Lecture
Modern Convolutional Networks and Image Recognition
In course
DEMO: fugiat enim laboris sit
Laborum adipisicing laboris ut incididunt do in cillum. Do veniam eu eu irure do sint consequat. Et enim in irure dolor excepteur non nisi in sit veniam. Occaecat dolore incididunt mollit est ex qui cillum proident ex magna. Irure aliquip eu tempor in sit elit reprehenderit est. Ad deserunt cillum reprehenderit occaecat.
Description
This lecture covers the evolution of deep convolutional networks in the context of image recognition, focusing on the breakthroughs in the ImageNet competitions. It discusses the development of networks like AlexNet, ResNet, and Inception modules, highlighting their impact on improving image recognition accuracy. The lecture also explores the concept of transfer learning for image recognition, showcasing how pre-trained models can be adapted to new tasks with high accuracy.
Instructor
ex id consequat officia
Sunt nisi culpa esse labore irure. Fugiat consequat occaecat quis sit Lorem sint cillum enim sit anim nostrud mollit dolor duis. Magna mollit sit proident eu veniam aute ut dolor laborum exercitation eiusmod. Do do aliquip quis voluptate anim irure culpa irure minim. Et laborum aute consequat tempor sunt laboris sit aute aliquip. Ut nisi excepteur quis labore ullamco officia dolor nisi magna pariatur fugiat id ea culpa.
Official source
About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.
Ontological neighbourhood
Related lectures (34)
Neural Networks: Multilayer Learning
Covers the fundamentals of multilayer neural networks and deep learning, including back-propagation and network architectures like LeNet, AlexNet, and VGG-16.
NFNets: Removing BatchNorm for High-Performance Image Recognition
Explores NFNets as an alternative to BatchNorm in ResNets, achieving high performance on ImageNet.
Deep Learning for Autonomous Vehicles: Learning
Explores learning in deep learning for autonomous vehicles, covering predictive models, RNN, ImageNet, and transfer learning.
Image Recognition: Datasets and Algorithms
Explores a 2019 paper on image recognition, dataset challenges, biases, and the impact of large-scale datasets on deep learning models.
Neural Networks Optimization
Explores neural networks optimization, including backpropagation, batch normalization, weight initialization, and hyperparameter search strategies.