40 lines
1.4 KiB
Plaintext
40 lines
1.4 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "e65d2ddd",
|
|
"metadata": {
|
|
"origin_pos": 0
|
|
},
|
|
"source": [
|
|
"# 线性神经网络\n",
|
|
":label:`chap_linear`\n",
|
|
"\n",
|
|
"在介绍深度神经网络之前，我们需要了解神经网络训练的基础知识。\n",
|
|
"本章我们将介绍神经网络的整个训练过程，\n",
|
|
"包括：定义简单的神经网络架构、数据处理、指定损失函数和如何训练模型。\n",
|
|
"为了更容易学习，我们将从经典算法————*线性*神经网络开始，介绍神经网络的基础知识。\n",
|
|
"经典统计学习技术中的线性回归和softmax回归可以视为线性神经网络，\n",
|
|
"这些知识将为本书其他部分中更复杂的技术奠定基础。\n",
|
|
"\n",
|
|
":begin_tab:toc\n",
|
|
" - [linear-regression](linear-regression.ipynb)\n",
|
|
" - [linear-regression-scratch](linear-regression-scratch.ipynb)\n",
|
|
" - [linear-regression-concise](linear-regression-concise.ipynb)\n",
|
|
" - [softmax-regression](softmax-regression.ipynb)\n",
|
|
" - [image-classification-dataset](image-classification-dataset.ipynb)\n",
|
|
" - [softmax-regression-scratch](softmax-regression-scratch.ipynb)\n",
|
|
" - [softmax-regression-concise](softmax-regression-concise.ipynb)\n",
|
|
":end_tab:\n"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"language_info": {
|
|
"name": "python"
|
|
},
|
|
"required_libs": []
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
} |