AssemblyAI

SEPTEMBER 26, 2023

In this tutorial, we will demonstrate how to perform Retrieval Augmented Generation with audio data by leveraging AssemblyAI’s document loader for LangChain, a popular framework that provides building blocks for LLM-based applications. Additionally, we can exclude the virtual environment from source control. filepath/URL).

Database 98

Database Python SQL Machine Learning 98

phData

APRIL 5, 2024

In this blog, we’ll cover what the Document AI tool is, what use cases it solves, and how to integrate it with document processing pipelines. What is Document AI from Snowflake? PDFs or scanned handwritten docs) and can answer questions about them using natural language. Why is Document AI Important?

AI 52

AI AI Natural Language Processing Tableau 52

Flipboard

APRIL 11, 2023

But it makes me wonder what topics aren’t getting the attention that they deserve. However, I wouldn’t write off NFTs and blockchains just yet. Facebook renamed itself, and then found out that nobody could agree on what the Metaverse was—at least in part because Facebook’s ideas were, well, lame.

Database 134

Database Python Clustering SQL 134

ODSC - Open Data Science

FEBRUARY 22, 2024

Here’s a bit more on why that’s the case. Industry, Opinion, Career Advice What Dagster Believes About Data Platforms The beliefs that organizations adopt about the way their data platforms should function influence their outcomes. How Dash Enterprise 5.2 We’ll also touch upon details of their book and what went into writing it.

AI 52

AI AI Machine Learning Machine Learning 52

Chatbots Life

APRIL 18, 2023

Here is how to prepare for the beginning of the biggest disruption in technology ChatGPT has taken the internet by storm. Let’s take a quick look at what is being disrupted, how, and what you can do about it…. Let’s take a quick look at what is being disrupted, how, and what you can do about it….

AI 78

AI AI 78

Towards AI

JULY 20, 2023

Let’s talk about “Cryptonite: How I Stopped Worrying and Learned(?) Solving the ambiguity problem, whether its derived strictly from NLP only or from a combination of multi-modal models, or from graphs, will be key in order for models to achieve what Thomas Paine called “Common Sense”. Because it requires models to have n-order logic.

Deep Learning 83

Deep Learning Deep Learning Data Analysis Data Analysis 83

phData

MARCH 18, 2024

Specifically, we’ll show how to create dbt snapshots and how they simplify the setup and maintenance of SCD Type-2 tables, offering a significant advantage for data management. What is SCD SCD stands for Slowly Changing Dimension, a dimension that changes over time. What are dbt Snapshots? Let’s begin!

Data Warehouse 52

Data Warehouse SQL Data Pipeline Analytics 52

Hacker News

SEPTEMBER 12, 2023

I interviewed more than 20 of today’s most successful B2B founders, and from their stories, I’ve found: A simple framework for moving closer to PMF Signs that you’re approaching PMF How long it should take you to find PMF Advice for what to do if you aren’t finding PMF Let’s get into it.

Analytics 181

Analytics Analytics Data Analyst 181

DataRobot Blog

NOVEMBER 9, 2017

In fact, I’ve seen it generate a fair bit of consternation amongst business leaders and executives who are actively trying to figure out what all of this AI stuff is about in the first place. What matters is making progress. One of the things that we realized early on is that there’s a massive amount of confusion about what AI even is.

AI 52

AI AI Data Scientist Machine Learning 52

Explosion

AUGUST 3, 2017

This is good, because the examples are how you program the behaviour – the learner itself is really just a compiler. What’s not good is the current technology for creating the examples. That’s why we’re pleased to introduce Prodigy , a downloadable tool for radically efficient machine teaching.

Supervised Learning 52

Supervised Learning Python Machine Learning Machine Learning 52

Ines Montani

AUGUST 4, 2017

I’m excited and proud to finally share what we’ve been working on since launching Explosion AI , alongside our NLP library spaCy and our consulting projects. You need to select the examples, write manuals and hire annotators for the boring work. I’ve always had a hard time accepting that this was simply how things are.

Python 52

Python Supervised Learning Artificial Intelligence Artificial Intelligence 52

Dataconomy

OCTOBER 27, 2023

It’s no wonder why. Our top 10 AI tools for business HIX ArticleGPT – Best AI Content Generation Platform Pictory – Best AI Video Editor Surfer SEO – Best AI SEO Article Writing Tool Clockwise – Best AI Scheduling Tool DALL.E So, like those 80% of retail companies – you want to adopt AI into your business practices.

