## What is/are Deep Learning?

Deep Learning - We propose a background subtraction framework with deep learning model.^{[1]}Deep learning is a complex machine learning algorithm that can learn the deep inner rules of a sample.

^{[2]}In recent years, Deep Learning methods have become very popular in NLP classification tasks, due to their ability to reach high performances by relying on very simple input representations.

^{[3]}Recently, many image-domain denoising approaches based on deep learning have been proposed and obtained promising results.

^{[4]}This study proposes an innovative theme of emotional stimuli selection based on the food visual cues and expect to construct the optimal emotional feature space as input of deep learning model to achieve better classification accuracy on the real-time emotional recognition system.

^{[5]}Classical and non-classical approaches include logical constructions, deep learning, genetic and ant algorithms, denotative (formalised) semantics and ontologies.

^{[6]}Node embedding algorithms are mainly divided into four categories: matrix factorization-based algorithms, random walk based algorithms, deep learning based algorithms and the algorithm based on the role of node structure.

^{[7]}In this paper, we propose a deep learning architecture that produces accurate dense depth for the outdoor scene from a single color image and a sparse depth.

^{[8]}Although various methods based on the hand-crafted features and deep learning methods have been developed for various applications in the past few years, distinguishing untrained identities in testing phase still remains a challenging task.

^{[9]}Deep learning methods offer a new approach for designing decoders that can be trained and tailored for arbitrary channel statistics.

^{[10]}Convolutional neural networks(CNN) are a subset of deep learning methods recently used widely for image segmentation.

^{[11]}With recent advances in deep learning, considerable attention has been given to achieving automatic speech recognition performance close to human performance on tasks like conversational telephone speech (CTS) recognition.

^{[12]}We propose a set of approaches to solve this problem using a class of deep learning and transfer learning models, and evaluate our approaches empirically using a large-scale real world dataset that displays street scenes containing various materials which are covered with graffiti.

^{[13]}U-Net is a classical unsupervised deep learning algorithm and a representative algorithm of full convolution neural network.

^{[14]}Machine Learning and Deep Learning based methods provide the state-of-the-art results.

^{[15]}However, very few existing algorithms deal with deep learning.

^{[16]}Although deep learning (DL) based image registration methods out perform time consuming conventional approaches, they are heavily dependent on training data and do not generalize well for new images types.

^{[17]}Deep learning techniques, and in particular Convolutional Neural Networks (CNNs), have led to significant progress in image processing.

^{[18]}With this motivation, we address this issue and provide a new survival analysis framework using deep learning and active learning with a novel sampling strategy.

^{[19]}We compare two deep learning architectures to classify poor quality CMR images: 1) 3D spatio-temporal Convolutional Neural Networks (3D-CNN), 2) Long-term Recurrent Convolutional Network (LRCN).

^{[20]}Deep Convolutional Neural Network (DCNN) is considered as a popular and powerful deep learning algorithm in image classification.

^{[21]}Recently, developed algorithms in the face recognition field that are based on deep learning technology have made significant progress.

^{[22]}The application of deep learning algorithms has the potential to reduce unnecessary referrals and costs in scoliosis screening.

^{[23]}Both street view data and deep learning are valuable tools for automated environmental exposure assessments for health-related studies.

^{[24]}Using deep learning models on small scale datasets would result in overfitting.

^{[25]}In this paper, simple methodologies of deep learning application to conventional multiple-input multiple-output (MIMO) communication systems are presented.

^{[26]}Recently, Machine learning and deep learning has been employed for ncRNAs identification and classification and has shown promising results.

^{[27]}This study estimates GWLs with deep learning and artificial neural networks (ANNs), namely a multilayer perceptron (MLP), long short term memory (LSTM), and a convolutional neural network (CNN) with four different input variable combinations for two watersheds (Baltic River and Long Creek) in Prince Edward Island, Canada.

^{[28]}We use deep learning to detect individual stems and employ filters, morphological operations, and Random Sample Consensus to model the boundary of each stem and estimate the pixel width and metric width of each stem.

^{[29]}To solve the difficult problem of spatial perception for ultra-low altitude obstacle avoidance, a motion parallax estimation algorithm is proposed by combing the deep learning and the epipolar geometry in this paper.

^{[30]}In recent years, deep learning models have been widely used in the field of hyperspectral imaging.

^{[31]}In order to improve imaging quality of real-time FSPI, a fast image reconstruction framework based on deep learning (DL) is proposed.

^{[32]}Recognizing this challenging task, an efficient deep learning based prediction model is proposed for wind power forecasting.

^{[33]}In this paper, a deep learning-based method for segmenting lung fields from chest radiographs has been proposed.

^{[34]}One of the sub-categories of the discriminative model is deep learning.

^{[35]}The first paper introduces a deep learning model for estimating short-term life expectancy (>3 months) of metastatic cancer patients by analyzing free-text clinical notes in electronic medical records, while maintaining the temporal visit sequence.

^{[36]}Aiming at the problem of heavy workload of manual supervision and low precision of traditional smoke alarm, this paper proposes an improved algorithm based on YOLOv3-tiny deep learning network for indoor smoking behavior detection.

^{[37]}The aim of this study is to introduce a method of wavelet transform in combination with deep learning network for the classification of VEBs.

^{[38]}Recently, deep learning (DL) is of great interest in hyperspectral image (HSI) classification.

^{[39]}recognizing human activity and engagement) are performed by an Autoencoder, which is a Deep Learning and Unsupervised Learning method.

^{[40]}In medical HCC, deep learning has demonstrated its powerful ability in the field of computer vision.

^{[41]}, pose/orientation estimation) in the context of deep learning.

^{[42]}The success of deep learning techniques, especially Convolutional Neural Networks (CNN) in solving the problem of computer vision applications has inspired researchers to overcome the problem of the semantic gap.

^{[43]}Apart from presenting an alternative teaching and learning model, the metaphor-based approach fosters deep learning.

^{[44]}Despite remarkable progress in the field of deep learning assisted human pose estimation, the performance of such systems decreases while noise and errors increase with the complexity of the scene.

^{[45]}This paper proposes a comprehensive approach toward large-scale and faster prediction of metro system characteristics by employing the integration of four leading-edge technologies: big data, deep learning, in-memory computing, and Graphics Processing Units (GPUs).

^{[46]}Background Deep learning algorithms have achieved human-equivalent performance in image recognition.

^{[47]}We aim to test whether deep learning techniques can be used to reproduce visual classification of observations, physical classification of simulations and highlight any differences between these two classifications.

^{[48]}This framework consists of a short human-computer interactive evaluation that utilizes artificial intelligence, namely deep learning, and can predict whether the participant is depressed or not with satisfactory performance.

^{[49]}In this work, we propose a deep learning–based method to address this issue, variational deep embedding with recurrence (VaDER).

^{[50]}