In this submission I will discuss the differences between supervised
and unsupervised learning as I understand it based on the provided
materials and materials found on the web. All of the references to the
materials on which this submission is based can be found at the
bottom of the post.
For starters let’s talk about supervised learning. As you can guess from
the naming supervised learning means a process of learning when the
so called “operator” executes supervision or overwatching over an
object which learns. In this context supervision means not just
surveillance but somewhat active involvement and this involvement
can be manifested in a supply of solutions which can be utilized as an
example for unsolved tasks (Computerhile, 2015). When the on a new
data is started the program performs a comparison between provided
solutions or better to say it applies knowledge extracted from those
solutions in order to solve new tasks. An example for supervised
learning would be sorting of pictures into different categories where we
defined certain traits of each category, for example cars and bikes
(Salian, 2019). Usually in supervised learning we can predict the output
with somewhat high precision. Output and input is in our control.
Because of that it is more reliable and simpler compared to
unsupervised learning.
Now let us talk about unsupervised learning. In the case of
unsupervised learning there is less input from the operator, for
example operator can define a certain trait they want to see in the
output but they do not provide examples of final solutions (Johnson,
2022). For unsupervised learning the output is not certain or much less
certain compared to supervised learning. At the same time
unsupervised learning can reveal some patterns in the data which
were not obvious which brings me to the though that more atomicity
can allow your subordinates to manifest their creativity (James, 2013).
References:
A., & Salian, I. (2019). NVIDIA Blog: Supervised Vs. Unsupervised
Learning. Retrieved from: https://blogs.nvidia.com
Computerphile. (2015). Machine Learning Methods - Computerphile.
Retrieved from: https://www.youtube.com
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An
Introduction to Statistical Learning with Applications in R. New York,
NY: Springer
and unsupervised learning as I understand it based on the provided
materials and materials found on the web. All of the references to the
materials on which this submission is based can be found at the
bottom of the post.
For starters let’s talk about supervised learning. As you can guess from
the naming supervised learning means a process of learning when the
so called “operator” executes supervision or overwatching over an
object which learns. In this context supervision means not just
surveillance but somewhat active involvement and this involvement
can be manifested in a supply of solutions which can be utilized as an
example for unsolved tasks (Computerhile, 2015). When the on a new
data is started the program performs a comparison between provided
solutions or better to say it applies knowledge extracted from those
solutions in order to solve new tasks. An example for supervised
learning would be sorting of pictures into different categories where we
defined certain traits of each category, for example cars and bikes
(Salian, 2019). Usually in supervised learning we can predict the output
with somewhat high precision. Output and input is in our control.
Because of that it is more reliable and simpler compared to
unsupervised learning.
Now let us talk about unsupervised learning. In the case of
unsupervised learning there is less input from the operator, for
example operator can define a certain trait they want to see in the
output but they do not provide examples of final solutions (Johnson,
2022). For unsupervised learning the output is not certain or much less
certain compared to supervised learning. At the same time
unsupervised learning can reveal some patterns in the data which
were not obvious which brings me to the though that more atomicity
can allow your subordinates to manifest their creativity (James, 2013).
References:
A., & Salian, I. (2019). NVIDIA Blog: Supervised Vs. Unsupervised
Learning. Retrieved from: https://blogs.nvidia.com
Computerphile. (2015). Machine Learning Methods - Computerphile.
Retrieved from: https://www.youtube.com
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An
Introduction to Statistical Learning with Applications in R. New York,
NY: Springer
