> For the complete documentation index, see [llms.txt](https://sejkai.gitbook.io/academic/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://sejkai.gitbook.io/academic/deep-learning/neural-network-and-deep-learning.md).

# Neural Networks and Deep Learning

在 Neural Networks and Deep Learning 中

我們將會學習 deep learning 的基礎 :

* 知道 deep learning 的主流技術
* 能夠 build, train, apply 一個 fully connected 的 deep neural networks
* 知道如何 implement 一個 vectorized neural networks
* 了解 neural networks architecture 的 key parameters

而這也是 Deep learning 必修的第一堂課 !

## Introduction

認識一些 NN 的專業名詞，以及他們應該被應用在哪裡

* what is nn
* Supervised in nn
* why dl taking off

## Basics

讓我們用 NN 的 mindsets 來解決 ML 問題

* logistic in nn
* vectorization

## Shallow neural networks

用單層的 hidden layer 來試作 forward, backward propogation

* nn representation
* vectorized implementation
* non-linear activation function
* gradient descent
* backpropogation preview
* random initialization

## Deep neural network

知道為何要使用 "deep" 的 nn

* forward propogation
* why deep ?
* forward & backward propogation
* parameters (weight, bias)
* hyperparameters (experience, learning rates, iter, layers)