AI 140

AI AI Natural Language Processing Algorithm 140

The MLOps Blog

OCTOBER 3, 2023

How to transition from data analytics to MLOps engineering Piotr: Miki, you’ve been a data scientist, right? I know that you are not a big fan of titles; you’d rather prefer to talk about what you actually can do. But I’d say what you do is not a common combination. And later, an MLOps engineer.

ML 52

ML ML Data Scientist Machine Learning 52

O'Reilly Media

NOVEMBER 28, 2023

And everyone has opinions about how these language models and art generation programs are going to change the nature of work, usher in the singularity, or perhaps even doom the human race. What’s the reality? We wanted to find out what people are actually doing, so in September we surveyed O’Reilly’s users.

AI 108

AI AI Data Analysis Data Analysis 108

Hacker News

AUGUST 21, 2023

To understand why it's bad we need to go back in time all the way to when I first launched the API that was intended to be consumed programmatically by other people's services. Which is why they turned their attention to the non-authenticated, non-documented unified search API. Here's how it works: Get it?

Azure 122

Azure 122

The MLOps Blog

AUGUST 3, 2023

What is DAGWorks? It’s a little bit of an homage to how we think and how we’re trying to solve problems. We want to enable a team of junior data scientists to write code, take it into production, maintain it, and then when they leave, importantly, no one has nightmares about inheriting their code. Stefan: Yeah.

ML 52

ML ML Data Scientist Machine Learning 52

Heartbeat

DECEMBER 15, 2023

And an Assessment of How They Impact Your ragas Metrics Photo by Ilya Pavlov on Unsplash If you’ve ever wondered how the quality of information sourced by language models affects their outputs, you’re in the right place. Why is this important? Let’s write some code!

Database 52

Database Natural Language Processing AI AI 52

Explosion

DECEMBER 14, 2021

What to expect 4.2 What to expect This blog post presents a technical approach to analyzing user reviews and acts as a proof of concept. joint pain) is linked to a description of how the aspect is affected by the product (e.g. Section 1: Introducing Healthsea ? Section 4: Clausecat 1.1 Creating better access to health 4.1

Clustering 52

Clustering Machine Learning Machine Learning Natural Language Processing 52

The MLOps Blog

NOVEMBER 14, 2023

Deep learning model visualization helps us understand model behavior and differences between models, diagnose training processes and performance issues, and aid the refinement and optimizations of models | Source Why do we want to visualize deep learning models?

Deep Learning 111

Deep Learning Deep Learning Data Scientist Machine Learning 111

Hacker News

MARCH 14, 2023

But behind the justification of protecting students lay a market-altering policy: the bill was introduced at the behest of Microsoft lobbyists, in an effort to exclude Google Docs from classrooms. Here’s how it might work. AI models can use past examples to learn to estimate how that information changes the network.

AI 174

AI AI Machine Learning Machine Learning 174

O'Reilly Media

JULY 25, 2023

If you’re reading this, chances are you’ve played around with using AI tools like ChatGPT or GitHub Copilot to write code for you. or “ha look how incompetent it is … it couldn’t even get my simple question right!” This article summarizes what I learned from that experience.

AI 98

AI AI ML ML 98

Heartbeat

JULY 25, 2023

If so, how much effort does it take to go from that system to a deep learning framework-ready system? TFRecords So today, we are going to explore how we can optimize our deep learning pipelines using TensorFlow’s TFRecords. I’ve seen a few blogs on this topic, and all of them fail to adequately describe what TFRecords are.

Deep Learning 52

Deep Learning Deep Learning Python ML 52

Explosion

OCTOBER 15, 2017

One of the best improvements is a new system for adding pipeline components and registering extensions to the Doc , Span and Token objects. This has been especially true of the core Doc , Token and Span objects. If every extension required spaCy to return a different Doc subclass, there would be no way to do that. In spaCy v2.0

Natural Language Processing 52

Natural Language Processing Python Deep Learning Deep Learning 52

Towards AI

JULY 21, 2023

Fury What a week. Why use the Model Forge?! A notebook we created using the quick versatility of the Forge, showing how to link models together in a single pipeline for inference. ", "What was score?"]execute Now you can see how fun preprocessing really is ?! Let’s recap. Explore the 27.2K

SQL 83

SQL Deep Learning Deep Learning Natural Language Processing 83

Data Science 101

OCTOBER 23, 2023

” Georgia Mountford-Blake (@georgiagemo) on Threads So @georgiagemo , you grew up with an interest in writing, but at some point added coding to your skillset. How did that happen? After graduation I took dual degree at uni – Bachelors in Journalism & Computer Science – because why pick one when you can do both?!

