![\"\"](\"https:\/\/cdn.midjourney.com\/802497e3-5b63-4bba-b789-4f314f502cfc\/0_1.webp\")
\nSo, your aim is to dive into AI studies? Yet you are unsure about how or where to begin?<\/p>\n
\nSo, your aim is to dive into AI studies? Yet you are unsure about how or where to begin?<\/p>\n
In 2020, I shared a list of the Top 20 free Data Science, ML, and AI MOOCs available online<\/a>. However, I have come to realize that enrolling in numerous courses is not the most effective approach.<\/p>\n To break free from the cycle of endless tutorials and truly gain expertise, you need to engage in practical applications, develop algorithms from scratch, implement research papers, and undertake engaging AI projects to solve real-world issues.<\/p>\n This piece endeavors to create a complimentary<\/strong> curriculum that aligns with this ideology. I am actively pursuing some of these courses, hence feel free to get in touch<\/strong><\/a> on Twitter<\/strong><\/a> or Linkedin<\/strong><\/a> if you wish to learn alongside me!<\/p>\n Moreover, please drop a comment if you identify any omissions!<\/p>\n Before delving into specifics, there are certain insights to consider regarding the curriculum and some guidance on the learning process.<\/p>\n This curriculum adopts a top-down methodology \u2014 initially focus on coding, theory later<\/strong>.<\/p>\n I prefer learning out of necessity<\/strong>. Whenever there is a problem to address, a solution to devise, or a prototype to construct, I will extensively search for the essential information, comprehend it, and subsequently act upon it.<\/p>\n For instance, my ambition is to evolve into an AI engineer<\/a> well-versed in LLMs at a foundational level. This entails the ability to code transformers from the ground up and fine-tune LLMs on GPUs. Currently, I lack this proficiency due to gaps in my knowledge, which I am determined to bridge.<\/p>\n This curriculum primarily focuses on NLP; if you are interested in other AI specializations like computer vision or reinforcement learning, drop a comment below or directly message me on Twitter<\/strong><\/a> or Linkedin<\/strong><\/a>. I will provide you with some recommended resources.<\/p>\n Prior to inundating you with a plethora of links, I wish someone had emphasized two critical aspects<\/strong> I should have been aware of before embarking on the learning journey.<\/p>\n The realm of knowledge is vast and continuous learning is imperative, especially in the field of AI where groundbreaking research and concepts emerge on a weekly basis.<\/p>\n The gravest mistake one can make is to confine learning to private spheres. By doing so, you limit opportunities for growth. Mere completion of tasks lacks significance. What holds greater value is how you assimilate the information, transform it into knowledge for dissemination, and conceive innovative solutions and ideas based on that knowledge.<\/p>\n Hence, it is vital to educate in a public space<\/strong><\/a>.<\/p>\n This can entail:<\/p>\n Moreover, when it comes to Twitter,<\/p>\n When used effectively and in accordance with the right individuals, Twitter proves to be the most valuable social platform in contemporary times.<\/p>\n Whom to follow<\/strong>? Check out this curated AI list by Suhail<\/a>.<\/p>\n Utilizing Twitter<\/strong>? Refer to Near’s guide on Effective Twitter Practices<\/a>.<\/p>\n Reach out to individuals on Twitter. Be genuine, concise, and articulate your requirements clearly. This guide on Crafting Cold Emails<\/a> by Sriram Krishnan is also applicable to Direct Messages.<\/p>\n Tweet Composition?<\/strong> Refer to Elements of a Tweet<\/a> by Jason<\/a>, the developer of Instructor<\/a>, who accumulated 14k followers within months.<\/p>\n If you are perusing this article, do follow me on Twitter<\/strong><\/a>!<\/p>\n Contact me<\/strong><\/a> regarding your ongoing projects! Collaboration on intriguing endeavors always piques my interest.<\/p>\n Let’s now delve into the details.<\/p>\n DALL\u00b7E<\/p>\n Machine learning heavily relies on three core mathematical pillars: linear algebra, calculus, as well as probability and statistics. Each of these elements plays an essential role in facilitating the optimal performance of algorithms.<\/p>\n A phenomenal series on Math for Machine Learning from a developer’s viewpoint can be explored here<\/strong><\/a> by Weights & Biases.<\/p>\n source code<\/a>)<\/p>\n If you prefer a code-centric approach to Linear Algebra, explore Computational Linear Algebra<\/strong><\/a> (video series<\/a>, source code<\/a>) shared by the developers of fast.ai.