"Deep learning is an area of machine learning that emerged from the intersection of neural networks, artificial intelligence, graphical modeling, optimization, pattern recognition and signal processing." (N D Lewis, "Deep Learning Made Easy with R: A Gentle Introduction for Data Science", 2016)
"Methods that are used to train models with several levels of abstraction from the raw input to the output. For example, in visual recognition, the lowest level is an image composed of pixels. In layers as we go up, a deep learner combines them to form strokes and edges of different orientations, which can then be combined to detect longer lines, arcs, corners, and junctions, which in turn can be combined to form rectangles, circles, and so on. The units of each layer may be thought of as a set of primitives at a different level of abstraction." (Ethem Alpaydın, "Machine learning : the new AI", 2016)
"A branch of machine learning to whose architectures belong deep ANNs. The term “deep” denotes the application of multiple layers with a complex structure." (Iva Mihaylova, "Applications of Artificial Neural Networks in Economics and Finance", 2018)
"A deep-learning model is a neural network that has multiple (more than two) layers of hidden units (or neurons). Deep networks are deep in terms of the number of layers of neurons in the network. Today many deep networks have tens to hundreds of layers. The power of deep-learning models comes from the ability of the neurons in the later layers to learn useful attributes derived from attributes that were themselves learned by the neurons in the earlier layers." (John D Kelleher & Brendan Tierney, "Data science", 2018)
"Also known as deep structured learning or hierarchical learning is part of a broader family of machine learning methods based on learning data representations, as opposed to task-specific algorithms." (Soraya Sedkaoui, "Big Data Analytics for Entrepreneurial Success", 2018)
"Deep learning broadly describes the large family of neural network architectures that contain multiple, interacting hidden layers." (Benjamin Bengfort et al, "Applied Text Analysis with Python: Enabling Language-Aware Data Products with Machine Learning", 2018)
"It is a part of machine learning approach used for learning data representations." (Dharmendra S Rajput et al, "Investigation on Deep Learning Approach for Big Data: Applications and Challenges", 2018)
"The ability of a neural network to improve its learning process." (David Natingga, "Data Science Algorithms in a Week" 2nd Ed., 2018)
"A learning algorithm using a number of layers for extracting and learning feature hierarchies before providing an output for any input." (Tanu Wadhera & Deepti Kakkar, "Eye Tracker: An Assistive Tool in Diagnosis of Autism Spectrum Disorder", 2019)
"a machine-learning technique that extends standard artificial neural network models to many layers representing different levels of abstraction, say going from individual pixels of an image through to recognition of objects." (David Spiegelhalter, "The Art of Statistics: Learning from Data", 2019)
"A part of a broader family of machine learning methods based on learning data representations." (Nil Goksel & Aras Bozkurt, "Artificial Intelligence in Education: Current Insights and Future Perspectives", 2019)
"A recent method of machine learning based on neural networks with more than one hidden layer." (Samih M Jammoul et al, "Open Source Software Usage in Education and Research: Network Traffic Analysis as an Example", 2019)
"A subbranch of machine learning which inspires from the artificial neural network. It has eliminated the need to design handcrafted features as in deep learning features are automatically learned by the model from the data." (Aman Kamboj et al, "Ear Localizer: A Deep-Learning-Based Ear Localization Model for Side Face Images in the Wild", 2019)
"It is class of one machine learning algorithms that can be supervised, unsupervised, or semi-supervised. It uses multiple layers of processing units for feature extraction and transformation." (Siddhartha Kumar Arjaria & Abhishek S Rathore, "Heart Disease Diagnosis: A Machine Learning Approach", 2019)
"Is the complex, unsupervised processing of unstructured data in order to create patterns used in decision making, patterns that are analogous to those of the human brain." (Samia H Rizk, "Risk-Benefit Evaluation in Clinical Research Practice", 2019)
"The ability for machines to autonomously mimic human thought patterns through artificial neural networks composed of cascading layers of information." (Kirti R Bhatele et al, "The Role of Artificial Intelligence in Cyber Security", 2019)
"The method for solving problems that have more probabilistic calculations based on artificial neural networks." (Tolga Ensari et al, "Overview of Machine Learning Approaches for Wireless Communication", 2019)
"A category of machine learning methods which is inspired by the artificial neural networks" (Shouvik Chakraborty & Kalyani Mali, "An Overview of Biomedical Image Analysis From the Deep Learning Perspective", 2020)
"A sub-field of machine learning which is based on the algorithms and layers of artificial networks." (S Kayalvizhi & D Thenmozhi, "Deep Learning Approach for Extracting Catch Phrases from Legal Documents", 2020)
"A type of machine learning based on artificial neural networks. It can be supervised, unsupervised, or semi-supervised, and it uses an artificial neural network with multiple layers between the input and output layers." (Timofei Bogomolov et al, "Identifying Patterns in Fresh Produce Purchases: The Application of Machine Learning Techniques", 2020)
"An extension of machine learning approach, which uses neural network." (Neha Garg & Kamlesh Sharma, "Machine Learning in Text Analysis", 2020)
