Concept learning

Concept learning, also known as category learning, concept attainment, and concept formation, is defined by Bruner, Goodnow, & Austin as "the search for and testing of attributes that can be used to distinguish exemplars from non exemplars of various categories". More simply put, concepts are the mental categories that help us classify objects, events, or ideas, building on the understanding that each object, event, or idea has a set of common relevant features. Thus, concept learning is a strategy which requires a learner to compare and contrast groups or categories that contain concept-relevant features with groups or categories that do not contain concept-relevant features.
The concept of concept attainment requires the following five categories:

the definition of task;
the nature of the examples encountered;
the nature of validation procedures;
the consequences of specific categorizations; and
the nature of imposed restrictions.

In a concept learning task, a human classifies objects by being shown a set of example objects along with their class labels. The learner simplifies what has been observed by condensing it in the form of an example. This simplified version of what has been learned is then applied to future examples. Concept learning may be simple or complex because learning takes place over many areas. When a concept is difficult, it is less likely that the learner will be able to simplify, and therefore will be less likely to learn. Colloquially, the task is known as learning from examples. Most theories of concept learning are based on the storage of exemplars and avoid summarization or overt abstraction of any kind.
In machine learning, this theory can be applied in training computer programs.

Concept learning: Inferring a Boolean-valued function from training examples of its input and output.
A concept is an idea of something formed by combining all its features or attributes which construct the given concept. Every concept has two components:
*Attributes: features that one must look for to decide whether a data instance is a positive one of the concept.
*A rule: denotes what conjunction of constraints on the attributes will qualify as a positive instance of the concept.
Types of concepts

Concept learning must be distinguished from learning by reciting something from memory or discriminating between two things that differ. However, these issues are closely related, since memory recall of facts could be considered a "trivial" conceptual process where prior exemplars representing the concept are invariant. Similarly, while discrimination is not the same as initial concept learning, discrimination processes are involved in refining concepts by means of the repeated presentation of exemplars. Concept attainment is rooted in inductive learning. So, when designing a curriculum or learning through this method, comparing like and unlike examples are key in defining the characteristics of a topic.

Concrete or perceptual concepts vs abstract concepts

Concrete concepts are objects that can be perceived by personal sensations and perceptions. These are objects like chairs and dogs where personal interactions occur with them and create a concept. Concepts become more concrete as the word we use to associate with it has a perceivable entity. According to Paivio’s dual-coding theory, concrete concepts are the one that is remembered easier from their perceptual memory codes. Evidence has shown that when words are heard they are associated with a concrete concept and are re-enact any previous interaction with the word within the sensorimotor system. Examples of concrete concepts in learning are early educational math concepts like adding and subtracting.
Abstract concepts are words and ideas that deal with emotions, personality traits and events. Terms like fantasy or cold have a more abstract concept within them. Every person has their personal definition, which is ever-changing and comparing, of abstract concepts. For example, cold could mean the physical temperature of the surrounding area, or it could define the action and personality of another person. However, within concrete concepts there is still a level of abstractness; concrete and abstract concepts can be seen on a scale. Some ideas like chair and dog are more cut and dry in their perceptions but concepts like cold and fantasy can be seen in a more obscure way. Examples of abstract concept learning are topics like religion and ethics. Abstract-concept learning is seeing the comparison of the stimuli based on a rule and when it is a novel stimulus. Abstract-concept learning has three criteria to rule out any alternative explanations to define the novelty of the stimuli. One transfer stimuli has to be novel to the individual. This means it needs to be a new stimulus to the individual. Two, there is no replication of the transfer stimuli. Third and lastly, to have a full abstract learning experience, there has to be an equal amount of baseline performance and transfer performance.
Binder, Westbury, McKiernan, Possing, and Medler used fMRI to scan individuals' brains as they made lexical decisions on abstract and concrete concepts. Abstract concepts elicited greater activation in the left precentral gyrus, left inferior frontal gyrus and sulcus, and left superior temporal gyrus, whereas concrete concepts elicited greater activation in bilateral angular gyri, the right middle temporal gyrus, the left middle frontal gyrus, bilateral posterior cingulate gyri, and bilateral precunei.
In 1986 Allan Paivio hypothesized the dual-coding theory, which states that both verbal and visual information is used to represent information. When thinking of the concept dog, thoughts of both the word dog and an image of a dog occur. Dual-coding theory assumes that abstract concepts involve the verbal semantic system and concrete concepts are additionally involved with the visual imaginary system.

