Edge computing and just-in-time learning

Practical approaches to achieve efficient, optimal results

By MIT Horizon

Emerging technologies can provide fresh perspectives on educational practices. In this article, we’ll explore how edge computing — technologies that process data close to its source — can serve as an analogy for “just-in-time learning,” a strategy that delivers instruction precisely when and where it’s needed. This comparison not only highlights the importance of timeliness in both technology and learning but also underscores the potential for more personalized, context-aware educational experiences.

Understanding edge computing

To appreciate the significance of edge computing, it’s helpful to first consider its counterpart, cloud computing. Cloud computing has revolutionized the way data is stored and processed, centralizing these tasks in large data centers, allowing for scalable, flexible, and cost-effective computing solutions that are accessible from virtually anywhere. However, this approach also has its limitations, particularly when it comes to latency-the delay between sending data to a cloud server and receiving a response. For applications that require real-time processing, such as autonomous vehicles or certain kinds of infrastructure, this delay can be a critical drawback.

Edge computing addresses this issue by shifting data processing closer to the data source, or “at the edge” of the network. Instead of relying on distant, centralized servers, edge computing uses local devices or servers to process data on-site or near the point of generation. This reduces latency, enhances efficiency, and enables faster, more context-aware decision-making. For example, an autonomous vehicle equipped with edge computing can process sensor data in real time, allowing it to make split-second decisions without the need for constant communication with a remote server.

Just-in-time learning

Just as edge computing offers a more efficient and responsive approach to data processing, just-in-time learning represents a shift toward more immediate, need-based education. In traditional learning environments, instruction is often delivered in a structured, prescheduled manner. Professional development programs might include training sessions that are planned months in advance and which might happen in artificial settings, such as a meeting room, rather than in the context of where the skills would actually get used. This approach asks people to absorb information so that, at some point, they can hopefully apply it when needed, but, in reality, this often leads to learners forgetting or misapplying the knowledge when the time comes.

In contrast, just-in-time learning focuses on delivering information at the moment it is most relevant, allowing learners to acquire knowledge or skills in response to immediate challenges or needs. This method can be particularly effective in professional contexts. By providing targeted instruction exactly when it’s needed, just-in-time learning minimizes the risk of information decay and enhances the learner’s ability to apply knowledge in real-world scenarios.

To understand how just-in-time can be beneficial in a professional setting, consider the way many people approach everyday learning tasks. If you need to fix something around the house or learn a new skill, you’re likely to turn to resources like Google, YouTube, or ChatGPT for guidance. Whether you’re trying to figure out how to julienne a carrot, patch a hole in the wall, or understand the causes of inflation, you can quickly access specific resources (videos, podcasts, articles, etc.) that provide the information you need. What’s more, you can immediately apply what you’ve learned, reinforcing the knowledge through practical use. This immediacy is at the heart of just-in-time learning, making it a powerful tool for both personal and professional growth.

Specialization and efficiency

Another critical aspect of edge computing is its ability to optimize performance for specialized functions. For instance, instead of sending vast amounts of data from an autonomous vehicle to a distant cloud computing center, the vehicle can transmit data to local edge servers that are custom-built to handle that specific type of information. These edge servers can clean, process, and analyze the data more efficiently, providing lower-latency services that enhance the vehicle’s performance.

Similarly, in the realm of learning, there is a notable shift that occurs as individuals move from novice to expert. When learners are just beginning to acquire a new skill or body of knowledge, they typically rely on general cognitive processes and problem-solving strategies. They consciously think through each step, often translating abstract concepts into familiar actions. However, as they gain experience and practice, these processes become more automatic. The steps involved in performing a task are streamlined, errors decrease, and fewer cognitive resources are required. This transition from conscious effort to automaticity makes the process more efficient and effective, just like edge computing can be optimized for specialized tasks.

Learning on the edge

The parallels between edge computing and just-in-time learning reveal important insights into how we can create more responsive, efficient, and personalized educational experiences. Both approaches emphasize the importance of proximity-whether that be processing data close to its source or delivering instruction close to the moment of need. Both also highlight the benefits of specialization, streamlining processes to make them more efficient and effective.