Our Favorite Posts Of Last Week (Jan 06, 2019)

How to code The Transformer in Pytorch

Could The Transformer be another nail in the coffin for RNNs? Doing away with the clunky for loops, it finds a way to allow whole sentences to simultaneously enter the network in batches. The miracle is that Natural Language Processing (NLP) can then reclaim the advantage of python’s highly efficient linear algebra libraries.
Link: https://towardsdatascience.com/how-to-code-the-transformer-in-pytorch-24db27c8f9ec
Word Count: 2925

100+ Google Sheets Templates

Looking to up your marketing game? Grab copies of over 100 Google Sheets marketing templates & automation tools. So you work in marketing. Regardless of your position, you are going to spend a good chunk of your time in spreadsheets.
Link: https://sheetsformarketers.com/google-sheets-templates/
Word Count: 221

Google’s Mueller spend New Year’s helping SEOs tackle hacked content, slow website issues

John Mueller, a Google webmaster trends analyst, spent a portion of his New Years break responding to concerns and questions around Google search related issues. Here’s what kept him occupied. Slow server leads to crawling and indexing issues.
Link: https://searchengineland.com/googles-mueller-spend-new-years-helping-seos-tackle-hacked-content-slow-website-issues-309934
Word Count: 568

Time Series Prediction Using LSTM Deep Neural Networks

This article focuses on using a Deep LSTM Neural Network architecture to provide multidimensional time series forecasting using Keras and Tensorflow - specifically on stock market datasets to provide momentum indicators of stock price.
Link: https://www.altumintelligence.com/articles/a/Time-Series-Prediction-Using-LSTM-Deep-Neural-Networks
Word Count: 3955

How to Display Steppers on Mobile Forms

When your form has multiple pages, a stepper is a must. Steppers keep users informed about their progress by indicating what step they’re on and how many steps are left. Displaying steppers on mobile forms is challenging due to limited spacing.
Link: https://uxmovement.com/mobile/how-to-display-steppers-on-mobile-forms/
Word Count: 329

What Facebook knows about you

On Facebook's map of humanity, the node for "you" often includes vast awareness of your movements online and a surprising amount of info about what you do offline, too. The big picture: Even when you're cautious about sharing, Facebook's dossier on you will be hefty.
Link: https://www.axios.com/facebook-personal-data-scope-suer-privacy-de15c860-9153-45b6-95e8-ddac8cd47c34.html
Word Count: 957

[Notes] Neural Language Model with PyTorch

I was reading this paper titled “Character-Level Language Modeling with Deeper Self-Attention” by Al-Rfou et al., which describes some ways to use Transformer self-attention models to solve the language modeling problem.
Link: https://medium.com/the-artificial-impostor/notes-neural-language-model-with-pytorch-a8369ba80a5c
Word Count: 1488

Introducing state of the art text classification with universal language models

This post is a lay-person’s introduction to our new paper, which shows how to classify documents automatically with both higher accuracy and less data requirements than previous approaches.
Link: http://Natural Language Processing (NLP).fast.ai/classification/2018/05/15/introducting-ulmfit.html
Word Count: 1834