Computer Science 59

Computer Science Computer Science Database AI 59

Mlearning.ai

JANUARY 17, 2024

Each section of this story comprises a discussion of the topic plus a curated list of resources, sometimes containing sites with more lists of resources: 20+: What is Generative AI? If classic AI is the wise owl, generative AI is the wiser owl with a paintbrush and a knack for writing. Let us dive into the wild world of genAI.

AI 98

AI AI Deep Learning Deep Learning 98

Heartbeat

JULY 27, 2023

Protobufs for TFRecords So why the heck did I just spend all that time covering protobufs. You can read more about the “oneof” keyword here But wait, why did I create the individual protos of ByteList, FloatList, and Int64List just to wrap them in yet another proto? Note: This is the second part of a two part series.

Deep Learning 52

Deep Learning Deep Learning Python ML 52

The MLOps Blog

MARCH 28, 2024

Optimizing your GPU instances ensures that your organization pays only for what it needs, especially when using a cloud-based service where every hour and minute counts on the bill. Utilization The GPU utilization metric quantifies how the GPU is engaged during the training of deep-learning models.

Deep Learning 52

Deep Learning Deep Learning Data Pipeline Machine Learning 52

AWS Machine Learning Blog

MARCH 28, 2024

You can deploy this solution with just a few clicks using Amazon SageMaker JumpStart , a fully managed platform that offers state-of-the-art foundation models for various use cases such as content writing, code generation, question answering, copywriting, summarization, classification, and information retrieval.

AWS 111

AWS Machine Learning Machine Learning AI 111

Explosion

MARCH 17, 2019

We’ve fixed almost every outstanding bug on the tracker, given the docs a huge makeover, improved both speed and accuracy, made installation significantly easier and faster, and developed some exciting new features. This is exactly what algorithms like word2vec, GloVe and FastText set out to solve. average was 2 lbs.")

Python 52

Python Natural Language Processing Deep Learning Deep Learning 52

Ocean Protocol

FEBRUARY 28, 2024

Predictoor involves two groups of people: Predictoors: data scientists who use AI models to predict what the price of ETH, BTC, etc will be 5 (or 60) minutes into the future. Simultaneously, build a first-class data pipeline and analytics dapp, to better answer the question “how much $ am I making” and drill-down questions.

Data Scientist 64

Data Scientist Data Pipeline Algorithm AI 64

Explosion

AUGUST 22, 2017

Ideally, our optimisers would be so good that they’d always find the same – optimal – solution to a given problem, no matter how the weights are initialised. This means that if you optimise for two problems in succession, catastrophic forgetting is what should happen. This isn’t true, but it’s something we’re aiming for.

Natural Language Processing 52

Natural Language Processing Big Data Big Data ML 52

Mlearning.ai

MAY 15, 2023

What is Python? What are the benefits of using Python Python is a high-level, interpreted, general-purpose programming language. What is a dynamically typed language? Before we understand a dynamically typed language, we should learn about what typing is. What is an Interpreted language? What is Scope in Python?

Python 52

Python ML ML Data Analysis 52

Mlearning.ai

JUNE 8, 2023

Intuitively, think when you compare if two things are similar to each other, you want to represent the two things (text, image, video, audio or ideally anything that can be digitized) as two points and then find how close they are. Think how you can find two points are close to each other in a 2-dimensional space, like in this article.

Machine Learning 52

Machine Learning Machine Learning Clustering Database 52

Ines Montani

MAY 9, 2017

I’ll also give you my perspective on how to make commercial open-source work for both users and developers. After we provided more docs and refactored our website’s markup language, we saw a big increase in small pull requests – from fixing minor typos in the docs (I admire everyone who goes out of their way to do this!)

Natural Language Processing 52

Natural Language Processing Deep Learning Deep Learning Python 52

Explosion

JANUARY 12, 2018

We set ourselves ambitious goals this year, and we’re very happy with how we achieved them. Here’s what we got done. Introduced new system for extending Doc , Span and Token objects with custom attributes. improved our build and test infrastructure, and made huge improvements to the docs.

Machine Learning 52

Machine Learning Machine Learning Supervised Learning Python 52

ML Review

FEBRUARY 11, 2019

First, my aim is not to explain how or why ULMFIT became to be a state-of-the-art model because there are many resources like this fast.ai Since I’ve already spent quite some time digging deeper, I thought it would be cool to share what I distilled from it. Each channel will be zeroed out independently on every forward call.

Deep Learning 52

Deep Learning Deep Learning ML ML 52