Imerzi - Adaptive Learning

Updated: Apr 11

Author: Bradley Wolfenden

In today’s world, people expect customization. Whether that’s in relation to your favorite drink at the local coffee shop, your new laptop’s configurations, vitamins, graphics, music playlists, cars, or homes, there are deeply rooted psychological explanations as to why an ability to customize has become the new baseline for consumers. Luckily, when it comes to academics and training programs, the technology exists to deliver customized, or adaptive, learning experiences.

Adaptive learning is the delivery of custom learning experiences that address the unique needs of the learner. The concept applies to both the knowledge level of the content delivered to the individual, and the format or method by which the content is presented. Essentially, to be most effective, the learning material needs to meet the learner where they’re at from a proficiency perspective and be delivered in a way that most reflects how their unique brain prefers to consume information.

Before the technology necessary to drive autonomous, adaptive learning became available, one-on-one tutoring was the closest example of this concept. Almost inevitably, one-on-one tutors adjust to their student by altering the pace of instruction, timing of help or hints, types of learning activities, etc. And while research shows how impactful one-on-one tutoring is, it’s nearly impossible to scale. This is where technology, and more specifically, computer algorithms, can expand our abilities by augmenting the limited teacher/ tutor resources.

Adaptive learning technologies are driven by three fundamental questions:

1. What does the learner already ‘know’?

2. What should the learner experience next?

3. How does this learner’s brain prefer to consume information?

Building adaptive learning algorithms around these questions allows for the content to be shaped to the needs of the individual student and emulates the role of the teacher. In doing so, the emphasis in learning shifts from seat-time to mastery-based. Constantly, feedback from within each lesson is immediately fed back into the learning algorithms for continual adaptability and growth. This method of instruction demands learners achieve proficiency in order to progress and complete the coursework, but allows the learner to take their own path at their own pace.

While the technology necessary to support this approach to learning is new, the thinking behind it, isn’t. Educational psychologist Benjamin Bloom, in 1984, published his original research on this topic, “2 Sigma Project” in Educational Researcher. What he found is that the average learner in a one-to-one mastery-based learning situation performed two standard deviations better than the average learner in a conventional setting. This means that 98% of the learners in the one-to-one mastery-based situation performed as well as the average learner in the traditional setting.

The potential of adaptive learning has since been recognized by everyone from the National Aeronautics and Space Administration (NASA) to the U.S. Department of Defense to the U.S. Department of Education. In fact, the U.S. Department of Education’s National Education Technology Plan (NETP) fully endorses the use of data and devices to advance learning and achievement. Integrating adaptive learning into cybersecurity education, training and development is crucial to preparing the next generation of well-qualified cyber professionals. The field requires a knowledgebase that is both broad and deep, is highly evolving, and demands its employees maintain their skillsets despite frequent advancements in technologies and threats. With more than 500,000 vacant cybersecurity jobs in the U.S. alone, adaptive learning strategies are one solution to closing the cyber workforce gap.