As part of participating in EDTC 0560: Using Technology for Teaching and Training, we developed a group project on Future Trends in Educational Technology. My group chose Adaptive Learning. This is part 2 of my research on Developing and Emerging Adaptive Technologies. Part 1 outlines current Adaptive Learning Technologies.
Where are we going?
“This is a key step in developing player-adaptive games that can respond to player actions to improve the gaming experience for education.”
– Dr. James Lester, Professor of Computer Science, North Carolina State speaking on Crystal Island
- Open Tools, Frameworks and Environments
- Big Data, Machine Learning and Deep Learning
- Educational Video Games
- Devices, Wearables & Integrated Technologies
Open Frameworks, Tools and Environments
Next Generation Digital Learning Environment (NGDLE) is an EduCause framework for describing new directions for supplementing or moving away from LMSs. NGDLE envisages a small central hub (host) supplemented by an app store of plug-in tools. The framework is built upon open learning tools interoperability using IMS standards
The Tsugi Project is a model to move the industry toward a Next Generation Digital Learning Environment (NGDLE). It provides a scalable multi-tenant tool hosting environment based on emerging IMS standards. It provides a framework for building scalable, interoperable and open learning tools integration (LTI) using international IMS Global Learning Consortium standards.
Learning and Performance Support Systems (LPSS) is National Research Council of Canada’s integration of an adaptive learning and performance platform that supports personal training and learning.
The platform provides:
- Learning services and a selection of learning materials;
- Automated Competency Development and Recognition algorithms that analyze learners workflows and job skills and develop training programs;
- Personal Learning Record to manage a learner’s learning and training records and credentials over a lifetime;
- Personal Learning Assistant that provides context aware assistance and enables a learners to view, update and access training and development resources anywhere, at any time.
Machine Learning & Deep Learning
Machine Learning is an Artificial Intelligence (AI) that integrates machine and human environments. Machines learn from data created by human action. Deep Learning (DL) is a third generation Machine Learning that integrates machine and human environments. DL’s AI has the ability to learn tasks based on human interactions “without being explicitly programmed”.
Human interactions are input as data. Deep Learning uses analytics to analyze that data. Artificial intelligence uses data to learn tasks. The AI predicts the learner’s behaviour and adapts to customize the learning pathway by creating tasks for the learner.
- TensorFlow, Google open-source Deep Learning software for developing machine intelligence
- Google DeepMind is a 3D game-like neural network artificial intelligence platform
Digital Educational Games
Educational Games have borrowed key adaptive technologies from open world commercial Serious Games: Deep Learning and Goal Recognition.
Deep Learning uses data mining from beta learners to learn behaviours. Goal Recognition predicts player’s goals based on their actions in the environment. Learning is customized by an adaptive learning process that responds to the learner’s in-game actions.
Crystal Island, an open world, player adaptive game, makes use of Deep Learning Goal Recognition. Learning is customized by an adaptive learning process that responds to the learner’s in-game actions.
Devices, Wearables & Integrated Technologies
Devices and Wearables will collect more data to optimize learning. They will send data to teachers to track learner engagement. They integrate learning into our personal lives.
- Ubiquitous wearable, integrated technologies and mobile app innovations for Next-Generation education
- Personalized learning via wearables
- Tacks student engagement
- Increasingly allowing more opportunities to learn anywhere, anytime
- More opportunities to collect more data to optimize learning
- Time, space/location, direction
- Serve out personalized content on learned schedule
- Understands life contexts and spaces: integrates learning into personal time
Atkinson, S.P. (2015). Adaptive Learning and Learning Analytics: a new learning design paradigm. Retrieved from: http://i.unisa.edu.au/siteassets/staff/tiu/documents/adaptive-learning-and-learning-analytics—a-new-learning-design-paradigm.pdf
Arroway, P. (2016). Learning Analytics in Higher Education. EDUCAUSE Library. Retrieved from: https://library.educause.edu/~/media/files/library/2016/2/ers1504la.pdf
Bates, A.W. (2015). EDUCAUSE looks beyond the (current) LMS environment: is it a future we want?. Retrieved from: http://www.tonybates.ca/2015/05/11/educause-looks-beyond-the-current-lms-environment/
Brown, M. (2016). 6 Implications of the Next-Generation Digital Learning Environments (NGDLE) Framework. EDUCAUSE Review. Retrieved from: http://er.educause.edu/blogs/2016/6/6-implications-of-the-next-generation-digital-learning-environments-ngdle-framework
Brown, M., Dehoney, J. and Millichap, N. (2015). What’s Next for the LMS. EduCause Review. Retrieved from: http://er.educause.edu/articles/2015/6/whats-next-for-the-lms
Brown, M., Dehoney, J. and Millichap, N. (2015). The Next Generation Digital Learning Environment: A Report on Research. Retrieved from: https://net.educause.edu/ir/library/pdf/eli3035.pdf
EduTech Update (2015). Adaptive Learning Technology. Retrieved from: http://www.edtechupdate.com/adaptive-learning/examples/technology/
Ferguson, Rebecca; Brasher, Andrew; Clow, Doug; Griffiths, Dai and Drachsler, Hendrik (2016). Learning Analytics: Visions of the Future. Retrieved from: http://oro.open.ac.uk/45312/1/LAK16%20LACE%20panel%20final.pdf
Haythornthwaite, C., Andrews, R., Fransman, J. & Meyers, E.M. (2016). The Sage Handbook of E-learning Research, 2nd edition.
Horizon Report (2017). 2017 Higher Education Edition. Retrieved from: http://cdn.nmc.org/media/2017-nmc-horizon-report-he-EN.pdf
Min, W., Ha E.Y., Rowe, J., Mott, B., & Lester, J. (2014). Deep Learning-Based Goal Recognition in Open-Ended Digital Games. Retrieved from: https://www.intellimedia.ncsu.edu/wp-content/uploads/min-aiide-2014.pdf
Moskal, P, Carter, D. & Johnson, D. (2017). 7 Things You Should Know About Adaptive Learning. https://library.educause.edu/resources/2017/1/7-things-you-should-know-about-adaptive-learning
Pearson, J. (2017). This Deep Learning Algorithm Can Predict Your Next Move in a Video Game. MotherBoard. Retrieved from: https://motherboard.vice.com/en_us/article/this-deep-learning-algorithm-can-predict-your-next-move-in-a-video-game
The Tsugi Project (2017). Retrieved from: https://tsugi.org