Abstract
The authors emphasize the application scope of the deep learning (DL) technologies in the instructional analysis, design, development, implementation, and evaluation of the educational tools that can enhance the 21st-century modes and models of learning and instruction. The latest trend in the remote learning systems opens a wonderful opportunity for the DL technologies to be integrated with these systems that can impact the way of learning, teaching, design, and development of such systems. The DL technologies provide the data driven decisions and analytical outcomes that can be integrated with the educational technologies. The existing educational technologies and remote learning systems lack in such integrated DL services that can impact the overall education learning systems of the 21st century. The learners and instructors can also benefit from such DL-integrated educational tools. The authors expand further details on the application and implication of the DL services mentioned above in the chapter.
TopBackground
There are some existing online learning services as the Moodle, Jenzabar, Blackboard etc. (Community M., 2021), (Community J., 2021), (Community B., 2021). These services provide the basic online learning management services for the institution, instructors, and students (e.g., Fig 1, 2). The instructors can upload the course materials, recorded class sessions, discussion topics etc. The students can also view the course materials, recorded sessions. As a result, these online learning services become an integral part of the 21st century remote learning model. Moreover, these eLearning management systems provide some analytical services associated with the learners’ enrollment, engagement, retention rate etc. As for example, the florida southern college manages recruitment and retention data with the Jenzabar analytics (Community J., 2021). The Blackboard analytics provide deep insights for various data analytics and predictions to increase effectiveness in enrollment management, recruitment and retention, instructional design and identification of at-risk students (Community B., 2021).
However, these systems lack in the ADDIE aided online learning modes and models and that is where the motivation behind incorporating such ADDIE aided services originate from. There are several studies, that support such incorporation as suggested by (Muniasamy & Alasiry, 2020), (Engelbrecht, 2003), (Martens, Gulikers, & Bastiaens, 2004). Inspired by the studies and applications and implications of the DL, the authors are interested to provide the guidelines for incorporating such services in this chapter.
Key Terms in this Chapter
Image Analysis: The image analysis is a process of extracting meaningful information from the digital image. The process incorporates simple image analysis as reading bar coded tags or as sophisticated as identifying different objects from the image. The CNN is an example of image analysis.
Machine Learning (ML): The machine learning (e.g., ML) is the part of AI, that can learn and improve learning automatically using the data. Some of the real world examples of the ML include virtual personal assistants, video surveillance, malware filtering, etc.
Deep Learning (DL): The deep learning (e.g., DL) is the subset of the machine learning that allows machines to solve complex problems from the multidimensional, complex datasets. Some examples of the DL include self-driving cars, natural language processing, visual recognition, fraud detection, etc.
Computer-Generated Imagery (CGI): The computer-generated imagery (e.g., CGI) is the images created by the applications of the computer graphics, computer simulated results, computer animations, etc.
Natural Language Processing (NLP): The NLP, a branch of the artificial intelligence (e.g., AI), can help the computer to understand, interpret and manipulate the human language by the RNN. Some common examples of the NLP include the email filters, smart assistants, language translation, predictive text, etc.
Artificial Intelligence (AI): The artificial intelligence (e.g., AI) is the smart programs, machines capable of performing the tasks, that require human intelligence. Some of the examples of AI include text editors or auto correct, search and recommendation algorithms, chatbots, digital assistants, etc.
Causal Inference: The causal inference allows the researchers to draw causal conclusions based on the data by following different estimation strategies, assumptions.
Cyberattack: The cyberattack is any attempt to expose, alter, disable, destroy, steal, or gain information through unprivileged or unauthorized access to the computer, network systems.
Multidimensional Search: The searching operation is done in multiple dimensions rather than single one. The searching complexity increases as the no. of dimension increases. The dimensions can be correlated by the searching keywords.
Recurrent Neural Network (RNN): The recurrent neural network (e.g., RNN) is an ANN that can recognize a data’s sequential characteristics and use patterns to predict the next likely scenario. It is generally used in the speech recognition and natural language processing (e.g., NLP).
Digital Assistant: The digital assistant is a computer program that can assist the user by completing different tasks as answering the calls, performing basic tasks etc. The Amazon Echo and Google Home are popular examples of the digital assistant.
Convolutional Neural Network (CNN): The convolutional neural network (e.g., CNN) is a DL algorithm that can analyze image data and differentiate different objects observed in the data.
Cybersecurity: The cybersecurity is the protection measures of the computer systems and networks from the cyberattack. The cyberattack includes the information disclosure, theft or damage to the hardware systems, the disruption or misdirection of the services associated with the system.
Inferential Outcome: The inferential outcome refers to the inferential statistics that makes judgments of the probability that an observed difference between groups is a dependable one or one that might have happened by chance in this study.
Deep Neural Network (DNN): The deep neural network (e.g., DNN) is an artificial neural network (e.g., ANN) with multiple layers between the input and output layers that allow to learn the features that optimally represent the given training data.
Classifier: The classifier utilizes some training data to understand the relationship between the input data and the class. The classifier belongs to the supervised learning where the datasets are labeled.
Deep Learning Technologies: The deep learning technologies define the technology that follows the concept of DL. The deep neural network (e.g., DNN), recurrent neural network (e.g., RNN), convolutional neural network (e.g., CNN) are some examples of the DL technologies.