Kaumudi SinghFollowCode Like A Girl--ListenShareMachine Learning (ML) and Artificial Intelligence (AI) — are two topics that have created much buzz around themselves in recent years. Especially since the advent of Generative AI, where users can generate new subject matter by giving appropriate directives to the AI tools, there is an AI-based app for almost everything.If you wish to write an essay, you have apps that can generate an outline or an entire article based on your directions. If you want to create or edit an image, you can find an app. A generative AI-based app is available if you want to generate quirky tag lines for your Instagram post. The bottom line is that if you look for it, you will find an AI-assisted app that will claim to help you in your endeavours.With such a booming Field, it is expected that many of you would wish to contribute to it. Now, contributing to the field of ML and AI has multiple avenues. You can either use the existing methodologies and algorithms and apply them to solve old and new problems. This will require a good understanding of the problem and the available solution(s), if any.This will be akin to taking the accelerometer (which measures the acceleration of an object in three-dimensional space) and placing it in your fitness band to count the number of steps you have taken. Accelerometers were available for a very long time. But one day, someone decided to use them to count the steps taken by a person, and it opened up a whole new dimension of possibilities.Nonetheless, you can also contribute to the field of Machine Learning and AI by working at a more fundamental level and developing new methodologies and algorithms. These algorithms can then be used to solve real-world problems. In our fitness band analogy, this will correspond to developing new and efficient accelerometers.If you would like to study and work in the field of Machine Learning and Artificial Intelligence and are looking for resources on how to get started (or you have just started), plenty of online resources can help you. Full-fledged courses from top universities and instructors are available online (read YouTube), absolutely free of cost. All you have to do is search, and you are likely to find something that suits you — from a very basic introduction to the field to highly detailed courses.However, before you dive head-first into these lessons with all your energy, I urge you to take a step back and pay attention to the prerequisites, which can be easily overlooked. If you plan to take an introductory course in Machine Learning and AI, basic knowledge about the three elementary fields will help you better comprehend all the math and logic behind the different algorithms that you’ll be learning in your course.These three elementary fields are:ML and AI algorithms draw heavily from different ideas in these three fields. The different aspects of developing, training, and deploying an AI algorithm utilize one or many concepts from these fields. So, informing yourselves about the basics of these fields will benefit you when you begin your AI journey.Where do I even begin with this subject matter? Linear algebra deals with expressing a (set of) problem(s) in terms of vectors and matrices. These vectors and matrices are then manipulated to solve the said (set of) problem(s). Knowledge of this basic building block can aid your comprehension of many scientific and technological fields, Machine Learning and AI included.Everything in Machine Learning and AI is expressed in vectors and matrices. Everything is represented as matrices From how inputs and outputs are described to the description of different features of the inputs. Additionally, calculations in neural networks depend heavily on matrix multiplications.So understanding how these matrices can be best manipulated and exploited for your cause will help you go the extra mile quite easily when studying and working with the different ML and AI algorithms.The best part is that plenty of online study materials can help you learn the basics of Linear Algebra. The most famous one is the Lecture Series by Prof. Gilbert Strang. Another great introduction to the field is the Lecture Series by Prof. Vittal Rao. Both these courses are extremely easy to follow while being quite detailed about the subject matter.Probability and probability distributions deal with quantifying how likely an event is. This is another one of those primary mathematical fields utilized almost everywhere, and you’ll never be at any loss knowing the basics.Everything a Machine Learning algorithm or a Neural Network detects or predicts is ambiguous. You’ll always come across statements like — the algorithm predicts the outcome with 85% accuracy. The algorithm will produce the correct outcome 85 out of 100 times. Probability theory can equip you with mechanisms to calculate this metric.Suppose you are studying an algorithm and testing it for different applications or designing a new algorithm. In that case, familiarity with the concept of probability and probability distribution will help you better judge the capabilities of the algorithms and their outputs.Again, learning the basics of probability is quite accessible. Online lectures can come to your rescue. Lectures from MIT OpenCourseWare and NPTEL can be utilized to learn probability and probability distributions.The field of optimization consists of a group of algorithms that help you reach the best solution to your problem within the restrictions put in place on your desired solution.It must be trained before a Machine Learning algorithm or a Neural Network can be applied to solve a problem. While training, sample inputs are fed into the algorithm so that the algorithm can learn its task. So, if the algorithm is used to distinguish spam mail from regular mail, samples of both spam and regular mail will be fed into the algorithm. The algorithm will then fine-tune itself based on the inputs to reach a setting that allows it to categorize the mail efficiently. To reach this setting, the algorithm starts with an initial setting and then adjusts it to maximize the amount of spam mail it detects correctly.To achieve this, different optimization algorithms are employed. The gradient descent algorithm is the most commonly used algorithm for this purpose. Nonetheless, knowledge of the general idea of optimization, the associated algorithms, and their shortcomings will aid in your holistic understanding of ML and AI.Moreover, when developing your own algorithm, knowledge of the different optimization algorithms will allow you to make a more informed decision regarding what fits your algorithm the best.As before, tons of online materials can help you with the subject. Lectures from Stanford and KIT are available online to help you start with the topic.Please understand that when I say these three topics are prerequisites for Machine Learning and AI, I by no means imply that you can only start working in the field after learning these prerequisites. You most definitely can. However, topics from these prerequisite subjects will come up during your studies. To grasp all the ML and AI concepts, I would highly recommend familiarizing yourself with the basics of these prerequisites, at the very least.With an introduction to these three fundamental fields, you’ll face little to no difficulty figuring out the inner workings of an ML or AI algorithm. Therefore, I hope you take some time to understand the basics of these three principle fields.And with that last note, I take your leave, extending all my best wishes for your exploration of the Machine Learning and Artificial Intelligence field.----Code Like A GirlTechnology enthusiast who is addicted to travel, books, and life in general. Find me at https://www.linkedin.com/in/kaumudi-singh-457b538b/Kaumudi SinghinDigital Global Traveler--1ayşe bilge gündüzinCode Like A Girl--4Python Code NemesisinCode Like A Girl--Kaumudi SinghinReaders Hope--4Jude Ellison S. Doyle--219AL Anany--78Stephen BarrinThe Modern Scientist--80Stephan JoppichinBooks Are Our Superpower--67Kim Witten, PhD--161Devon Price--19HelpStatusWritersBlogCareersPrivacyTermsAboutText to speechTeams