<\/p>\n Follow Introduction to Linear Algebra for Applied Machine Learning with Python<\/strong><\/a> in parallel with the course.<\/p>\n If you desire a more conventional approach, check out the lectures at Imperial College London<\/strong> \u2014 Linear Algebra<\/a> & Multivariate Calculus<\/a>.<\/p>\n View 3Blue1Brown\u2019s Essence of Linear Algebra<\/strong><\/a> and Essence of Calculus<\/strong><\/a>.<\/p>\n Observe Statistics Fundamentals<\/strong><\/a> by StatQuest for statistics<\/p>\n Additional Resources<\/strong><\/p>\n DALL\u00b7E<\/p>\n Beginners can start here: Practical Python Programming<\/strong><\/a>.<\/p>\n If you are already adept in Python, consider Advanced Python Mastery<\/strong><\/a><\/p>\n Both are exceptional courses from David Beazley, the creator of Python Cookbook.<\/p>\n Next, delve into James Powell\u2019s<\/strong> presentations<\/a><\/p>\n Explore Python Design Patterns<\/a>.<\/p>\n Additional Resources<\/strong><\/p>\n Watch PyTorch Tutorials<\/a> by Aladdin Persson<\/a><\/p>\n The PyTorch website offers valuable content.<\/p>\n Challenge yourself with some puzzles<\/p>\n Additional Resources<\/strong><\/p>\n DALL\u00b7E<\/p>\n Refer to the 100-page ML<\/a> book.<\/p>\n While studying, implement the algorithms from scratch.<\/p>\n Check out the repositories listed below<\/p>\n For a challenging task, build PyTorch from scratch by following this course.<\/p>\n Apply your knowledge in competitive scenarios.<\/p>\n Explore Bringing machine learning to production<\/a> by Vicki Boykis<\/p>\n She also documented her experience building Viberary<\/a>, a semantic book search engine.<\/p>\n Obtain a dataset and develop a model (e.g., leverage earthaccess<\/a> for NASA Earth data).<\/p>\n Construct a user interface using streamlit<\/a> and share it on Twitter.<\/p>\n Put the models into production. Track your experiments. Learn to monitor models. Experience data and model drift firsthand.<\/p>\n Explore these valuable resources<\/p>\n For those interested in a top-down approach, begin with fast.ai.<\/p>\n If you enjoyed fast.ai, explore Full Stack Deep Learning<\/a>.<\/p>\n For a more in-depth and conventional course, consider checking out UNIGE 14×050 \u2014 Deep Learning<\/a> by Fran\u00e7ois Fleuret<\/a>.<\/p>\n If you need to delve into theory later on, these are excellent resources.<\/p>\n<\/span><\/a>Starting from the Top-down<\/h1>\n
<\/span><\/a>Educating in a Public Domain<\/h1>\n
\n
<\/span><\/a>Employing Twitter as a Tool<\/h1>\n
<\/span><\/a>Contents Overview<\/h1>\n
\n
\n\u2218 Python<\/a>
\n\u2218 PyTorch<\/li>\n
\n\u2218 Creating Algorithms from Scratch<\/a>
\n\u2218 Participation in Competitions<\/a>
\n\u2218 Execution of Side Projects<\/a>
\n\u2218 Deployment of Projects<\/a>
\n\u2218 Supplementary Materials<\/a><\/li>\n
\n\u2218 Fast.ai<\/a>
\n\u2218 Involvement in More Competitions<\/a>
\n\u2218 Implementation of Research Papers<\/a>
\n\u2218 Exploring Computer Vision<\/a>
\n\u2218 Diving into NLP<\/a><\/li>\n
\n\u2218 Watching Neural Networks: Zero to Hero<\/a>
\n\u2218 Participating in a Free LLM Boot Camp<\/a>
\n\u2218 Creating Projects with LLMs<\/a>
\n\u2218 Engaging in Hackathons<\/a>
\n\u2218 Exploring Research Papers<\/a>
\n\u2218 Developing Transformers from Scratch<\/a>
\n\u2218 Suggested Blog Reads<\/a>
\n\u2218 Viewing Umar Jamil’s Work<\/a>
\n\u2218 Learning to Operate Open-source Models<\/a>
\n\u2218 Prompt Engineering Techniques<\/a>
\n\u2218 Fine-tuning LLMs<\/a>
\n\u2218 Research about RAG<\/a><\/li>\n<\/span><\/a>Foundations in Mathematics<\/h1>\n
![\"\"](\"https:\/\/cdn.midjourney.com\/b4d2dff1-ba97-43f8-9658-24987cb408a3\/0_0.webp\")
<\/p>\n\n
\n
<\/span><\/a>Resources<\/h1>\n
![\"\"](\"https:\/\/cdn.midjourney.com\/a2f650c2-d452-4d76-b506-6f26c9845d8c\/0_0.webp\")
<\/p>\n<\/span><\/a>Python<\/h2>\n
\n
<\/span><\/a>PyTorch<\/h2>\n
\n
\n
\n
<\/span><\/a>Machine Learning<\/h1>\n
![\"\"](\"https:\/\/cdn.midjourney.com\/6c6f3332-a0b2-4ce7-a474-42ad8068ac43\/0_3.webp\")
<\/p>\n<\/span><\/a>Develop from Scratch<\/h2>\n
\n
\n
<\/span><\/a>Participate in Competitions<\/h2>\n
\n
<\/span><\/a>Engage in Side Projects<\/strong><\/h2>\n
<\/span><\/a>Deploy the Models<\/h2>\n
\n
<\/span><\/a>Additional Resources<\/h2>\n
\n
<\/span><\/a>Deep Learning<\/h1>\n
![\"\"](\"https:\/\/cdn.midjourney.com\/309c3b6c-52ec-4ad6-8bfd-fac1976b5b1c\/0_0.webp\")
<\/p>\n<\/span><\/a>Fast.ai<\/h2>\n
\n
\n