Defined (or relational) and associated concepts

Relational and associated concepts are words, ideas and thoughts that are connected in some form. For relational concepts they are connected in a universal definition. Common relational terms are up-down, left-right, and food-dinner. These ideas are learned in our early childhood and are important for children to understand. These concepts are integral within our understanding and reasoning in conservation tasks. Relational terms that are verbs and prepositions have a large influence on how objects are understood. These terms are more likely to create a larger understanding of the object and they are able to cross over to other languages.
Associated concepts are connected by the individual’s past and own perception. Associative concept learning involves categorizing stimuli based on a common response or outcome regardless of perceptual similarity into appropriate categories. This is associating these thoughts and ideas with other thoughts and ideas that are understood by a few or the individual. An example of this is in elementary school when learning the direction of the compass North, East, South and West. Teacher have used “Never Eat Soggy Waffles”, “Never Eat Sour Worms” and students were able to create their own version to help them learn the directions.

Complex concepts

Constructs such as a schema and a script are examples of complex concepts. A schema is an organization of smaller concepts and is revised by situational information to assist in comprehension. A script on the other hand is a list of actions that a person follows in order to complete a desired goal. An example of a script would be the process of buying a CD. There are several actions that must occur before the actual act of purchasing the CD and a script provides a sequence of the necessary actions and proper order of these actions in order to be successful in purchasing the CD.

Concept attainment learning plan development

Concept attainment for in education and learning is an active learning method. Therefore, learning plans, methods, and goals can be chosen to implement concept attainment.
David Perkin's Work on Knowledge as Design, Perkin's 4 Questions outline learning plan questions:
1) What are the critical attributes of the concept?
2) What are the purposes of the concept?
3) What model cases of the concept?
4) What are the arguments for learning the concept?

Bias in concept attainment

Concept learning has been historically studied with deep influences from goals and functions that concepts are assumed to have. Research has investigated how function of concepts influences the learning process, which focuses on the external function. Focusing on different models for concept attainment research would expand studies in this field. When reading articles and studies, noticing potential bias and qualifying the resource is required in this topic.

Inductive learning and ML conflict with concept learning

In general, the theoretical issues underlying concept learning for machine learning are those underlying induction. These issues are addressed in many diverse publications, including literature on subjects like Version Spaces, Statistical Learning Theory, PAC Learning, Information Theory, and Algorithmic Information Theory. Some of the broad theoretical ideas are also discussed by Watanabe, Solomonoff, and Rendell ; see the reference list below.

Modern psychological theories

It is difficult to make any general statements about human concept learning without already assuming a particular psychological theory of concept learning. Although the classical views of concepts and concept learning in philosophy speak of a process of abstraction, data compression, simplification, and summarization, currently popular psychological theories of concept learning diverge on all these basic points. The history of psychology has seen the rise and fall of many theories about concept learning. Classical conditioning created the earliest experimental technique. Reinforcement learning as described by Watson and elaborated by Clark Hull created a lasting paradigm in behavioral psychology. Cognitive psychology emphasized a computer and information flow metaphor for concept formation. Neural network models of concept formation and the structure of knowledge have opened powerful hierarchical models of knowledge organization such as George Miller's Wordnet. Neural networks are based on computational models of learning using factor analysis or convolution. Neural networks also are open to neuroscience and psychophysiological models of learning following Karl Lashley and Donald Hebb.