What is Machine Learning?

Machine learning is a subset of Artificial Intelligence (AI) that gives computers the capability to learn without being explicitly programmed, relying on patterns and interferences. As a learning method, machine learning uses algorithms that build a mathematical model based on sample data, known as "training data", in order to make predictions or decisions.

For example, if we want to teach a computer to identify pictures with cats, we will use a dataset of labeled pictures as cats or non-cats. The Machine Learning algorithm will use these samples to sort the kind of images we want.

The person who coined the term 'machine learning' was Arthur Lee Samuel - American pioneer in the field of computer gaming and artificial intelligence - in 1959. Also, this is his definition of Machine Learning:

[Machine Learning is the] field of study that gives computers the ability to learn without being explicitly programmed. - Arthur Samuel, 1959

Photo source:Datarevenue.com

What are the most used machine learning techniques?

Machine learning algorithms are often categorized as supervised or unsupervised, but there are also other methods. The most common are:

• Supervised machine learning algorithms
• Unsupervised machine learning algorithms
• Semi-supervised machine learning algorithms
• Reinforcement machine learning algorithms

Which are the most common machine learning algorithms?

• Linear Regression
• Logistic Regression
• Decision Tree
• SVM
• Naive Bayes
• kNN
• K-Means
• Random Forest
• Dimensionality Reduction Algorithms
• Gradient Boosting algorithms
• GBM
• XGBoost
• LightGBM
• CatBoost

Examples of machine learning applications:

1. Online recommendation systems like Amazon or Netflix;
2. Classifying emails as spam or not spam;
3. Google's Discover Newsfeed;
4. Personal Assistants (Google Assistant, Siri, Cortana);
5. Self-driving cars;
6. Fraud prevention in banking and credit decisions making.

How to learn machine learning?

According to Elite Data Science, there 4 important steps you have to take into this learning process:

1. Prerequisites - Build a foundation of statistics, programming, and a bit of math;
• Python for Data Science;
• Statistics for Data Science;
• Math for Data Science;
2. Sponge Mode - Immerse yourself in the essential theory behind machine learning;
3. Targeted Practice - Use ML packages to practice the following 9 essential topics:
• The Big Picture;
• Optimization;
• Data Preprocessing;
• Sampling and Splitting;
• Supervised Learning;
• Unsupervised Learning;
• Model Evaluation;
• Ensemble Learning;
• Business Applications.
4. Machine Learning Projects - Dive deeper into interesting domains with larger projects.

Which are the best Programming Languages for Machine Learning?

According to the TechRepublic.com, the most in-demanding programming languages for Machine Learning in 2019 are:

1. Python;
2. C++;
3. JavaScript;
4. Java;
5. C#;
6. Julia;
7. Shell;
8. R;
9. TypeScript;
10. Scala.

Resources:

1. Wikipedia: Machine Learning
2. Coursera: Machine Learning
3. Analytics Vidhya: Essentials of Machine Learning Algorithms
4. Elite Data Science: How to Learn Machine Learning