Network Architecture Search: AutoML and others

Показать описание

In the Deep Learning Crash Course series, we talked about some of the good practices in designing neural networks but we didn't talk about how to do it automatically. That's what we are going to cover in this video: automatic network architecture search, which is what the media advertises as AI that creates AI.

*** References ***

Neural Architecture Search with Reinforcement Learning

Learning Transferable Architectures for Scalable Image Recognition

Progressive Neural Architecture Search

Efficient Neural Architecture Search via Parameter Sharing

Efficient Architecture Search by Network Transformation

Network Morphism

Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution

Auto-Keras: An Efficient Neural Architecture Search System

Convolutional Neural Fabrics

DARTS: Differentiable Architecture Search

Neural Architecture Optimization

SMASH: One-Shot Model Architecture Search through HyperNetworks

* Off-topic reference
More Parkour Atlas by Boston Dynamics

Рекомендации по теме

Комментарии

Thanks, Leo. Thanks for the research paper, it was informative.

satyajitdas

Sometimes I think we're(and media) exaggerating neural networks who are actually "universal function approximators". Good content btw.

Very good overview of non recent development

daluwang

Very good explantation and easy to follow. Thanks!

mathlibrary

Thank you for this! When life give you lemons...

richarda

Interesting video. Have you seen "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks"? It is the result of research into the best network design. They managed to design a network that was 8.4x less complex, 6.1x faster, and more accuracy, than even the best existing convolutional networks. By optimizing the layer design and reducing wastefulness.

BenderdickCumbersnatch

Wonderful and informative knowledge acquired :)

angtrinh

Great work! Thank you very much! :) Really helped for my exams.

kdsuch

Thank you for an informative video. However I'm still left with the question: Are these methods worth it, and if so, when are they better than manual optimization?

dumbledoor

Great content! What kind of software you're using for drawings like at 4:30?

emersonmicu

Sir, finding difficulty in learning neural network

pooranmashi

please use better microphone or better sound process

housexx

Network Architecture Search: AutoML and others

Network Architecture Search: AutoML and others

AutoML Fall School 21: Introduction to Neural Architecture Search

Auto ML and Neural Architecture Search

Google Model Search - Neural Network Architecture Search

AutoML — How to Find the Neural Architecture that Best Models Your Dataset

State of the Art Neural Networks - Neural architecture search (NAS)

Easy AI Concepts: Neural Architecture Search (NAS) #ai

Mohamed Abdelfattah | 'Fast and Hardware-Aware Neural Architecture Search'

Neural Architecture Search and Google’s New AutoML Zero with Quoc Le - #366

Accelerator-aware Neural Network Design using AutoML

AutoML Fall School 2022 - Neural Architecture Search by Colin White

AutoML Fall School 21: Meta-Learning for Neural Architecture Search

Directions in ML: Algorithmic foundations of neural architecture search

A framework for exploring and modelling neural architecture search methods

[ECCV 2020 Tutorial] AutoML for Efficient 3D Deep Learning

Auto-Keras: An Efficient Neural Architecture Search System

Wuyang Chen | 'Neural Architecture Search on ImageNet in Four GPU Hours'

ENAS | Lecture 15 (Part 2) | Applied Deep Learning (Supplementary)

DataXDay - How to scale Neural Network Architecture Search with RabbitMQ and Kubernetes

Directions in ML: 'Neural architecture search: Coming of age'

Introduction to Neural Architecture Search

[CVPR 2020 Tutorial] AutoML for TinyML with Once-for-All Network

EfficientML.ai Lecture 7 - Neural Architecture Search (Part I) (MIT 6.5940, Fall 2023)

Efficient Forward Architecture Search