What order should I take your courses in?



Welcome to the "Lazy Programmer Course Order" page!

When it comes to learning data science and machine learning, there is no “one size fits all” solution. Different people have different goals and different ways of learning.

So, for those of you who’ve asked me, “what order should I take your courses in?”, the answer is: it depends!

Are you interested in computer vision, or NLP? Are you interested in reinforcement learning and control for academic applications / robotics, or supervised learning for business applications? Do you prefer a “first principles” approach, or do you like to dive right in and use state-of-the-art tools in just one line of code?

What is the right choice? The right one is the one you choose. Are you ready?

Choose your own adventure:



I’m interested in deep learning, and I want to know how it really works. I'm not afraid of backpropagation or coding, and I have a strong STEM background. I want a deep-dive into every area where deep learning is applied, like NLP, computer vision, reinforcement learning, and recommender systems. I want a detailed understanding of modern deep learning libraries like Tensorflow 2 and PyTorch.
I’m interested in deep learning, but math is not for me and I want to write as little code as possible. I want to apply deep learning as quickly as possible to applications like NLP, computer vision, reinforcement learning, GANs, and recommender systems.
I’m interested in machine learning and data science for business applications, like recommender systems, online advertising, and online marketing. I want to maximize click-through rates and conversion rates.
I want to learn reinforcement learning and control. I want to build agents to solve mazes and play video games like Atari and Super Mario. I'm interested in robotics.
I want to learn computer vision and teach machines to understand what they see in the world. I want to build applications for image classification, facial recognition, object detection, image segmentation, super-resolution, image generation, and style transfer. I'm interested in how machines can generate art, and I'm curious about technologies like GANs, diffusion models, and DALL-E 2.
I want to learn NLP (natural language processing), sequence models, and transformers. I want to build applications for text classification, spam detection, sentiment analysis, topic modeling, article spinning, document clustering, information retrieval, latent semantic indexing, text generation, language translation, text summarization, and question-answering. I'm curious about technologies like BERT, GPT-3, and ChatGPT.
I want to know all about Bayesian machine learning and Bayesian statistics. Bayesian is better.
I’m interested in applying machine learning and artificial intelligence to time series analysis, financial analysis, and algorithmic trading.
I want to learn all the algorithms from a “typical” machine learning course, like k-means clustering, naive bayes, PCA, kernel methods, decision trees, and boosting.
I don't meet the math and programming prerequisites for STEM subjects. I need to learn calculus, linear algebra, probability, Python, and other fundamentals.
I just want to learn it all!
This website is using cookies. That's Fine