By Rachael Tatman – 17 min read
One question I get fairly often from folks who are just getting into NLP is how to evaluate systems when the output of that system is text, rather than some sort of classification of the input text.
The Poisson Distribution and Poisson Process Explained
By Will Koehrsen – 14 min read
A tragedy of statistics in most schools is how dull it’s made. Teachers spend hours wading through derivations, equations, and theorems, and, when you finally get to the best part – applying concepts to actual numbers – it’s with irrelevant, unimaginative examples like rolling dice.
Understanding Convolutional Neural Networks through Visualizations in PyTorch
By Vihar Kurama – 11 min read
In the present era, machines have successfully achieved 99% accuracy in understanding, identifying the features and objects in the images. We see them daily, to quote a few, smartphones recognizing faces in the camera, ability to search particular photos in google photos, scanning text from the barcode or books at a good pace etc.
Quality over quantity: building the perfect data science project
By Jeremie Harris – 7 min read
In startup lingo, a "vanity metric" is a number that companies keep track of in order to convince the world – and sometimes themselves – that they’re doing better than they actually are.
How to visualize convolutional features in 40 lines of code
By Fabio M. Graetz – 18 min read
Recently, while reading Jeremy Rifkin’s book "The End of Work", I came across an interesting definition of AI. Rifkin writes: "today when scientists talk of artificial intelligence, they generally mean ‘the art of creating machines that perform functions which require intelligence when performed by people.’
How to do Deep Learning on Graphs with Graph Convolutional Networks (Part 1, Part 2)
By Tobias Skovgaard Jepsen – 9 min read
Machine learning on graphs is a difficult task due to the highly complex, but also informative graph structure. This post is the first in a series on how to do deep learning on graphs with Graph Convolutional Networks (GCNs), a powerful type of neural network designed to work directly on graphs and leverage their structural information.
Deep Learning Vision for Non-Vision Tasks
By Max Pechyonkin – 7 min read
In recent years, deep learning has revolutionized computer vision. And thanks to transfer learning and amazing learning resources, anyone can start getting state of the art results within days and even hours, by using a pre-trained model and adapting it to your domain.
Mastering the Data Science Interview Loop
By Andrei Lyskov – 12 min read
In 2012, Harvard Business Review announced that Data Science will be the sexiest job of the 21st Century. Since then, the hype around data science has only grown. Recent reports have shown that demand for data scientists far exceeds the supply.
Automating project management with deep learning
By Euan Wielewski – 10 min read
In the data-driven future of project management, project managers will be augmented by artificial intelligence that can highlight project risks, determine the optimal allocation of resources and automate project management tasks.
Attn: Illustrated Attention
By Raimi Karim – 12 min read
For decades, Statistical Machine Translation has been the dominant translation model, until the birth of Neural Machine Translation (NMT). NMT is an emerging approach to machine translation that attempts to build and train a single, large neural network that reads an input text and outputs a translation