In this article we explore the idea of learning. The core concept behind it. On one hand we learn what machine learning is. While on the other hand, we discover how we learn as humans.
Machine Learning Model
Machine Learning Model is defined as a mathematical representation of the output of the training process.
Types of Machine Learning:
- Supervised Learning
Supervised machine learning indicates the practice of training algorithms to predict results. The input data are fed into such algorithms. That’s being done to obtain specific outcomes.
- Classification Models
- Regression Models
- Unsupervised Learning
Unlike in the case of supervised learning, unsupervised learning is more random. It offers the algorithm more autonomy. From the data itself they detect a pattern.
And those patterns help solve clustering and association problems.
- Clustering
- Association Rule
- Dimensionality Reduction
Human Learning Model:
When observed objectively, the way we learn is not much different. Sometimes we are being fed certain data to get desired results. Like how it happened in our schools.
And sometimes we consume information on our own and act on it.
Let’s explore the basics of the Human Learning Model and know about our different styles of absorbing information.
The VARK model of human learning divides our learning styles into four broad segments.
We are all very much familiar with these.
- Visual
- Auditory
- Reading & Writing
- Kinesthetic
But apart from the four basic types of learning, there are four additional categories.
- Logical/analytical learners
- Social/linguistic learners
- Nature learners
- Solitary learners
But there’s one core thing that distinguishes human learning from machine learning.
That’s the use of emotions. Our learning processes are not always very pragmatic or output oriented.
For instance we often experience emotions in different forms and try to adapt.
Fear is that kind of emotion. Being scared is the state of mind. We need to understand the difference between Fear and emotion, as both are different. We are just scared (which is a temporary feeling) to try new things.
There are other emotions and intuitions too which drive our learning. If we utilize these emotions to our learning path, we won’t be scared of anything.
Curiosity VS Necessity
Curiosity drives innovation. It is an impulse to pursue a thought, find a solution, seek new possibilities or keep on a path to see what’s around the next bend.
Also at the same time, necessities also trigger certain learning and innovation. Our history is full of both kinds of learning and discoveries.
From the discovery of fire and wheel to the modern human innovation, curiosity and necessity both have been a driving force in its own way.
Evolution & Survival Instincts
Evolution and instincts are also great enablers when it comes to adaptive learning. Our species, along with many others in the world, has shown how evolution and survival needs can be a great motivation to learn from the environment.
Now with the collective understanding of how humans learn and how machines learn let’s do a comparative analysis.
Machine Learning VS Human Learning:
ML Works in the following aspects.
- data,
- association,
- equations,
- Predictions
- Decision Tree
- Memory
Human learning is also kind of similar but also different when it comes to emotions and memories.
- data,
- association,
- equations and
- emotions
- Short memory
- Long-term memory
Conclusion:
The idea behind this article is to enable you to know more about your own learning style. Coming out of your own fear and anxiety and taking on new challenges.
Like Machine Learning algorithms our minds also more productive with constant learning. Because it’s just reverse engineering used to replicate and build a machine learning model, same as our human brain and its learning model with some extra calculations and algorithms. Our brain is more powerful than any AI/ML which should be utilized efficiently with the help of learning styles. It filters out wrong and useless information. Instead nourishes itself with the things that matter.
2