How Enlearn Is Different
Enlearn has developed a next-generation personalized learning platform built on the understanding that all learning is contextual and shaped by complex interactions between a student, teachers, curricula, peers, and other interdependent variables in the learning ecosystem. In order to produce large improvements in outcomes at scale – particularly for students who are struggling – a personalized learning system needs to synchronize and optimize these variables for the benefit of each learner. By leading in the development and application of new, cutting-edge research, Enlearn has created a learning platform that not only amplifies content, but continuously learns and improves itself over time.
Enlearn stands apart from other personalized learning platforms in four key ways: Ā
Amplify your content
Unlike other adaptive platforms, Enlearn goes far beyond āreshufflingā academic content created by authors. By following the studentās thinking process throughout a learning activity, Enlearn is able to provide the right explanations, strategies, or scaffolds within each problem to accelerate learning in real time. By enabling adaptation across multiple variables, Enlearn amplifies the initial content and can achieve significantly stronger results than any platform that simply reorders fixed content.
The Enlearn platform can:
- Increase content 10-100X
- Use data to automatically refine content ontologies and conceptual dependencies
- Create detailed explanations of how to think about solving every problem
- Instrument 100ās of scaffolds and supports for each problem automatically
Personalize for the student, teacher, and classroom
Because learning is influenced by multiple variables, the Enlearn platform is designed to adapt to meet the unique needs of the student and teacher, as well as address a variety of classroom configurations.
Whole-student adaptivity
In most digital learning products today, personalization is built around two things: a studentās level of knowledge and individual learning preferences. Ā Enlearn extends personalization to include the studentās:
- Demonstrated skill level
- Problem progression history
- Scaffolding and fading support needs
- Non-cognitive development (growth mindset, productive struggle, agency)
- Meta-cognitive development (problem solving strategies, self-assessment)
Teaching Assistant
The Enlearn platform can notify teachers when students confront particularly challenging misconceptions or learning hurdles and recommend resources. Like an excellent teaching assistant, Enlearn enables teachers to maximize classroom time and target their expertise where itās needed most by providing:
- Real-time recommendations for instructional activities, including offline activities, based on diagnostic data
- Data about studentās cognitive and non-cognitive skills and recommendations for further developing those skills
- Insights about students’ learning preferences, problem solving approaches, and growth mindset
- Data about each studentās learning history
Classroom Structure
The Enlearn platform is easily deployable in classrooms with limited technology and lends itself to optimizing various classroom configurations and approaches by providing:
- Student grouping recommendations based on common misconceptions or learning gaps
- Data about optimal classroom structures (blended learning, station/flex/lab models)
- Streamlined, rapid diagnostics
Diagnose, discover, remediate
Because Enlearn tracks where and how individuals are struggling or progressing throughout the problem-solving process, a single problem can provide as much insight as several multiple choice questions. This rapid acquisition of granular data about student understanding continuously improves Enlearnās real-time diagnostic capacity, enabling it to identify and address known misconceptions and discover unknown misconceptions or conceptual obstacles. By precisely targeting practice on critical concepts, sub-concepts or skill gaps, students spend time on what matters most. The Enlearn engine is driven by algorithms that optimize results with each new data point so that the very next student benefits from improvements in accuracy, efficiency, and intervention effectiveness.
The Enlearn platform can:
- Provide rapid, fine grain diagnostics
- Dynamically curate the next problem to discover exact misconceptions
- Analyze steps, timing, and scaffolds during problem solving to provide the most insight on each studentās thinking process
- Target practice at the sub-concept or micro-skill level
- Provide detailed explanations of reasoning for each step in a problem
- Toggle between an explain mode and student work mode at any point
- Deliver just-in-time adjustment of explanations based on partial solution errors
- Follow multiple approaches to solving a problem and suggests more efficient ones
- Address studentsā learning needs by adjusting the problem type, conceptual difficulty of a specific problem type, or level of scaffolding within a problem
Designed for continuous improvement
Enlearn benefits from a unique partnership with the Center for Game Science at the University of Washington (U.W.). Headed by Enlearnās founder, a team of over 15 researchers at the U.W. continues to build on over 10 years of research focused exclusively on how the Enlearn platform can further improve learning outcomes.
This research is pushing new frontiers in learning science, as well as machine learning and knowledge representation. Moreover, this innovative partnership enables Enlearn to take advantage of cutting-edge research and apply these new discoveries to our platform. The result is a state-of-the-art learning platform designed to continuously improve over time.
Key features unique to the Enlearn platform
The creators of Enlearn initiated, conducted, and published new research aimed at solving problems that simply could not be solved by the collective body of knowledge in the above mentioned disciplines. Some examples of Enlearn-specific research discoveries include:
- How to produce significant changes in productive struggle and growth mindset in a digital setting
- Novel machine learning methods capable of dealing with complex educational learning settings that were not solvable with previous machine learning methods
- Novel ways to represent, encode, and generate learning content at the thought process level. This enables the platform to follow the studentās thinking processes during problem solving, amplify curriculum 10-100x, and personalize content, delivery, and learning pathways for each unique learner.
Self-learning platform
Researchers behind the Enlearn Platform realize that the common approach to scientific research of learning is to find principles behind learning methods that work in general terms. Ā This approach does not, however, provide insight into the ideal learning process for any individual learner, unique classroom setting, or specific teacher. Ā For this reason, the Enlearn Platform is designed to:
- Learn itself and become highly specialized for each classroom and each student
- Automatically analyze and apply insights from each new student learning on the platform to future learners
- Self-adapt to ensure that Enlearn is highly personalized and differentiated in ways that general principles in the current state-of-the-art research are not capable of knowing
- Get more specialized in the continuous rapid process of self-adaptation