MACHINE LEARNING FULL COURSE

MODULE 1

 MACHINE LEARNING

Machine Learning (Ml) is a modern software development technique that enables computers to solve  problems by using examples of real world data.

 
Introduction To Machine Learning

There are several changes happening across all areas of societies which involve how to use machine leaning (ML) to solve a problem. Some examples of these areas are;

• Recent advancement in industries such as autonomous vehicles.
• Accurate and rapid translation of the text into hundreds of languages
• AI assistants that might  find in your home
• Work safety improvements
• quicker pharmaceutical design and development.

what is machine leaning?

machine learning is part of the broader field of artificial intelligence. within machine learning there are several  different kinds of tasks of techniques which include;

in supervised learning->every training sample from the dataset has a corresponding label  or output values we will explore more in depth in this module

in unsupervised learning->there are no labels for the training data. A machine learning algorithm tries to learn the underlying pattern or distributions that govern the data . we will explore this in depth in this module

in reinforcement learning->the algorithm figures out which actions to take in a situation to maximize a reward (in the form of a number) on the way to reaching a specific goal. This is a completely different approach than supervised and unsupervised learning. We will dive deep into this in next lesson.

how machine learning different

in traditional problem solving with software, a person analyzes a problem and engineers a solution in code to solve that problem. For many real world problems, this process can be laborious(or even impossible) because a correct solution would need to take a vast number of edge cases into considerations.

in a way machine learning automates some of the statistical reasoning and pattern matching the problem solver would traditionally do.

The overall goal is to use model created by a model training algorithm to generate predictions ir find patterns in data that can be used to solve a problem.

key terms and most common techniques used to solve problems in Ml

Model->a model is an extremely generic program (or block of code), made specific by the data used  to train it. it is used to solve different problems.

Model training ->algorithm work through an interactive process where the current model iteration is analyzed to determine what changes can be made to get closer to goal. Those changes are made and the iteration continues untill thwe model is evaluated to meet the goals.

Model inference->This is when the trained model is usedto generate predictions.