YoVDO

ImageNet Classification with Deep Convolutional Neural Networks - Paper Explained

Offered By: Yannic Kilcher via YouTube

Tags

Image Classification Courses Deep Learning Courses Convolutional Neural Networks (CNN) Courses Data Augmentation Courses

Course Description

Overview

Explore the groundbreaking AlexNet paper that revolutionized deep learning in this comprehensive video explanation. Delve into the architecture of the first successful deep convolutional neural network trained on multiple GPUs, which outperformed previous computer vision systems on ImageNet classification by a significant margin. Learn about key concepts such as ReLU nonlinearities, multi-GPU training, local response normalization, overlapping pooling, data augmentation, and dropout. Gain insights into the necessity of larger models, the advantages of CNNs, and the impressive classification results achieved by AlexNet. Understand the paper's impact on the field of artificial intelligence and its contribution to the deep learning revolution.

Syllabus

- Intro & Overview
- The necessity of larger models
- Why CNNs?
- ImageNet
- Model Architecture Overview
- ReLU Nonlinearities
- Multi-GPU training
- Classification Results
- Local Response Normalization
- Overlapping Pooling
- Data Augmentation
- Dropout
- More Results
- Conclusion


Taught by

Yannic Kilcher

Related Courses

TensorFlow を使った畳み込みニューラルネットワーク
DeepLearning.AI via Coursera
Emotion AI: Facial Key-points Detection
Coursera Project Network via Coursera
Transfer Learning for Food Classification
Coursera Project Network via Coursera
Facial Expression Classification Using Residual Neural Nets
Coursera Project Network via Coursera
Apply Generative Adversarial Networks (GANs)
DeepLearning.AI via Coursera