Deep Machine Learning - A New Frontier in Artificial Intelligence Research [Research Frontier]

By Itamar Arel, Derek C. Rose, T. Karnowski. 2010

1,183 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Forecasting Crude Oil Prices: a Deep Learning based Model (2017, background): “It can deal with the issues which are associated with applying back-propagation to deeply layered neural networks traditionally, such as long learning time, necessity of a substantial labeled dataset for training, and inadequate parameter selection techniques that lead to poor local optima[16].”
Easy over hard: a case study on deep learning (2017, background): “Fisher et al. [20] characterizes software analytics as a work flow that distills large quantities of low-value data down to smaller sets of higher value data.”
Blind Image Quality Assessment via Deep Learning (2015, background): “Deep learning models have thrived over the years [30], not only in the field of computer vision, but also in many others, such as audio [31], natural language processing [32], and so on [21], [33]–[35].”
Deep Convolutional Neural Networks and Learning ECG Features for Screening Paroxysmal Atrial Fibrillation Patients (2018, background): “It hardly needs any data preprocessing and pretraining algorithms [34].”
Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives (2012, result): “This paper is meant to be a follow-up and a complement to an earlier survey (Bengio, 2009) (but see also Arel et al. (2010)).”
Structural damage identification based on autoencoder neural networks and deep learning (2018, background): “The original applications mainly focused on face detection, objective recognition, speech recognition and detection, and natural language processing [18,19].”
Deep learning for visual understanding: A review (2016, methodology): “The greedy learning procedure has two main advantages [58]: (1) it generates a proper initialization of the network, addressing the dif-ﬁ culty in parameter selection which may result in poor local optima to some extent; (2) the learning procedure is unsupervised and requires no class labels, so it…”