# Introduction to the Course

Get a basic understanding of the course, its prerequisites, and its target audience.

## We'll cover the following

## What is machine learning?

**Machine learning** is a field of study that is dedicated to building software that can learn to perform specific tasks. Examples of common tasks for machine learning are recognizing objects from digital pictures or predicting the location of a robot or a self-driving car from a variety of sensor measurements. These techniques have contributed largely to a new wave of technologies that are commonly associated with artificial intelligence (AI). This course is dedicated to introducing the fundamentals of this discipline.

Machine learning is exploding, both in research and industrial applications. Although many of the machine learning ideas have been around for many years, the latest breakthroughs are based on the following two advancements:

- The availability of large datasets with labeled data.
- The availability of fast specialized processors such as graphics processing units $\text{(GPUs)}$.

In addition, progress is fueled by a deeper understanding of building models and learning from data as well as some new techniques that brought everything together.

## Course Overview

This course focuses on the following:

- General machine learning methods
- Probabilistic modeling
- Balancing the rigor of mathematical arguments
- The principle ideas behind machine learning
- Kernel methods and Lagrange methods for optimizations with constraints
- Support vector machines
- Multilayer perceptron
- Convolutional neural networks
- Object detection
- Linear regression
- Artificial neural networks
- Random numbers and density functions
- Probabilistic models
- Generative models
- Sequence processing
- Natural language processing
- Recurrent neural networks
- Decision trees

Throughout this course, we’ve kept explanations brief while still providing some ideas about the deeper reasoning behind the methods. We’ve used mathematical notation mainly as descriptors to keep presentations brief and to show the general form of some equations.

For the most part, this course does not include rigorous mathematical proofs or derivations, but we hope to provide enough details for you to see how results can be derived. We’ve kept design and treatments brief intentionally and hope to motivate you to consult further courses for advanced studies.

## Prerequisites and target audience

You should have a working knowledge of * Python* and be familiar with the mathematical notations and norms of modeling. You should also have a prior understanding of calculus, linear algebra, and statistics.
This course’s target audience is beginners who are eager to pursue a career in machine learning.