Book ChapterDOI
Recent Trends in Deep Learning with Applications
K. Balaji,K. Lavanya +1 more
- pp 201-222
TLDR
The main purpose of using deep learning algorithms are such as faster processing, low-cost hardware, and modern growths in machine learning techniques.Abstract:
Deep learning methods play a vital role in Internet of things analytics. One of the main subgroups of machine learning algorithm is Deep Learning. Raw data is collected from devices. Collecting data from all situations and doing pre-processing is complex. Monitoring data through sensors continuously is also complex and expensive. Deep learning algorithms will solve these types of issues. A deep learning method signifies at various levels of representation from lower level features to very higher level features of data. The higher level features provide more abstract thoughts of information than the lower level which contains raw data. It is a developing methodology and has been commonly applied in art, image caption, machine translation, natural language processing, object detection, robotics, and visual tracking. The main purpose of using deep learning algorithms are such as faster processing, low-cost hardware, and modern growths in machine learning techniques. This review paper gives an understanding of deep learning methods and their recent advances in Internet of things.read more
Citations
More filters
Journal ArticleDOI
Machine Learning for Smart Environments in B5G Networks: Connectivity and QoS.
Saeed H. Alsamhi,Saeed H. Alsamhi,Faris A. Almalki,Hatem Al-Dois,Soufiene Ben Othman,Soufiene Ben Othman,Jahan Hassan,Ammar Hawbani,Radyah Sahal,Brian Lee,Hager Saleh +10 more
TL;DR: In this paper, a survey on the use of ML for enhancing IoT applications is presented, and an in-depth overview of the various IoT applications that can be enhanced using ML, such as smart cities, smart homes, and smart healthcare.
Book ChapterDOI
Medical Image Analysis With Deep Neural Networks
K. Balaji,K. Lavanya +1 more
TL;DR: The essentials of deep learning methods with convolutional neural networks are presented and their achievements in medical image analysis, such as in deep feature representation, detection, segmentation, classification, and prediction are analyzed.
Posted Content
Human or Machine: Automating Human Likeliness Evaluation of NLG Texts
Erion Çano,Ondrej Bojar +1 more
TL;DR: An attempt to automate the human likeliness evaluation of the output text samples coming from natural language generation methods used to solve several tasks by using a discrimination procedure based on large pretrained language models and their probability distributions.
Classification of Lung Nodule Using Hybridized Deep Feature Technique
TL;DR: A hybridized approach has been followed to classify lung nodule as benign or malignant to help in early detection of lung cancer and help in the life expectancy of lungcancer patients thereby reducing the mortality rate by this deadly disease scourging the world.
References
More filters
Posted Content
Zero-bias autoencoders and the benefits of co-adapting features
TL;DR: This work shows that negative biases are a natural result of using a hidden layer whose responsibility is to both represent the input data and act as a selection mechanism that ensures sparsity of the representation and proposes a new activation function that decouples the two roles of the hidden layer.
Proceedings ArticleDOI
A novel sparse auto-encoder for deep unsupervised learning
TL;DR: A novel sparse variant of auto-encoders as a building block to pre-train deep neural networks through KL-divergence, which requires fewer hyper-parameters and the sparsity level of the hidden units can be learnt automatically.
Posted Content
Saturating Auto-Encoders
Rostislav Goroshin,Yann LeCun +1 more
TL;DR: A simple new regularizer for auto-encoders whose hidden-unit activation functions contain at least one zero-gradient (saturated) region is introduced, and a wide variety of features can be learned when different activation functions are used.
Journal ArticleDOI
EPuL: An Enhanced Positive-Unlabeled Learning Algorithm for the Prediction of Pupylation Sites.
Xuanguo Nan,Lingling Bao,Xiaosa Zhao,Xiaowei Zhao,Arun Kumar Sangaiah,Gai-Ge Wang,Zhiqiang Ma +6 more
TL;DR: This work proposed an enhanced positive-unlabeled learning algorithm (EPuL) to the pupylation site prediction problem, which uses only positive and unlabeled samples and separates the training dataset into the positive dataset and the unlabeling dataset which contains the remaining non-annotated lysine residues.