Human learning

    In the context of machine learning, “human learning” typically refers to the ways in which humans design, develop, and improve machine learning models and algorithms.

    • Learning is typically referred to as the process of gaining information through observation.
    • why do we need to learn?
      • In our daily life, we need to carry out multiple activities.
      • It may be task as simple as walking done the street or doing the home work.
      • we keep learning more or in other words acquiring more information the efficiency in doing the tasks keep improving.

    Types of Human Learning

    Human learning happens in one of the three ways.

    1.Learning directly under expert guidance:

    • Somebody who is an expert in the subject directly teaches us.
    • An infant may inculcate certain traits and characteristics, learning Straight from it’s guardians.
    • He calls his hand, a ‘hand’, because that is the information he gets from his parents.
    • The Next phase of life, baby learns how to form words from the alphabets and number from the digits.
    • In all phases of life of a human being, learning is imparted by some one, purely because of the fact that he/she has already gathered the knowledge by virtue of his/her experience in that field.

    2.Learning guided by knowledge gained from experts:

    • we build our own notion indirectly based on what we have learnt from the expert in the post.
    • Learning also happens with the knowledge which has been imparted by teacher or mentor at some point of time in some other from/context.

    3.Learning by self or Self learning.

    • we do it ourselves, may be after multiple attempts, some being unsuccessful.
    • In many situations, humans are left to learn on their own.
    • A classic example is a baby learning to walk through obstacles. He bumps on to obstacles and falls down multiple times till he learns that whenever there is an obstacle, he needs to cross over it.

     

    Advantages:
    1. Automation and efficiency.
    2. Personalization and recommendations.
    3. Continuous improvement.
    Disadvantages:
    1. Data quality and dependency issues.
    2. Lack of interpretability and transparency.
    3. Resource-intensive and complexity.