **ao, X Chang, PY Huang, Z Li… - ACM computing …, 2021 - dl.acm.org
Active learning (AL) attempts to maximize a model's performance gain while annotating the
fewest samples possible. Deep learning (DL) is greedy for data and requires a large amount …

Sentiment analysis: A review and comparative analysis of web services

J Serrano-Guerrero, JA Olivas, FP Romero… - Information …, 2015 - Elsevier
Sentiment Analysis (SA), also called Opinion Mining, is currently one of the most studied
research fields. It aims to analyze people's sentiments, opinions, attitudes, emotions, etc …

Breast cancer classification from histopathological images using patch-based deep learning modeling

I Hirra, M Ahmad, A Hussain, MU Ashraf… - IEEE …, 2021 - ieeexplore.ieee.org
Accurate detection and classification of breast cancer is a critical task in medical imaging
due to the complexity of breast tissues. Due to automatic feature extraction ability, deep …

Sentiment analysis: Mining opinions, sentiments, and emotions

J Zhao, K Liu, L Xu - 2016 - direct.mit.edu
With the increasing development of Web 2.0, such as social media and online businesses,
the need for perception of opinions, attitudes, and emotions grows rapidly. Sentiment …

Adversarial active learning for deep networks: a margin based approach

M Ducoffe, F Precioso - arxiv preprint arxiv:1802.09841, 2018 - arxiv.org
We propose a new active learning strategy designed for deep neural networks. The goal is
to minimize the number of data annotation queried from an oracle during training. Previous …

[LIBRO][B] Sentiment analysis and opinion mining

B Liu - 2022 - books.google.com
Sentiment analysis and opinion mining is the field of study that analyzes people's opinions,
sentiments, evaluations, attitudes, and emotions from written language. It is one of the most …

Deep sparse rectifier neural networks

X Glorot, A Bordes, Y Bengio - Proceedings of the fourteenth …, 2011 - proceedings.mlr.press
While logistic sigmoid neurons are more biologically plausible than hyperbolic tangent
neurons, the latter work better for training multi-layer neural networks. This paper shows that …

A new active labeling method for deep learning

D Wang, Y Shang - 2014 International joint conference on …, 2014 - ieeexplore.ieee.org
Deep learning has been shown to achieve outstanding performance in a number of
challenging real-world applications. However, most of the existing works assume a fixed set …

Pattern classification and clustering: A review of partially supervised learning approaches

F Schwenker, E Trentin - Pattern Recognition Letters, 2014 - Elsevier
The paper categorizes and reviews the state-of-the-art approaches to the partially
supervised learning (PSL) task. Special emphasis is put on the fields of pattern recognition …

The Nod-like receptor (NLR) family: a tale of similarities and differences

M Proell, SJ Riedl, JH Fritz, AM Rojas… - PloS one, 2008 - journals.plos.org
Innate immunity represents an important system with a variety of vital processes at the core
of many diseases. In recent years, the central role of the Nod-like receptor (NLR) protein …