The world’s leading publication for data science, AI, and ML professionals.

Weekly Selection

Why Prediction is the Essence of Intelligence

By Peter Sweeney— 10 min read.

Is it a coincidence that machine learning and intelligence are both rooted in prediction? Are we approaching a momentous juncture when our technology embodies the essence of intelligence? Or is this yet another chapter in a long history of misconceptions? And if it is indeed the essence, in a system of many components, what elevates prediction above the rest?


Redefining Basketball Positions with Unsupervised Learning

By Evan Baker – 8 min read.

The NBA Finals are over. The last of the champagne bottles have been emptied and the confetti has begun to settle. Now that the Golden State Warriors have finished unleashing their otherworldly dominance on the basketball world, I thought it would be a good time to wrap up a hardwood-focused machine learning project.


Multi-Layer Neural Networks with Sigmoid Function – Deep Learning for Rookies 1 and 2.

By Nahua Kang – 21 and 15 min read.

Last time, we introduced the field of Deep Learning and examined a simple a neural network – perceptron……or a dinosaur……ok, seriously, a single-layer perceptron. We also examined how a perceptron network process the input data we feed in and returns an output.


A Pickup Line Generator with Tensorflow

By Andrew Pierno – 5 min read.

I saw an article a few months ago about someone who created a pickup line generator. Since I’m just starting out in the world of deep learning, I’ve been thinking of fun projects that would at least provide me with entertainment while I learn. A terrible pickup line generator sounded like magic.


6 ways people are making money with machine learning

By Aaron Edell – 5 min read.

Machine learning is definitely VERY cool, much like virtual reality or a touch bar on your keyboard. But there is a big difference between cool and useful. For me, something is useful if it solves a problem, saves me time, or saves me money. Usually, those three things are connected, and relate to a grander idea; Return on Investment.


About choosing your optimization algorithm carefully

By Michael Green – 6 min read.

Why is simulation important anyway? Well, first off we need it since many phenomena (I would even say all interesting phenomena) cannot be encapsulated by a closed form mathematical expression which is basically what you can do with a pen and paper or a mathematical software.


Introducing PDPbox

By SauceCat – 6 min read.

PDPbox is a partial dependence plot toolbox written in Python. The goal is to visualize the impact of certain features towards model prediction for any supervised learning algorithm. (now support all scikit-learn algorithms)


Sequence to sequence model: Introduction and concepts

By Manish Chablani – 3 min read.

We use embedding, so we have to first compile a "vocabulary" list containing all the words we want our model to be able to use or read. The model inputs will have to be tensors containing the IDs of the words in the sequence.


Generative Adversarial Networks- History and Overview

By Kiran Sudhir – 12 min read.

Of late, generative modeling has seen a rise in popularity. In particular, a relatively recent model called Generative Adversarial Networks or GANs introduced by Ian Goodfellow et al.


Related Articles