Tagged in

Machine Learning


Are Linear Models *Actually* “Easily Interpretable”?

I originally published this blog post on LinkedIn.

An oft-repeated meme in data science circles is that linear models can sometimes be preferable to other machine learning methods because they’re “easily…


Using simple instance to understand the backward propagation (Part I)

John D. Carmack II (twitter @John Carmack), the legendary programmer posted an article on Facebook several months ago about how he managed to implement neural network from scratch in C++. Just like what he…


TensorflowJS — Hello World

What is TensorflowJS ?

A WebGL accelerated, browser based JavaScript library for training and deploying ML models.

Yesterday Google announced TensorflowJS which is a JavaScript library to implement Machine Learning in the browser…


Training on MNIST dataset with TensorFlow Dataset, Estimator and Slim APIs — Part 4

In the previous posts, we built the input and model functions for our TensorFlow estimator. Now, its time to put everything together and run an experiment on the MNIST dataset. The code…


​Strengthening African ​Machine Learning

The Deep Learning Indaba has two principal aims: to increase African participation and contribution to the advances in artificial intelligence and machine learning, and address issues of diversity in these fields of science.


Global Data Science conference, Santa Clara

I will be speaking at the event organized by the Global Big Data Conference, on Wednesday 4th April. The talk will be on trends in Visualizing Machine learning with a walkthrough of some case studies.

This story is unavailable.

Very interesting read Danilo Pena. To be honest, I had no idea there was such an approach to get heartbeat data from accelerometers. I would love to hear more from the project as my first impression when reading was that the data can be pretty innacurate. Needless to say that the way the phone is carried bye the subject can drastically lead to very…