For newcomers to the field of artificial intelligence, prioritizing among endless AI resources can be an overwhelming challenge. This list attempts to do exactly that: it’s a carefully curated compilation of resources for getting up to speed quickly on key topics in artificial intelligence research and its long-term implications.

The list is divided into “80/20” sections with a few high-priority readings, for maximum value with minimal time investment, and “deep dive” sections for further exploration.

Readers need not be technical, nor have a prior background in artificial intelligence. The list may be of special interest to those considering entering the…


Simple, plain-English explanations accompanied by math, code, and real-world examples.

This series is available as a full-length e-book! Download here. Free for download, contributions appreciated (paypal.me/ml4h)

Roadmap

Part 1: Why Machine Learning Matters. The big picture of artificial intelligence and machine learning — past, present, and future.

Part 2.1: Supervised Learning. Learning with an answer key. Introducing linear regression, loss functions, overfitting, and gradient descent.

Part 2.2: Supervised Learning II. Two methods of classification: logistic regression and SVMs.

Part 2.3: Supervised Learning III. Non-parametric learners: k-nearest neighbors, decision trees, random forests. Introducing cross-validation, hyperparameter tuning, and ensemble models.

Part 3: Unsupervised Learning. Clustering: k-means, hierarchical. …


A compendium of resources for crafting a curriculum on artificial intelligence, machine learning, and deep learning.

This article is an addendum to the series Machine Learning for Humans 🤖👶, a guide for getting up-to-speed on machine learning concepts in 2-3 hours.

General advice on crafting a curriculum

Going to school for a formal degree program for isn’t always possible or desirable. For those considering an autodidactic alternative, this is for you.

1. Build foundations, and then specialize in areas of interest.

You can’t go deeply into every machine learning topic. There’s too much to learn, and the field is advancing rapidly. …


Exploration and exploitation. Markov decision processes. Q-learning, policy learning, and deep reinforcement learning.

This series is available as a full-length e-book! Download here. Free for download, contributions appreciated (paypal.me/ml4h)

“I just ate some chocolate for finishing the last section.”

In supervised learning, training data comes with an answer key from some godlike “supervisor”. If only life worked that way!

In reinforcement learning (RL) there’s no answer key, but your reinforcement learning agent still has to decide how to act to perform its task. In the absence of existing training data, the agent learns from experience. It collects the training examples (“this action was good, that action was bad”) through trial-and-error as it attempts its task, with the goal of maximizing long-term reward.

In…


Where, why, and how deep neural networks work. Drawing inspiration from the brain. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs). Real-world applications.

This series is available as a full-length e-book! Download here. Free for download, contributions appreciated (paypal.me/ml4h)

With deep learning, we’re still learning a function f to map input X to output Y with minimal loss on the test data, just as we’ve been doing all along. Recall our initial “problem statement” from Part 2.1 on supervised learning:

Y = f(X) + ϵTraining: machine learns f from labeled training dataTesting: machine predicts Y from unlabeled testing data

The real world is messy, so sometimes f is complicated. In natural language problems large vocabulary sizes mean lots of features. Vision…


Clustering and dimensionality reduction: k-means clustering, hierarchical clustering, principal component analysis (PCA), singular value decomposition (SVD)

This series is available as a full-length e-book! Download here. Free for download, contributions appreciated (paypal.me/ml4h)

How do you find the underlying structure of a dataset? How do you summarize it and group it most usefully? How do you effectively represent data in a compressed format? These are the goals of unsupervised learning, which is called “unsupervised” because you start with unlabeled data (there’s no Y).

The two unsupervised learning tasks we will explore are clustering the data into groups by similarity and reducing dimensionality to compress the data while maintaining its structure and usefulness.

Examples of where unsupervised learning…


Non-parametric models: k-nearest neighbors, decision trees, and random forests. Introducing cross-validation, hyperparameter tuning, and ensemble models.

This series is available as a full-length e-book! Download here. Free for download, contributions appreciated (paypal.me/ml4h)

Non-parametric learners.

Things are about to get a little… wiggly.

In contrast to the methods we’ve covered so far — linear regression, logistic regression, and SVMs where the form of the model was pre-defined — non-parametric learners do not have a model structure specified a priori. We don’t speculate about the form of the function f that we’re trying to learn before training the model, as we did previously with linear regression. Instead, the model structure is purely determined from the data.

These models are more…


Classification with logistic regression and support vector machines (SVMs).

This series is available as a full-length e-book! Download here. Free for download, contributions appreciated (paypal.me/ml4h)

Classification: predicting a label

Is this email spam or not? Is that borrower going to repay their loan? Will those users click on the ad or not? Who is that person in your Facebook picture?

Classification predicts a discrete target label Y. Classification is the problem of assigning new observations to the class to which they most likely belong, based on a classification model built from labeled training data.

The accuracy of your classifications will depend on the effectiveness of the algorithm you choose, how you apply it…


The two tasks of supervised learning: regression and classification. Linear regression, loss functions, and gradient descent.

This series is available as a full-length e-book! Download here. Free for download, contributions appreciated (paypal.me/ml4h)

How much money will we make by spending more dollars on digital advertising? Will this loan applicant pay back the loan or not? What’s going to happen to the stock market tomorrow?

In supervised learning problems, we start with a data set containing training examples with associated correct labels. For example, when learning to classify handwritten digits, a supervised learning algorithm takes thousands of pictures of handwritten digits along with labels containing the correct number each image represents. The algorithm will then learn the…


Fly free all year using credit card rewards by following this 10-minute guide

tl;dr:

  1. Sign up for a credit card with a good signup bonus (often $500+ in travel credits)
  2. Meet the minimum spending requirement within 3 months
  3. Redeem the points for free flights and hotel nights
  4. Rinse and repeat

In the two years since graduating from college, I’ve been taking free round trip flights around the world using a strategy called “churning”. A few destinations I’ve visited or will visit soon:

Florence, Italy | Puerto Vallarta, Mexico | Tokyo, Japan | Marrakech, Morocco | New York City, New York | Portland, Oregon | San Diego, California | Phoenix, Arizona (3x) | Las…

Vishal Maini

Strategy & communications @DeepMindAI. Previously @Upstart, @Yale, @TrueVenturesTEC. Views expressed here are my own.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store