Explosion

AUGUST 21, 2016

Let’s say you want to demonstrate how well your newly trained technology company tagging model works. Hopefully, your back-end service will reliably tag “Facebook”, which you could then highlight on the screen. You can use this to bias your data annotation, e.g. by annotating more tweets, and fewer blog posts.

Artificial Intelligence 40

Artificial Intelligence Artificial Intelligence AI AI 40

phData

OCTOBER 2, 2023

In this blog post, we’ll explore what a feature store is in the first place, explore a few of the key advantages (and disadvantages), and touch on when is the right time for your organization to build or adopt a feature store. Data platform abstraction. But first, let’s equip you with a brief background of a feature.

Data Warehouse 98

Data Warehouse ML ML Data Scientist 98

Heartbeat

JUNE 27, 2023

Graphs are an abstract data structure that have a powerful data representation technique. They are commonly utilized in a variety of applications such as text generation, machine translation, speech recognition, image captioning, video tagging, and text summarization. We pay our contributors, and we don’t sell ads.

Deep Learning 59

Deep Learning Deep Learning ML ML 59

Mlearning.ai

DECEMBER 21, 2023

RAG Pipeline This involves the actual RAG process which takes the user query at run time and retrieves the relevant data from the index, then passes that to the model We will focus on the Indexing pipeline in this blog Indexing Pipeline The indexing pipeline sets up the knowledge source for the RAG system.

Database 94

Database AI AI Machine Learning 94

Explosion

APRIL 1, 2017

Prodigy features many of the ideas and solutions for data collection and supervised learning outlined in this blog post. Each example consists of a context and its correct tag, provided by a human annotator. The output of the function is the weights table, W , which can be used to predict a tag given the context. Try Prodigy!

Supervised Learning 40

Supervised Learning Machine Learning Machine Learning Algorithm 40

The MLOps Blog

AUGUST 3, 2023

The answer was to give them the tooling abstractions and APIs such that they didn’t have to be good software engineers – MLOps best practices basically came for free. If you ever want to know some interesting stories about techniques and things, you can look up the Stitch Fix Multithreaded blog.

ML 52

ML ML Data Scientist Machine Learning 52

Applied Data Science

JUNE 1, 2021

This blog post is for visual creators, visual communicators, curious readers fascinated by visuals on the internet, readers whose business depends on correctly appreciating visuals, readers annoyed by a lack of truth and elegance in proliferating visuals. In any other case, a model is but an abstraction of our world.

Data Science 130

Data Science Database Business Intelligence Business Intelligence 130

Explosion

DECEMBER 17, 2013

I wrote this blog post in 2013, describing an exciting advance in natural language understanding technology. split() >>> tags, heads = parser.parse(tokens) >>> heads [-1, 2, 0, 0, 3, 0, 7, 5, 7, 10, 8, 0, 13, 15, 15, 11] >>> for i, h in enumerate(heads): head = tokens[heads[h]] if h >= 1 else 'None'.

Python 45

Python Algorithm Natural Language Processing 45

Explosion

JUNE 18, 2021

In this blog post, I’m going to discuss some of the biggest challenges for applied NLP and translating business problems into machine learning solutions. This blog post is based on talks I gave at the “Teaching NLP” workshop at NAACL 2021 and the L3-AI online conference. I call this “Applied NLP Thinking”. All of those details matter.

Machine Learning 52

Machine Learning Machine Learning Natural Language Processing Clustering 52

Explosion

MAY 17, 2023

But if you’re building a system and you want to calculate and display this information for every review, it’s very nice to just approach this as separate prediction tasks (tagging names, linking them to a knowledge base, and paragraph-level actor sentiment), with data structures that let you flexibly access the information.

Supervised Learning 135

Supervised Learning Natural Language Processing Clustering Machine Learning 135

The MLOps Blog

OCTOBER 3, 2023

And then, the virtual feature store is an abstraction on top of storage and a compute component. For example, Shopify published a blog post about Merlin. They just need to kind of tag things like “Hey, by the way, we’re using these data sources. We’re going to create and provide abstractions.”

ML 52

ML ML Data Scientist Machine Learning 52

Alation

FEBRUARY 17, 2023

In this blog, I’ll address some of the questions we did not have time to answer live, pulling from both Dr. Reichental’s book as well as my own experience as a data governance leader for 30+ years. In the final consumption layer, the data fields could be tagged for governance, PII specifics, and advanced classification and categorization.

Data Governance 52

Data Governance Data Quality Data Analyst Data Pipeline 52

The MLOps Blog

MARCH 21, 2023

Your role as a platform engineer, or in most cases, an “MLOps engineer” is to practically architect and build solutions that make it easy for your users to interact with the ML lifecycle while proving appropriate abstractions from the core infrastructure. Let’s talk about those platform user personas. My Story DevOps Engineers Who they are?

Machine Learning 69

Machine Learning Machine Learning Data Scientist ML 69