Our Favorite Posts Of Last Week (Jul 22, 2018)
Elastic Stack — A Brief Introduction
You are reading the right blog post if you have heard of Elastic Stack and want to explore or if you are an absolute dummy. I am sure you won’t be so after reading this! Let’s understand what Elastic Stack is and why do you need it. What is Elastic Stack ?
Word Count: 1194
Reproducible machine learning with PyTorch and Quilt
In this article, we'll train a PyTorch model to perform super-resolution imaging, a technique for gracefully upscaling images. We'll use the Quilt data registry to snapshot training data and models as versioned data packages.
Word Count: 1582
How to Get over Perfectionism (and Execute on Your Ideas)
As marketers, we’re all too familiar with putting off executing on an idea. There’s always a perfectly good reason for this: the end goal hasn’t quite crystallized yet. The resources and budget need to be better thought through. The analytics systems in place don’t seem up to par.
Word Count: 1829
Report on Text Classification using CNN, RNN & HAN
Hello World!! I recently joined Jatana.ai as NLP Researcher (Intern ?) and I was asked to work on the text classification use cases using Deep learning models. In this article I will share my experiences and learnings while experimenting with various neural networks architectures.
Word Count: 1786
What are impressions, position, and clicks?
This page helps explain impressions, position values, and click data in the Search Analytics report. The heuristics described here—such as the visibility requirement for an item in a carousel, or the position numbering—are subject to change.
Word Count: 2434
Perficient Acquires Stone Temple Consulting
– Perficient, Inc.
Word Count: 546
3 silver bullets of word embedding in NLP
Word Embedding is silver bullet to resolve many NLP problem. Most of modern NLP architecture adopted word embedding and giving up bag-of-word (BoW), Latent Dirichlet Allocation (LDA), Latent Semantic Analysis (LSA) etc. Traditionally, we use bag-of-word to represent a feature (e.g.
Word Count: 1264
Association Rules and the Apriori Algorithm: A Tutorial
When we go grocery shopping, we often have a standard list of things to buy. Each shopper has a distinctive list, depending on one’s needs and preferences. A housewife might buy healthy ingredients for a family dinner, while a bachelor might buy beer and chips.
Word Count: 2414