How to Design a Convolutional Neural Network
Check out the follow-up video:
How to Design a Neural Network | 2020 Edition
https://youtu.be/g2vlqhefADk
Designing a good model usually involves a lot of trial and error. It is still more of an art than science. The tricks and design patterns that I present in this video are mostly based on 'folk wisdom', my personal experience, and ideas that come from successful model architectures.
Deep Learning Crash Course playlist: https://www.youtube.com/playlist?list=PLWKotBjTDoLj3rXBL-nEIPRN9V3a9Cx07
Previous video:
https://youtu.be/-I0lry5ceDs
Highlights:
How to choose the number of layers
Deeper vs wider models
Design patterns and hyperparameters
Skip connections
ResNet
Inception module
Fully Convolutional Networks
Pointwise convolutions
Dimensionality reduction
MobileNets
Separable convolutions
How to choose sliding window stride
How to choose pooling parameters
How to choose activation function
What type of regularization to use
How to choose the batch size
Further reading:
Deep Learning by Ian Goodfellow:
http://www.deeplearningbook.org/
CS231n: Convolutional Neural Networks for Visual Recognition
http://cs231n.github.io/
Deep Residual Learning for Image Recognition
https://arxiv.org/pdf/1512.03385.pdf
Fully convolutional networks for semantic segmentation
https://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2B_011.pdf
Surface Water Mapping by Deep Learning
http://www.isikdogan.com/files/isikdogan2017_deepwatermap.pdf
Network In Network
https://arxiv.org/pdf/1312.4400.pdf
Rethinking the inception architecture for computer vision
https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Szegedy_Rethinking_the_Inception_CVPR_2016_paper.pdf
Mobilenets: Efficient convolutional neural networks for mobile vision applications
https://arxiv.org/pdf/1704.04861.pdf
Видео How to Design a Convolutional Neural Network канала Leo Isikdogan
How to Design a Neural Network | 2020 Edition
https://youtu.be/g2vlqhefADk
Designing a good model usually involves a lot of trial and error. It is still more of an art than science. The tricks and design patterns that I present in this video are mostly based on 'folk wisdom', my personal experience, and ideas that come from successful model architectures.
Deep Learning Crash Course playlist: https://www.youtube.com/playlist?list=PLWKotBjTDoLj3rXBL-nEIPRN9V3a9Cx07
Previous video:
https://youtu.be/-I0lry5ceDs
Highlights:
How to choose the number of layers
Deeper vs wider models
Design patterns and hyperparameters
Skip connections
ResNet
Inception module
Fully Convolutional Networks
Pointwise convolutions
Dimensionality reduction
MobileNets
Separable convolutions
How to choose sliding window stride
How to choose pooling parameters
How to choose activation function
What type of regularization to use
How to choose the batch size
Further reading:
Deep Learning by Ian Goodfellow:
http://www.deeplearningbook.org/
CS231n: Convolutional Neural Networks for Visual Recognition
http://cs231n.github.io/
Deep Residual Learning for Image Recognition
https://arxiv.org/pdf/1512.03385.pdf
Fully convolutional networks for semantic segmentation
https://www.cv-foundation.org/openaccess/content_cvpr_2015/app/2B_011.pdf
Surface Water Mapping by Deep Learning
http://www.isikdogan.com/files/isikdogan2017_deepwatermap.pdf
Network In Network
https://arxiv.org/pdf/1312.4400.pdf
Rethinking the inception architecture for computer vision
https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Szegedy_Rethinking_the_Inception_CVPR_2016_paper.pdf
Mobilenets: Efficient convolutional neural networks for mobile vision applications
https://arxiv.org/pdf/1704.04861.pdf
Видео How to Design a Convolutional Neural Network канала Leo Isikdogan
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Convolutional Neural Networks ExplainedOverfitting, Underfitting, and Model CapacityCan deep learning predict the stock market?Depthwise Separable Convolution - A FASTER CONVOLUTION!Transfer LearningDeep Unsupervised LearningHow to Design a Neural Network | 2020 EditionCan AI Create Original Art?What do filters of Convolution Neural Network learn?Convolution Neural Networks - EXPLAINEDWhat are Neural Networks || How AIs thinkGenerative Adversarial NetworksMulti-Task Learning | Explained in 5 MinutesOptimization Tricks: momentum, batch-norm, and moreComputer Science ElectivesSemifreddoNets: Partially Frozen Neural Networks for Efficient Computer Vision Systems (ECCV 2020)Image Filters ExplainedGenerative Adversarial Networks - FUTURISTIC & FUN AI !