When most people hear “Machine Learning,” they think of robot or something very big machines which work under heavy code depending on who you ask. But Machine Learning is not like that nor it is a futuristic fantasy, it’s already here for decades in some specialized applications, such as Optical Character Recognition (OCR).
The first ML application that really became mainstream, improving the lives of hundreds
of millions of people, took over the world back in the 1990s: it was the spam filter.
Where does Machine Learning start and where does it end? What exactly does it
mean for a machine to learn something?
Here in this blog, we will look at the map of Machine Learning and learn about the main regions and the most notable landmarks and jargon of ML that anyone in this field often uses. To write this blog, I will take help from a very famous book of ML, Hands-On Machine Learning With Scikit-Learn, Keras, and Tensorflow.
What Is Machine Learning?
Machine Learning is the science (and art) of programming computers so they can learn from data.
The slightly more general definition of ML by --Arthur Samuel
Machine Learning is the] field of study that gives computers the ability to learn
without being explicitly programmed.
An engineering-oriented definition for Machine Learning by --Tom Mitchell
A computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E.
Why Use Machine Learning?
• Problems for which existing solutions require a lot of hand-tuning or long lists of
rules: one Machine Learning algorithm can often simplify code and perform better.
• Complex problems for which there is no good solution at all using a traditional
approach: the best Machine Learning techniques can find a solution.
• Fluctuating environments: a Machine Learning system can adapt to new data.
• Getting insights about complex problems and large amounts of data.
Types of Machine Learning Systems
According to human supervision, we can divide ML into various categories:
Supervised Learning
Unsupervised Learning
Semi-supervised Learning
Reinforcement Learning
Whether they can learn incrementally or not, depending on that we can divide ML into two categories:
Online Learning
Batch Learning
Whether they work by comparing new data points to know data points, or instead detect patterns in the training data and build the model:
Instance-Based Learning
Model-Based Learning
Main Challenges of Machine Learning
Our main task is to select a learning algorithm and train it on some
data, the two things that can go wrong are “bad algorithm” and “bad data.”
Let’s start with examples of bad data:
Insufficient Quantity of Training Data
Nonrepresentative Training Data
Poor-Quality Data
Irrelevant Features
Now let's see some examples of bad algorithms:
Overfitting the Training Data
Underfitting the Training Data
Once we have trained a model
We don’t want to just “hope”, We want it generalizes to new cases accurately with good accuracy. We want to evaluate it, and finetune it if necessary and required to increase the performance of the model.
Testing and Validating
Hyperparameter Tuning and Model Selection
Holdout validation
Cross-validation
3. Data Mismatch
Here in this part, I have only made a map for the major terminologies & jargon often used in the field of machine learning. Before going very deep into each and every terminology that what it means. It was very necessary for me to create a structure or map which we are going to follow so that things will go on very easy way and anyone will able to digest those explanations very easily.
In my upcoming blog, I will start explaining each and every terminology discussed here in this part in a very easy and descriptive way.
Till then thanks for giving your time and reading my creation.
Comments