A memory-based learning system is an extended memory management system that decomposes the input space either statically or dynamically into subregions for the purpose of storing and retrieving functional information.
Memory-Based Learning (MBL) is a simple function approximation method whose roots go back, at least, to 1910. Training a memory based learner is an almost trivial operation: just store each data point in memory (or a database). Making a prediction about the output that will result from some input attributes based on the data is done by looking at similar points in memory, fitting a local model to those points, and then making a prediction based on the model.
Memory Types:
  1. Semantic Memory: Sometimes called declarative memory, the semantic memory contains the facts and generalized information that we know; concepts, principles, or rules and how to use them; and problem-solving skills and learning strategies.
  2. Episodic Memory: Our memory of personal experiences, is called episodic memory, a mental movie of things we have seen or heard. Episodic memory also can include flashbulb memory, in which an occurrence of an important event fixes mainly visual and auditory memories in a person's mind. When episodic memory and effective instruction is linked, educators can improve retention of concepts and information by explicitly creating memorable events involving visual or auditory images through the use of projects, plays, simulations, and other forms of active learning.
  3. Procedural Memory: The ability to recall how to do something, especially a physical task. The abilities to drive, type, and ride a bicycle are examples of skills that are retained in procedural memory.
MBL Synonyms:
In machine learning, instance-based learning (sometimes called memory-based learning) is a family of learning algorithms that, instead of performing explicit generalization, compares new problem instances with instances seen in training, which has been stored in memory. Instance-based learning is a kind of lazy learning. It is called instance-based because it constructs hypotheses directly from the training instances themselves.
MBL Components:
  1. A Learning Component: Memory-based, as it involves storing examples in memory without abstraction, selection, or restructuring.
  2. A Performance Component: Similarity-based, as the stored examples are used as a basis for mapping input to output; input instances are classified by assigning them an output label.
MBL Systems:
  1. Memory Requirement
  2. Sample Size
  3. Expected Performance
  4. Computational Complexity
MBL Process:
  1. RETRIEVE the most similar case or cases
  2. REUSE the information and knowledge in that case to solve the problem
  3. REVISE the proposed solution
  4. RETAIN the parts of this experience likely to be useful for future problem-solving
MBL Advantages:
  1. Its ability to adapt its model to previously unseen data.
  2. Instance-based learners may simply store a new instance or throw an old instance away.
MBL Resources:
  1. Edmodo: https://spotlight.edmodo.com/product/based-learning-13-mbl-memory-based-learning--389675/
  2. Classroom Games for Students’ Memory:https://spotlight.edmodo.com/product/classroom-games-for-students-memory--383747/
  3. Instructional Strategies Designed to Enhance Memory:https://spotlight.edmodo.com/product/instructional-strategies-designed-to-enchance-memory--389673/