🗄 A Model Compression Library You Need to Know About
Was this email forwarded to you? Sign up here 🗄 A Model Compression Library You Need to Know AboutWeekly news digest curated by the industry insiders📝 EditorialThe machine learning (ML) space is currently dominated by large models that often have computation requirements impossible for most organizations. Model compression is one of the disciplines that has been targeting that challenge by creating smaller models without sacrificing accuracy. Despite the obvious need, model compression remains a challenge for ML engineering teams as most frameworks in the space are relatively nascent. As a result, you rarely hear about ML engineering pipelines that incorporate model compression as a native building block. Quite the opposite, model compression tends to be one of those things that you only consider once the problem is too big to ignore; literally 😉 Last week, Microsoft Research open-sourced a new framework that attempts to streamline compression in deep learning models. DeepSpeed Compression is part of the DeepSpeed platform aimed to address the challenges of large-scale AI systems. The framework provides a catalog of common model compression techniques abstracted using a consistent programming model. The initial experiments showed up to 32x compression rates in large transformer architectures such as BERT. If DeepSpeed Compression follows the path to other frameworks in the DeepSpeed family, it could be productized as part of the Azure ML platform and streamline the adoption of compression methods in deep learning architectures. DeepSpeed Compression is definitely a framework to follow by the ML engineering community. 🔺🔻TheSequence Scope – our Sunday edition with the industry’s development overview – is free. To receive high-quality content about the most relevant developments in the ML world every Tuesday and Thursday, please subscribe to TheSequence Edge 🔺🔻 🗓 Next week in TheSequence Edge: Edge#211: we discuss what to test in ML models; explain how Meta uses A/B testing to improve Facebook’s newsfeed algorithm; explore Meta’s Ax, a framework for A/B testing in PyTorch. Edge#212: we dive deep inside the Masterful CLI Trainer, a low-code CV model development platform. Now, let’s review the most important developments in the AI industry this week 🔎 ML ResearchGeneralist Reinforcement Learning Agents Google Research published a paper unveiling a generalist reinforcement learning agent that can play many video games simultaneously →read more on Google Research blog Outlier Root Cause Analysis Amazon Research published a paper outlining a technique to detect the root causes of statistical outliers →read more on Amazon Research blog CodeRL Salesforce Research published a paper and open-sourced code for CodeRL, a reinforcement learning framework for program synthesis →read more on Salesforce Research blog The Algorithms Behind Transformers DeepMind published a research paper detailing the algorithms and mathematical foundations of transformer architectures →read more in the original research paper from DeepMind ☝️ We Recommend – Join this webinar and discover the Hopsworks 3.0 release!In this talk, Hopsworks VP of engineering will explore new capabilities in Hopsworks feature store 3.0 and how it can help data scientists who love Python to manage their features for training and serving models. He will also native Python support for feature engineering, feature pipelines, feature views that represent models in the feature store, transformation functions, and data validation with Great Expectations. Join us on Aug 3, at 7 PM CEST. 🤖 Cool AI Tech ReleasesDeepSpeed Compression Microsoft Research open-sourced DeepSpeed Compression, a framework for compression and system optimization in deep learning models →read more on Microsoft Research blog DALL-E Beta OpenAI expanded the availability of DALL-E to over a million people on the waitlist →read more on OpenAI blog New Tools and Frameworks for Alexa Amazon unveiled a series of new developer frameworks and tools for Alexa that improve developers’ and device makers’ experience →read more on Amazon Developer blog PlayTorch App PyTorch open-sourced the PlayTorch app to streamline the development of mobile AI experiences →read more on PyTorch blog 🛠 Real World MLOut of Memory Predictions at Netflix Netflix discusses the architecture powering ML models used to predict memory capacity errors in TVs and set-top boxes →read more on Netflix tech blog 💸 Money in AI
You’re on the free list for TheSequence Scope and TheSequence Chat. For the full experience, become a paying subscriber to TheSequence Edge. Trusted by thousands of subscribers from the leading AI labs and universities. |
Key phrases
Older messages
📌 Event: Join us for this live webinar to learn how Tide reduced model deployment time by 50%!