"Deep learning (also known as deep structured learning or hierarchical learning) is part of a broader family of machine learning methods based on learning data representations, as opposed to task-specific algorithms. Learning can be supervised, semi-supervised or unsupervised." (R Murugan, "Implementation of Deep Learning Neural Network for Retinal Images", 2020)
"Deep learning is a collection of algorithms used in machine learning, used to model high-level abstractions in data through the use of model architectures, which are composed of multiple nonlinear transformations. It is part of a broad family of methods used for machine learning that are based on learning representations of data." (Edward T Chen, "Deep Learning and Sustainable Telemedicine", 2020)
"Deep learning is a collection of neural-network techniques that generally use multiple layers." (Alex Thomas, "Natural Language Processing with Spark NLP", 2020)
"Deep learning is a kind of machine learning technique with automatic image interpretation and feature learning facility. The different deep learning algorithms are convolutional neural network (CNN), deep neural network (DNN), recurrent neural network (RNN), genetic adversarial networks (GAN), etc." (Rajandeep Kaur & Rajneesh Rani, "Comparative Study on ASD Identification Using Machine and Deep Learning", 2020)
"Deep learning is a subset of machine learning that models high-level abstractions in data by means of network architectures, which are composed of multiple nonlinear transformations." (Loris Nanni et al, "Digital Recognition of Breast Cancer Using TakhisisNet: An Innovative Multi-Head Convolutional Neural Network for Classifying Breast Ultrasonic Images", 2020)
"In contradistinction to surface or superficial learning, deep learning is inextricably associated with long-term retention of pertinent and solid knowledge, based on a thorough and critical understanding of the object of study, be it curricular content or not." (Leonor M Martínez-Serrano, "The Pedagogical Potential of Design Thinking for CLIL Teaching: Creativity, Critical Thinking, and Deep Learning", 2020)
"Is a group of methods that allow multilayer computing models to work with data that has an abstraction hierarchy." (Heorhii Kuchuk et al, "Application of Deep Learning in the Processing of the Aerospace System's Multispectral Images", 2020)
"It is a part of machine learning intended for learning form large amounts of data, as in the case of experience-based learning. It can be considered that feature engineering in deep learning-based models is partly left to the machine. In the case of artificial neural networks, deep neural networks are expected to have various layers within architectures for solving complex problems with higher accuracy compared to traditional machine learning. Moreover, high performance automatic results are expected without human intervention." (Ana Gavrovska & Andreja Samčović, "Intelligent Automation Using Machine and Deep Learning in Cybersecurity of Industrial IoT", 2020)
"Is a subset of AI and machine learning that uses multi-layered artificial neural networks to learn from data that is unstructured or unlabeled." (Lejla Banjanović-Mehmedović & Fahrudin Mehmedović, "Intelligent Manufacturing Systems Driven by Artificial Intelligence in Industry 4.0", 2020)
"This method is also called as hierarchical learning or deep structured learning. It is one of the machine learning method that is based on learning methods like supervised, semi-supervised or unsupervised. The only difference between deep learning and other machine learning algorithm is that deep learning method uses big data as input." (Anumeera Balamurali & Balamurali Ananthanarayanan,"Develop a Neural Model to Score Bigram of Words Using Bag-of-Words Model for Sentiment Analysis", 2020)
"A form of machine learning which uses multi-layered architectures to automatically learn complex representations of the input data. Deep models deliver state-of-the-art results across many fields, e.g. computer vision and NLP." (Vincent Karas & Björn W Schuller, "Deep Learning for Sentiment Analysis: An Overview and Perspectives", 2021)
"A sub branch of Artificial intelligence in which we built the DL model and we don’t need to specify any feature to the learning model . In case of DL the model will classify the data based on the input data." (Ajay Sharma, "Smart Agriculture Services Using Deep Learning, Big Data, and IoT", 2021)
"A sub-set of machine learning in artificial intelligence (AI) with network capabilities supporting learning unsupervised from unstructured data." (Mark Schofield, "Gamification Tools to Facilitate Student Learning Engagement in Higher Education: A Burden or Blessing?", 2021)
"A subarea of machine learning, which adopts a deeper and more complex neural structure to reach state-of-the-art accuracy in a given problem. Commonly applied in machine learning areas, such as classification and prediction." (Jinnie Shin et al, "Automated Essay Scoring Using Deep Learning Algorithms", 2021)
"A subset of a broader family of machine learning methods that makes use of multiple layers to extract data from raw input in order to learn its features." (R Karthik et al, "Performance Analysis of GAN Architecture for Effective Facial Expression Synthesis", 2021)
"An artificial intelligence function that imitates the workings of the human brain in processing data and creating patterns for use in decision making." (Wissam Abbass et al, "Internet of Things Application for Intelligent Cities: Security Risk Assessment Challenges", 2021)
