Artificial intelligence (deep learning) has achieved great success in many fields. For example, image recognition, medical image analysis, and self-driving cars. Each application has a specific neural network model and a learning strategy in the field of deep learning. This course will explore the deep learning architecture details and use computer vision-related applications as examples to introduce learning strategies. This course contains not only these essential expositions of deep Learning but also many practical programming tasks. The goal is to give students the ability to build a corresponding deep neural network based on their problems.
\nArtificial intelligence (deep learning) has achieved great success in many fields. For example, image recognition, medical image analysis, and self-driving cars. Each application has a specific neural network model and a learning strategy in the field of deep learning. This course will explore the deep learning architecture details and use computer vision-related applications as examples to introduce learning strategies. This course contains not only these essential expositions of deep Learning but also many practical programming tasks. The goal is to give students the ability to build a corresponding deep neural network based on their problems.<\/p>\n
| \u9031\u6b21 Week<\/th>\n | \u9032\u5ea6\u8aaa\u660e Progress Description<\/th>\n<\/tr>\n |
|---|---|
| 1<\/td>\n | Course Introduction<\/td>\n<\/tr>\n |
| 2<\/td>\n | Machine learning: The data-driven approach<\/td>\n<\/tr>\n |
| 3<\/td>\n | Loss Functions and Optimization<\/td>\n<\/tr>\n |
| 4<\/td>\n | Introduction to Neural Networks \/ Multilayer Perceptron<\/td>\n<\/tr>\n |
| 5<\/td>\n | Convolutional Neural Networks<\/td>\n<\/tr>\n |
| 6<\/td>\n | Intro to Pytorch and Tensorflow under Ubuntu System<\/td>\n<\/tr>\n |
| 7<\/td>\n | CNN Architectures: AlexNet, VGG \/ Final Project Proposal due<\/td>\n<\/tr>\n |
| 8<\/td>\n | Training Neural Networks<\/td>\n<\/tr>\n |
| 9<\/td>\n | In-class midterm<\/td>\n<\/tr>\n |
| 10<\/td>\n | CNN Architectures: GoogLeNet, ResNet, DenseNet, EfficientNet, etc<\/td>\n<\/tr>\n |
| 11<\/td>\n | Proposal presentation<\/td>\n<\/tr>\n |
| 12<\/td>\n | Object Detection<\/td>\n<\/tr>\n |
| 13<\/td>\n | Semantic Segmentation<\/td>\n<\/tr>\n |
| 14<\/td>\n | Unsupervised Learning: Generative Models<\/td>\n<\/tr>\n |
| 15<\/td>\n | Recurrent Neural Networks<\/td>\n<\/tr>\n |
| 16<\/td>\n | Semi-Supervised learning<\/td>\n<\/tr>\n |
| 17<\/td>\n | Invited talk<\/td>\n<\/tr>\n |
| 18<\/td>\n | Final Project Presentation<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n \u52a0\u7c3d\u8acb\u53c3\u8003\u7cfb\u4e0a\u516c\u544a<\/p>\n |