Friday, July 22, 2022
A real use case you don't want to miss!
🟢⚪️ Edge#210: Hopsworks 3.0, Connecting Python to the Modern Data Stack
Thursday, July 21, 2022
On Thursdays, we deep dive into one of the freshest research papers or technology frameworks that is worth your attention. Our goal is to keep you up to date with new developments in AI and introduce
📌 Event: Join us at The Future of Data-Centric AI 2022 — a free virtual event by Snorkel AI
Wednesday, July 20, 2022
We're excited to partner with Snorkel AI on The Future of Data-Centric AI, a free two-day virtual event on August 3-4 that will cover the latest data-centric approaches to AI application
🔂 Edge#209: A New Series About ML Testing
Tuesday, July 19, 2022
Welcome to our premium newsletter that helps you learn ML concepts and focuses on the projects that move the AI industry forward. The content is trusted by the main AI labs, universities, enterprises,
📌 Event: A dive into continuous training automation – webinar by Superwise
Monday, July 18, 2022
Join us on August 9th for a live coding session as we build out a continuous MLOps pipeline. We'll start with the ML pipeline and see how we can detect performance degradation and data drift in
You Might Also Like
Edge 389: Understanding Large Action Models
Tuesday, April 23, 2024
One of the most important concepts in autonomous agents. ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
Apple World Cup bid ⚽, Meta opens VR OS 🌎, Anthropic's prompt library 🤖
Tuesday, April 23, 2024
Apple is working to secure an exclusive TV deal with FIFA Sign Up |Advertise|View Online TLDR Together With WorkOS TLDR 2024-04-23 WorkOS is the only auth provider your B2B SaaS app needs to start
New Blogs on ThomasMaurer.ch for 04/23/2024
Tuesday, April 23, 2024
View this email in your browser Thomas Maurer Cloud & Datacenter Update This is the update for blog posts on ThomasMaurer.ch. Cloud operations for Windows Server through Azure Arc By Thomas Maurer
Post-Post 🗨️
Tuesday, April 23, 2024
Assessing the post-Twitter climate amid Post.News' shutdown. Here's a version for your browser. Hunting for the end of the long tail • April 22, 2024 Post-Post The demise of Post, one of the
BetterDev #257 - Building a GPS Receiver
Monday, April 22, 2024
Better Dev #257 Apr 22, 2024 Hi all, We come back with a new issue this week. If you like BetterDev, please help spead word out by refer to your friends. Buy me a coffee would be great too. This week I
Tomorrow's Free Notes Class: How to sign up!
Monday, April 22, 2024
Hi there, Tomorrow we will be hosting a Free Notes App Class. This is your last chance to register for tomorrow's live class and learn how to get the most out of your Notes app. Our experienced
Elon’s ‘balls to the wall’ autonomy push
Monday, April 22, 2024
Plus: Amazon ends California drone deliveries and Rippling's founder has a brand-new bag View this email online in your browser By Christine Hall Monday, April 22, 2024 Image Credits: Toru Hanai/
📱 Your iPhone is Now Discoverable by Others — Tips for Building Your First PC
Monday, April 22, 2024
Also: How to Play Windows Games on Your Mac, and More! How-To Geek Logo April 22, 2024 📩 Get expert reviews, the hottest deals, how-to's, breaking news, and more delivered directly to your inbox by
JSK Daily for Apr 22, 2024
Monday, April 22, 2024
JSK Daily for Apr 22, 2024 View this email in your browser A community curated daily e-mail of JavaScript news It Is so Cool to Develop React Native With Expo 1. What are the benefits of Expo?. "
😺 The social walkie-talkie
Monday, April 22, 2024
Hi, hi! It's Monday and it's Earth Day! Don't miss the Cat Nips section below for innovative products in the... Product Hunt Read in browser This newsletter is brought to you by YOU MIGHT