In the last blog we tried to understand what is Machine learning. Today we will look at how a typical workflow in applied AI/ML looks like. A typical workflow in applied Machine Learning can be broken down into following high-level steps:
Problem Statement Data Collection Data Pre-processing Data Analysis & Modelling Evaluation Let’s look at each workflow item in a bit more detail.
Problem Statement Definition of a clear and concise problem statement is essential to ensure solution is focused towards solving the identified problem.
What is Machine Learning We touched on the definition in the last post. Let’s expand on this, so machine learning is a process of teaching computers to perform actions which they are not explicitly programmed to perform. Simple put, machine learning is a method of teaching computers to learn from data and improve at performing specific tasks.
There are mainly three types of machine learning:
Supervised Learning Unsupervised Learning Reinforcement Learning Let’s delve into the first two types:
Introduction Hi there, welcome to a series on Artificial Intelligence and Machine Learning. AI/ML is now starting to become big in the tech industry with involvement from various big players such as Amazon, Google, Microsoft. And there are multiple terms such Generative AI, RAG, Tranformers and so on which are confusing and may lead to misunderstanding. This series is an attempt to provide a high-level view of:
terms used within AI/ML space introduction to AI/ML what are the different models used in AI/ML and for what purpose latest trends within AI/ML space and a few more 😊 I like the definition shared by IBM for AI/ML.