"Another term for unsupervised learning that includes reinforcement learning in which the machine responds to reaching goals given input data and constraints. Deep learning deals with multiple layers simulating neural networks with ability to process immense amount of data." (Sujata Ramnarayan, "Marketing and Artificial Intelligence: Personalization at Scale", 2021)
"Application of multi neuron, multi-layer neural networks to perform learning tasks." (Revathi Rajendran et al, "Convergence of AI, ML, and DL for Enabling Smart Intelligence: Artificial Intelligence, Machine Learning, Deep Learning, Internet of Things", 2021)
"Deep learning approach is a subfield of the machine learning technique. The concepts of deep learning influenced by neuron and brain structure based on ANN (Artificial Neural Network)." (Sayani Ghosal & Amita Jain, "Research Journey of Hate Content Detection From Cyberspace", 2021)
"Deep learning is a compilation of algorithms used in machine learning, and used to model high-level abstractions in data through the use of model architectures." (M Srikanth Yadav & R Kalpana, "A Survey on Network Intrusion Detection Using Deep Generative Networks for Cyber-Physical Systems", 2021)
"Deep learning is a subfield of machine learning that uses artificial neural networks to predict, classify, and generate data." (Usama A Khan & Josephine M Namayanja, "Reevaluating Factor Models: Feature Extraction of the Factor Zoo", 2021)
"Deep leaning is a subset of machine learning to solve complex problems/datasets." (R Suganya et al, "A Literature Review on Thyroid Hormonal Problems in Women Using Data Science and Analytics: Healthcare Applications", 2021)
"Deep learning is a type of machine learning that can process a wider range of data resources, requires less data preprocessing by humans, and can often produce more accurate results than traditional machine-learning approaches. In deep learning, interconnected layers of software-based calculators known as 'neurons' form a neural network. The network can ingest vast amounts of input data and process them through multiple layers that learn increasingly complex features of the data at each layer. The network can then make a determination about the data, learn if its determination is correct, and use what it has learned to make determinations about new data. For example, once it learns what an object looks like, it can recognize the object in a new image." (Bistra K Vassileva, "Artificial Intelligence: Concepts and Notions", 2021)
"Deep learning refers to artificial neural networks that mimic the workings of the human brain in the formation of patterns used in data processing and decision-making. Deep learning is a subset of machine learning. They are artificial intelligence networks capable of learning from unstructured or unlabeled data." (Atakan Gerger, "Technologies for Connected Government Implementation: Success Factors and Best Practices", 2021)
"It is a machine learning method using multiple layers of nonlinear processing units to extract features from data." (Sercan Demirci et al, "Detection of Diabetic Retinopathy With Mobile Application Using Deep Learning", 2021)
"It is a subarea of machine learning, where the models are built using multiple layers of artificial neural networks for learning useful patterns from raw data." (Gunjan Ansari et al, "Natural Language Processing in Online Reviews", 2021)
"It is an artificial intelligence technology that imitates the role of the human brain in data processing and the development of decision-making patterns." (Mehmet A Cifci, "Optimizing WSNs for CPS Using Machine Learning Techniques", 2021)
"One part of the broader family of machine learning methods based on artificial neural networks with representation learning. Learning can be supervised, semi-supervised or unsupervised." (Jan Bosch et al, "Engineering AI Systems: A Research Agenda", 2021)
"Part of Machine Learning, where methods of higher complexity are used for training data representation." (Andrej Zgank et al, "Embodied Conversation: A Personalized Conversational HCI Interface for Ambient Intelligence", 2021)
"Sub-domain in the field of machine learning that deals with the use of algorithms inspired by human brain cells to solve complex real-world problems." (Shatakshi Singhet al, "A Survey on Intelligence Tools for Data Analytics", 2021)
"This is also a subset of AI where unstructured data is processed using layers of neural networks to identify, predict and detect patterns. Deep learning is used when there is a large amount of unlabeled data and problem is too complex to be solved using machine learning algorithms. Deep learning algorithms are used in computer vision and facial recognition systems." (Vijayaraghavan Varadharajan & Akanksha Rajendra Singh, "Building Intelligent Cities: Concepts, Principles, and Technologies", 2021)
"A rapidly evolving machine learning technique used to build, train, and test neural networks that probabilistically predict outcomes and/or classify unstructured data." (Forrester)
"Deep Learning is a subset of machine learning concerned with large amounts of data with algorithms that have been inspired by the structure and function of the human brain, which is why deep learning models are often referred to as deep neural networks. It is is a part of a broader family of machine learning methods based on learning data representations, as opposed to traditional task-specific algorithms." (Databricks) [source]
"Deep Learning refers to complex multi-layer neural nets. They are especially suitable for image and voice recognition, and for unsupervised tasks with complex, unstructured data." (Statistics.com)
"is a machine learning methodology where a system learns the patterns in data by automatically learning a hierarchical layer of features. " (Accenture)
