# Convolutional Neural Networks

在 Convolutional Neural Networks 中

將會教導如何建立 CNN 然後應用在 image data 上

因為有了 CNN ，所以 computer vision 能夠快速進步

應用在各式各樣的專案中，如

* safe autonomous driving
* accurate face recognition
* automatic reading of radiology images

在這個課堂上，將可以

* 了解如何建立 CNN，甚至是他的變形，如 residual networks
* 了解如何應用 CNN 在 visual detection 和 recognition tasks
* 了解如何使用 neural style transfer 來產生藝術作品
* 將 CNN 應用於更多 image, video, 2D, 3D data

這將是 Deep learning 的第四堂課 !

## Foundations of Convolutional Neural Networks

了解 CNNs 裡的基本 layers 運作 (pooling, convolution)

並能夠堆疊他們來處理 multi-class image classification

* Computer vision
* Edge Detection
* Strided Convolutions
* Convolutions Over Volume
* Simple Convolutional Network
* Pooling Layers

## Deep convolutional models: case studies

來看一些實際在 research papers 中的 CNNs 實作技術

* Classic Networks
* ResNets
* Networks in Networks and 1x1 Convolutions
* Inception Network
* Transfer Learning
* Data Augmentation

## Object detection

利用學到的 CNNs 來實作 computer vision 最困難但最熱門的領域 : object detection

* Object Localization
* Landmark Detection
* Object Detection
* Convolutional Implementation of Sliding Windows
* Bounding Box Predictions
* Intersection Over Union
* Non-max Suppressio
* Anchor Boxes
* YOLO Algorithm

## Special applications: Face recognition & Neural style transfer

了解更多 CNNs 可以應用的範圍，例如 art generation, face recognition

我們將實際設計 algorithm 來做出以上兩件事 !

* One Shot Learning
* Siamese Network
* Triplet Loss
* Face Verification and Binary Classification
* Neural style transfer
* deep ConvNets learning
* Content Cost Function
* Style Cost Function
* 1D and 3D Generalizations


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://sejkai.gitbook.io/academic/deep-learning/convolutional-neural-networks.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.