De-Mystifying Math and Stats for Machine Learning: Learn from an application perspective rather than the theoretical perspective

Machine Learning (ML) is a wonderful field at the intersection of computer programming, mathematics and domain knowledge. The author has observed that many budding machine learning students and enthusiasts make the mistake of jumping to build and work on algorithms without adequately understanding the math behind algorithms. That is not the right way to go about learning machine learning. One must first understand the mathematics and statistics concepts relevant to machine learning. The algorithms and the associated programming should be learnt subsequently. By mathematics, we are not referring to theoretical mathematics but rather applied mathematics.

The following core concepts are covered in this book.

• Measures of Central Tendency Vs. Dispersion
• Mean Vs. Standard Deviation
• Percentiles
• Dependent Vs. Independent Variables
• Types of data
• Sample Vs. Population
• Hypothesis testing and Type 1 & 2 Errors
• Outliers, Box Plot and Data Transformation
• ML concepts

Concepts related to algorithms are also covered in this book.

• Measuring accuracy in algorithms
• Math behind regression
• Multi collinearity
• Math behind decision tree
• Math behind kNN
• Gradient descent and optimization

These concepts are explained from an application perspective, that is how these concepts are applied in real life. The author is confident that understanding these concepts will help you to lay a solid foundation and build a thriving career in artificial intelligence.