How to get started with Machine Learning

Here are resources that are helping me get started with machine learning, as well as a few that I would have loved to have known about earlier. I periodically update this page with new resources. If you have good ones, let me know!

Stanford Cheat Sheets

A summary of terms, algorithms, and equations. (I barely understand the equations.=) These sheets, developed by Afshine and Shervine Amidi, differentiate between artificial intelligence (AI), machine learning (ML), and deep learning (DL), but many concepts overlap with each other. See this Venn diagram.

• CS 221 · Artificial Intelligence Cheat Sheet
• CS 229 · Machine Learning Cheat Sheet
• CS 230 · Deep Learning Cheat Sheet

Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems

I highly recommend the book I'm currently reading, written by an ex-Googler who worked on YouTube's video classification algorithm. It's dense, but it introduces you to all relevant artificial intelligence, machine learning, and deep learning concepts and guides you through preparing custom datasets to train algorithms, as well as a bit of data science, I suppose. At the same time, it introduces you to three of the most-used machine learning frameworks—Sci-Kit Learn, Keras, and TensorFlow. This is the one I started using on my day-to-day job when I became an ML Engineer, developing and releasing machine learning models for production. Similar frameworks include Caffe and PyTorch, with the latter being used by Facebook developers. (Thanks to Keith Alfaro for the recommendation.)

• Buy on Amazon Spain
• Buy on Amazon US

Books

• The Elements of Differentiable Programming by Mathieu Blondel and Vincent Roulet, both from Google Deepmind.
• Understanding Machine Learning: From Theory to Algorithms. (Recommended by Viral Thakar.)
• Regression and Other Stories. Chapter 9 covers Prediction and Bayesian inference. (Thanks to Saeran Vasanthakumar for the recommendation.)

Open-source code and tutorials

I got started with machine learning by trying open-source algorithms. It's common to visit the GitHub repository corresponding to a paper and give it a try. Two examples are Pix2Pix (2016) and EfficientDet (2020). You can try using their code as is, then attempt to use a custom dataset for training and see how the model performs for your specific needs.

TensorFlow re-writes many of these models and makes easy-to-follow tutorials.

• Pix2Pix in TensorFlow Core - Made by the Google TensorFlow team, this tutorial offers you to View the code on GitHub, Download the Jupyter Notebook (written in Python) or Run the Notebook in Google Colab (where you can press a button in the cloud and see how each piece of Python code runs to understand the different parts of setting up and training an algorithm. Reading the dataset, preparing the training and validation set, creating the model, training it, and more).
• TensorFlow tutorials - This is a good place to get your hands dirty. While machine learning has a strong theoretical component, you can leave that aside and start by training and testing models for image classification, object detection, semantic image segmentation, and a lot more tasks.

Friendly user interfaces

• Runway - A friend of mine, Cristóbal Valenzuela, is building his own machine-learning platform for creatives. It's the place for people who don't know how to code (or don't want to) to use complex machine learning models, train them with custom data, and deploy them to the cloud. Here's an interview where he told me about the beginnings of Runway.
• Machine Learning for Designers Talk - I gave a talk about these types of interfaces, a few projects, and the role they play for designers and people who don't know how to code.

Courses

• Stanford CS231n: Convolutional Neural Networks. A YouTube playlist with the entire course. Helps understand the basic operations in modern convolutional neural networks (or ConvNets). How they work; what they are useful for; and how to work with them.
• Deep Learning with PyTorch - This course, by Yann LeCun and Alfredo Canziani at NYU, concerns the latest techniques in deep learning and representation learning. (Recommended by @arafaelpastrana.)
• Practical Deep Learning for Coders - Haven't followed this course yet. But Adam Menges highly recommended it to me to get started. (Alex Huang pointed out there's also a print book that follows along with the course: Deep Learning for Coders with fastai and PyTorch: AI Applications Without a PhD.)

Tutorials & live streams

• Machine Intelligence YouTube playlist. Here is a compilation of some of the machine-intelligence-related video tutorials I've recorded.
• Live Streams YouTube playlist. Weekly hands-on coding sessions on creative coding and machine intelligence for designers. From conceptual overviews to hands-on neural network architecture, automation, training, or cloud deployment.

Other resources

• TensorFlow: Tensor and Image Basics - A video with fundamental tensor and image operations in TensorFlow. How to use tensors to encode images and matrices and visualize them.
• TensorFlow: Visualizing Convolutions - A video to visualize the filters of an image convolution, an operation known for its ability to extract image features in an unsupervised way to perform classification tasks used in convolutional neural networks.
• Awesome Machine Learning - A big and frequently-updated list of machine learning resources.
• Suggestive Drawing - This is my Harvard's masters thesis, in which I explore how the collaboration between human and artificial intelligences can enhance the design process.

Found this post helpful?

• Share it with your friends. (Short URL is nono.ma/ml.)
• Let me know of resources I should add to this page.