You got intrigued by the machine learning world and wanted to get started as soon as possible, read all the articles, watched all the videos, but still isn’t sure about where to start, welcome to the club. Before we dive into the machine learning world, you should take a step back and think, what is stopping you from getting started? If you think about it, most of the time, we presuppose things about ourselves and assume that to be true without question. The most normal presumption that we make about ourselves is that we need to have prior knowledge before getting started. Get a degree, complete a course, or have a good understanding of a particular subject. The truth is that most of the time, this is a lie, the prior knowledge you think you need is most of the time not required or is so big that even experts from the field don’t fully understand it. The Seek of this prior knowledge is a trap that will make you run in circles, which leads us to the next presumption. The perfect condition, you can’t wait for the ideal environment or situation to get started, things will never be 100% ready, try and fail, then try again. It takes a lot of time to get good at machine learning; you won’t learn all at once and especially at the beginning. Instead of trying to acknowledge everything before getting started, do a little bit every day; you can make significant progress by creating small things every day for a considerable amount of time. The perfect condition will never exist, do it in your path, be consistent with it, and the results will come. After you start making little progress every day, you probably will end up having a struggle with something or failing to achieve your goal at a certain point. This feeling is tough; it’s hard to see yourself not making any progress, not having any sense of gratification, and then still not give up. Machine learning is hard, it might take you a few weeks, months or even years to see progress in a certain point but isn’t any harder than any other technical skill, it requires repetition and dedication to get where you want, you need to test it, make a mistake and learn from it. Never compare yourself with other people that are also learning with you or that you admire; instead, compare yourself with your past self and look at the progress that you have made, who you were five years ago? I bet you have changed a lot. Your Machine Learning Now you have your mindset on point and are ready to start, but you still are confused about what machine learning is. There’s a good reason to be confused, machine learning has a large field of study, but a lot of that won’t be relevant to you if you’re focused on solving a problem. , 1997. The field of machine learning is concerned with the question of how to construct computer programs that automatically improve with experience. — Machine Learning This is too broad. Just think about it. Machine learning is a broad field that can help you solve specific problems, but you don’t need to know about all of it. Think about machine learning as a tool, think in terms of the problem you’re trying to solve, and the solution you require. To do that, try to describe your problem in the most descriptive way: Find a model or procedure that makes the best use of historical data comprised of inputs and outputs to skillfully predict outputs given new and unseen inputs in the future. A clear description of the problem you’re trying to solve will discard entire sub-fields of machine learning, give you a clear objective that dominates all others, and probably will provide you with a frame that fits neatly into a field of machine learning. This practice will allow you to filter the material you read and the tools you choose to stay focused on the problem you’re trying to solve. The best solution to the problem above is described as the following: A model or procedure that automatically creates the most likely approximation of the unknown underlying relationship between inputs and associated outputs in historical data. having a definitive answer to the problem helps you see the ill-defined nature of the predictive modeling problem you’re trying to solve and sets reasonable expectations. Learn How To Learn Try to remember about your years in middle/high school and take a field of study like mathematics. Think about how the material was laid out, week-by-week, semester-by-semester, year-by-year. There was a logical way to layout the topics that build on each other and lead through a natural progression in skills, capability, and understanding. The problem is, this logical progression might only make sense to those who are already on the other side and know how to connect the dots between the topics, and also the logical progression through the material may not be the best and productive way to learn. This learning approach is not just a common way of teaching technical topics; it looks like the only way, at least until you think about how you learn. How did you learn to read? How did you learn to speak? How did you learn to Drive? If you stop and think about it, almost all of the things that you learned and are valuable to you were not through this process of logical progression. We are emotional humans that need motivation, interest, attention, encouragement, and results to learn something new. Don’t start learning from the very beginning. Instead, start by connecting the dots of the subjects you have an interest in with the results you want and learn how to get there fast. Create your program that focuses on getting results, going deeper into some areas as needed, but always in the context of getting the results you want. It might have poor results in the beginning but it improves with practice. That is, by far, my favorite technique to learn something new and can be applied in any field. Instead of trying to learn everything at once, just then to start working on what you want, start working on what you want right away and figure out what you need to learn to make it work out. The benefits of learning this way surpass the challenge of learning itself. You go straight to the thing you want and start practicing it. You gain a better context and motivation to learn the hard stuff, and you can quickly shift and filter topics based on your goals in the subject. It’s faster and more fun, and believe me; no one can beat the person who has fun working. The subject will be connected with you emotionally. You have attached it to an outcome or result that matters to you, and all that drives motivation, enthusiasm, and passion. “The one who has fun working will outperform all their competitors.” Learn Machine Learning Based on our learning approach above, don’t start to learn machine learning with precursor math, machine learning theory, or coding every algorithm from scratch. Instead, choose a straightforward problem that you want to solve using simple machine learning. After choosing a problem, figure out what you need to know to resolve this problem and apply it immediately without fearing failure, remember that almost everything you learned, you learned by practicing it and not reading the theory. The goal is to provide the context, and you can let your curiosity define the depth of study. Questions? If you’ve got any further questions, leave a response, or feel free to . email me This article was originally posted on . my website

Read My Stories

Too Long; Didn't Read

Make resilience your competitive advantage

How To Get Started With Machine Learning With The Right Mindset

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

Untitled Story

7 Competition-Killing Ways To Use Machine Learning for Ecommerce Brands

9 Applications of AI and ML in Commerce, Analytics, and More

Artificial Intelligence and Machine Learning: A Significant Game Changer in Healthcare

Context Matters in Semantic Ambiguity

Date and Time Values are a Mess - Here's Why

7 Competition-Killing Ways To Use Machine Learning for Ecommerce Brands

9 Applications of AI and ML in Commerce, Analytics, and More

Artificial Intelligence and Machine Learning: A Significant Game Changer in Healthcare

Context Matters in Semantic Ambiguity

Date and Time Values are a Mess - Here's Why

Light-Mode

Classic

Newspaper

Dark-Mode

Neon Noir

Minty

HN StartUps