Adaptive Learning


Adaptive Learning

Ever since I was a young kid, I always cared about how fast I could get things done. I never liked wasting time. My desire for setting my own learning pace attracted me to self-teaching. One problem I find in doing this is a lack of resources. I cannot find educational programs or books that convey the material in an appealing flow. It is either so fast that it is overwhelming or so slow that I get bored. This happened even at a young age when I was in grade school. I would teach myself something such as a math topic, but then when I went to school, I would sit there doing nothing as the teacher droned on about topics I already knew. This quest for efficiency and effectiveness led me to adaptive learning and an internship at Engility. I was fortunate enough to spend my summer in Engility’s Nascent Technology Center (the company’s division focused on developing new capabilities in emerging fields like artificial intelligence, machine learning and data analytics).

What Is Adaptive Learning?

In its simplest sense, adaptive learning describes a learning environment that analyzes the user's progress and reacts to it. For instance, the environment might adjust the difficulty of the questions or the material being displayed. Adaptive training presents the user with the most relevant information to them and allows them to learn more effectively as a result. It is inefficient to teach a user information they already know just because it is part of the standard training pipeline. Instead, with adaptive training, the material they already know is identified and skipped. Adaptive training also helps improve proficiency in a skill. With adaptive training, the scenario presented to the user can be adjusted to optimize the difficulty until the user can still succeed but learns the most. Ideally, this is obtained through the fewest number of training scenarios possible and is much more efficient than the standard “level-based” approach.

Applying Classroom Concepts to Internship Practice

As a computer engineering major at Virginia Tech studying basic software design, I see the intersection of my studies and work at Engility every day. I often have to use the different design methodologies I have learned in school to make decisions about how to structure a piece of code. Even in solving many of the problems I face, I use the basic engineering principles reviewed in the introductory courses.

Adaptive Learning Blog

What’s Next for Adaptive Learning (and Me)?

I see machine learning and artificial intelligence exploding in the coming years. It allows for so much to be done that humans are just not feasibly capable of. Specific to adaptive learning, I see the approach becoming very common. The work being done here is only the beginning. By building out a general structure, it can be applied to a multitude of scenarios ranging from educational uses to job-specific training. I see adaptive training becoming the standard educational platform in the near future.

This upcoming year, I will still be studying computer engineering and science at its core, but now having exposure to the data science and machine learning aspect of it, I plan on personally studying this information much more heavily. My experiences during this internship have shown me the truly magnificent power of machine learning and the pivotal role it will play in the future.

Learning can be achieved in so many different computational and statistical ways!

Interested in learning more about career opportunities at Engility? Visit www.engility.com/careers.

Share this Post:

Posted by Justin Deutsch

I am currently a sophomore at Virginia Tech studying computer engineering. I hope to further my education in software design and artificial intelligence. When not studying, I am involved with clubs on campus such as the Drone Design Team and enjoy playing soccer with my friends.