Learning in AI

What is learning? 

We define learning as the transformative process of taking in information that—when internalized and mixed with what we have experienced—changes what we know and builds on what we do. It’s based on input, process, and reflection. It is what changes us.

–From The New Social Learning by Tony Bingham and Marcia Conner

 

It is the activity of gaining knowledge or skill by studying, practicing, being taught, or experiencing something. Learning enhances the awareness of the subjects of the study. The ability of learning is possessed by humans, some animals, and AI-enabled systems. Learning is categorized as: 

•  Auditory Learning: It is learning by listening and hearing. For example, students listening to recorded audio lectures. 

• Episodic Learning: To learn by remembering sequences of events that one has witnessed or experienced. This is linear and orderly. 

• Motor Learning: It is learning by the precise movement of muscles. For example, picking objects, Writing, etc. 

• Observational Learning: To learn by watching and imitating others. For example, the child tries to learn by mimicking her parent.

•  Perceptual Learning: It is learning to recognize stimuli that one has seen before. For example, identifying and classifying objects and situations. 

• Relational Learning: It involves learning to differentiate among various stimuli on the basis of relational properties, rather than absolute properties. For Example, Adding ‘little less’ salt at the time of cooking potatoes that came up salty last time, when cooked with adding say a tablespoon of salt. 

• Spatial Learning: It is learning through visual stimuli such as images, colors, maps, etc. For Example, A person can create a roadmap in mind before actually following the road. 

• Stimulus-Response Learning: It is learning to perform a particular behavior when a certain stimulus is present. For example, a dog raises its ear on the hearing doorbell.

Types of Learning: 

1. Rote learning

Rote learning is the memorization of information based on repetition.

Examples of rote learning include memorizing the alphabet, numbers, and multiplication tables. Some consider rote learning to be a necessary step in learning certain subjects. Memorization isn’t the most effective way to learn, but it’s a method many students and teachers still use. A common rote learning technique is preparing quickly for a test, also known as cramming. 

For example: When a learner learns a poem or song by reciting or repeating it, without knowing the actual meaning of the poem or song. 

Advantages of Rote Learning 

•  Ability to quickly recall basic facts 

• Helps develop foundational knowledge 

Disadvantages of Rote Learning 

• Can be repetitive 

• Easy to lose focus 

• Doesn’t allow for a deeper understanding of a subject 

• Doesn’t encourage the use of social skills 

• No connection between new and previous knowledge 

• May result in the wrong impression or understanding a concept While being able to quickly recall pieces of information is helpful, to understand information on a deeper level students must use a different method of learning: meaningful learning.

2. Learning From Example:

Induction learning is carried out on the basis of supervised learning. In this learning process, a general rule is induced by the system from a set of observed instances. However, class definitions can be constructed with the help of a classification method. 

Supervised learning, in the context of artificial intelligence (AI) and machine learning, is a type of system in which both input and desired output data are provided. Input and output data are labeled for classification to provide a learning basis for future data processing. Supervised learning systems are mostly associated with retrieval-based AI but they may also be capable of using a generative learning model. 

Training data for supervised learning includes a set of examples with paired input subjects and the desired output (which is also referred to as the supervisory signal). In supervised learning for image processing, for example, an AI system might be provided with labeled pictures of vehicles in categories such as cars and trucks. After a sufficient amount of observation, the system should be able to distinguish between and categorize unlabeled images, at which time training can be said to be complete.

 Supervised learning models have some advantages over the unsupervised approach, but they also have limitations. The systems are more likely to make judgments that humans can relate to, for example, because humans have provided the basis for decisions. However, in the case of a retrieval-based method, supervised learning systems have trouble dealing with new information. If a system with categories for cars and trucks is presented with a bicycle, for example, it would have to be incorrectly lumped in one category or the other. If the AI system was generative, however, it may not know what the bicycle is but would be able to recognize it as belonging to a separate category.

3. Explanation Based Learning
4. Learning By Analogy