GoogLeNet Deep Neural Network Explained - Inception V1 Architecture and Implementation
Offered By: Yacine Mahdid via YouTube
Course Description
Overview
Explore the intricacies of GoogLeNet, also known as Inception V1, in this comprehensive 23-minute tutorial. Dive into the architecture of this 22-layer deep neural network, which revolutionized deep learning in 2014 with its innovative use of 1x1 convolutions. Learn how to implement GoogLeNet using PyTorch and apply it to the CIFAR-10 dataset. Follow a detailed breakdown of the "Going Deeper with Convolutions" paper, understanding the Inception module, architecture details, training process, and results. Gain hands-on experience with PyTorch implementation, covering Inception modules, BasicConv2D, InceptionAux, and the complete GoogLeNet structure. Perfect for machine learning enthusiasts looking to deepen their understanding of influential neural network architectures.
Syllabus
- Introduction:
- GoogLeNet with Pytorch on CIFAR-10:
- Background:
- Architecture Overview:
- Inception Module:
- Architecture Details:
- GoogLeNet Training:
- GoogLeNet Result:
- GoogLeNet Pytorch Overview:
- GoogLeNet Pytorch - Inception:
- GoogLeNet Pytorch - BasicConv2D:
- GoogLeNet Pytorch - InceptionAux:
- GooGleNet Pytorch - GoogLeNet:
- Conclusion:
Taught by
Yacine Mahdid
Related Courses
Diffusion Models - PyTorch ImplementationOutlier via YouTube Premonitions of Public Data for Private ML
Fields Institute via YouTube Elucidating the Design Space of Diffusion-Based Generative Models
Finnish Center for Artificial Intelligence FCAI via YouTube Differentially Private Diffusion Models Generate Useful Synthetic Images
Google TechTalks via YouTube Advanced Generative Adversarial Networks (GANs)
Packt via Coursera