# What are the Pre-requisites to learn Machine Learning

Machine learning is about teaching computers how to learn from data to make decisions or predictions on their own. For true machine learning, the computer must be able to learn to identify patterns and sequences without being explicitly programmed. Machine Learning (ML) is an interdisciplinary field comprising Computer Science, Electronics and Communication, Neuroscience, Psychology, Statistics, and many more exciting fields of science. There are several applications of Machine Learning and it is meant to work well in all situations. Machine learning does require the user to have a little understanding over mathematical concepts and some programming skills. For example, integration in mathematics and Java, Python, etc. in programming, in order to understand how various algorithms function in the backdrop. Here are some Pre-requisites to learn Machine Learning:

### Mathematics

Mathematical parts like Calculus, Algebra, Statistics play an important role in shaping a person’s mind towards Machine Learning. These parts are key features in Pre-requisites to learn Machine Learning. It does not require to have an in-depth understanding of a lot of advanced mathematics to get started with Machine Learning. To gain a solid understanding of the internal working of the algorithms it is important. For instance, math concepts like differentiability and continuity are widely used in Machine Learning algorithms and learning. In most cases, particularly if you’re getting started with an entry-level ML engineer, you don’t need to do the complex math. There are many machine learning libraries in Python and R that deal with complex math like calculus and linear algebra to get the algorithms to work.

Calculus: The heart of neural networks is the backpropagation algorithm, based totally on differentiation. These features contain many multivariable, where calculi play an important role to build a machine learning model.

Statistics: A basic understanding of mean, median, and mode of various probability distributions, especially the gaussian distribution is useful. Because most of the data found in the real world can be modeled via these probability distributions. Inferential statistics can be used to get important information from a sample of data instead of using a complete dataset.

Algebra: Algebra deals with important parts like vectors, matrices, and linear transformations. Linear Algebra is an important factor because the data we deal with is not uni-dimensional.

### Programming

Programming is one of the important aspects of pre-requisites need for Machine Learning. It is essential to know programming languages like R Python, Java, etc. in order to implement the whole Machine Learning process and its learning. These languages provide in-built libraries that make it very easy to implement Machine Learning algorithms. A little bit of programming is enough like knowledge of object-oriented concepts, memory management, data structures, and algorithms. The amount of programming required depends on whether you are planning to use ML or develop new ML algorithms. And on the question, you are trying to answer using machine learning. Even non-programmers can also get a long way without even writing a single line of code. Possible because of fantastic graphical and scripting machine learning environments like Weka, BigML, Orange, Scikit-Learn, and Waffles. These platforms help with data preparation, pre-processing, configuring algorithms, running, and reviewing results.