Are you interested in Neural Architecture Search but don’t know where to start?

Then you should consult “A Survey on Neural Architecture Search”. It is one of the key papers to understand the NAS space.

Thread⬇️
The NAS space is growing very rapidly.

“A Survey on Neural Architecture Search” provides a survey of the most important NAS:
+methods
+principles,
+components
2/6⬇️
NAS techniques can all be abstracted in two fundamental steps:

+What to search for: a search space
+How to search: a search algorithm
3/6⬇️
“A Survey on Neural Architecture Search” proposes 2 types of search spaces for all NAS problems:
+Global Search Space
+Cell Search Space

And 3 optimization methods:
+Reinforcement Learning
+Evolutionary Algorithms
+One-Shot Models
4/6⬇️
“A Survey on Neural Architecture Search” = one of those papers that any data scientist working with NAS methods should consult from time to time.

Link: arxiv.org/pdf/1905.01392…
5/6⬇️
TheSequence Edge covers:
+ML concept you should learn
+Review of an impactful research paper
+New ML framework or platform and how you can use it

thesequence.substack.com/p/thesequence-…
6/6

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with TheSequence

TheSequence Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @TheSequenceAI

19 Jun
🤖@Uber Ludwig = Open Source Framework for Creating ML Models Without Writing Any Code.

To use Ludwig all you need is a data file with the inputs attributes and the desired outputs, Ludwig does the result.
Thread🧵👇 Image
The main innovation behind Ludwig = idea of data-type specific encoders and decoders. Ludwig uses specific encoders and decoders for any given data type supported.
2/6⬇️ Image
Ludwig is based on a series of principles:
+No Coding Required
+Generality
+Flexibility
+Extensibility
+Interpretability
3/6⬇️
Read 6 tweets
7 Jun
The centralized nature of AI makes it difficult for startups to compete with the large tech incumbents that have access to:
+massive datasets
+virtually unlimited computing resources
+world-class research talent

Decentralized AI is the key

Thread⬇️
The research in decentralized ML is nothing new and can be traced back to the late 1970s

But the space has caught new momentum w/ blockchains and distributed ledger technologies
2/⬇️
However, blockchains are not the only technology trend influencing decentralized ML

Decentralized ML has benefited from:
+Blockchains
+Federated Learning
+Private ML
3/⬇️
Read 7 tweets
5 Jun
🤖@hopsworks = feature store for your deep learning solution

It’s a feature store platform with its own loyal community that has been adopted by several major companies
Thread🧵👇 Image
❓HopsWorks = open-source feature store platform that enables the management and maintenance of features in a deep learning infrastructure

It’s a centralized catalog of features that can be discovered, used, and maintained across different ML models
2/⬇️
HopsWorks capabilities:
+Feature Reusability
+Feature Discovery
+Feature Analysis
3/⬇️
Read 6 tweets
29 May
🤖@MLflow = one of the most popular platforms for end-to-end ML lifecycle management

It is integrated with every major framework and platform on the market

Thread🧵👇
❓MLflow = open-source framework that implements many of the principles of architectures like:
 
+FBLearner Flow by @FacebookAI
+TFX by @GoogleAI
+Michelangelo by @UberEng
2/⬇️
MLflow main components:
+MLflow Tracking
+MLflow Projects
+MLflow Models
+MLflow Model Registry
3/⬇️
thesequence.substack.com/p/edge12-the-c…
Read 6 tweets
28 May
TensorFlow Serving = the first mainstream model serving architecture in ML frameworks

+It serves ML models inside Google
+It is available in the cloud and via open-source

How it was created and how it works?
Thread⬇️
Deep dive into "TensorFlow-Serving: Flexible, High-Performance ML Serving" by @JeremiahHarmsen, @FangweiLi, @sukritiramesh, Christopher Olston, Noah Fiedel, Kiril Gorovoy, Li Lao, Vinu Rajashekhar, Jordan Soyke

2/⬇️
Paper outlined the architecture of a serving pipeline for @TensorFlow models

Capabilities of TensorFlow serving:

+model lifecycle management;
+experiments with multiple algorithms;
+efficient use of GPU resources
3/⬇️
Read 6 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!

Follow Us on Twitter!

:(