|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/deep-learning-prerequisites-the-numpy-stack-in-python/
课程评论：没有评论
以下是中国大学慕课《Python中的Numpy栈：深度学习先修课程（V2+）》的课程内容概要： 本课程旨在解决学习者在深入学习深度学习、机器学习和数据科学时遇到的关键障碍：未能熟练掌握Python中的Numpy栈。许多学员在理论理解后，却难以将概念转化为实际代码。本课程将重点展示在Numpy栈中实现深度学习和数据科学常用功能的方法。 课程核心内容包括： * **Numpy**：作为基础构建块，课程将深入讲解Numpy数组（ndarray）的概念，理解其作为数学对象（向量、矩阵）的特性，以及如何进行向量化和矩阵运算（加、减、乘、点积、逆、行列式、求解线性方程组）。特将通过演示证明Numpy向量化操作在速度上的优势。 * **Pandas**：课程将介绍Pandas如何简化数据集处理，重点讲解其核心对象DataFrame，并与R语言进行类比。内容涵盖使用Pandas高效加载数据集、按列/行过滤数据以及应用函数（apply）等机器学习常用操作。Pandas的表格化数据处理方式也与SQL的表结构相似。 * **Matplotlib**：在数据加载和处理之后，课程将围绕数据可视化展开，主要介绍Matplotlib在绘制常用图表（折线图、散点图、直方图）和显示图像方面的应用。 * **Scipy**：Scipy被定位为Numpy的扩展库。课程将介绍Scipy如何利用Numpy的基础构建块实现更特定的功能，包括但不限于：统计计算（PDF、CDF、抽样、统计检验）、信号处理（卷积、傅里叶变换）等。 **课程定位**：本课程是为那些理解深度学习或机器学习的理论，但难以将这些算法从零开始转化为可执行代码的学习者设计的。课程强调“实践出真知”，鼓励学员动手实现算法，而非仅仅调用现有库的简单函数。 **建议先修知识**：矩阵运算、概率论、Python编程基础（if/else、循环、列表、字典、集合），以及对点积、矩阵求逆、高斯概率分布等概念的“为何”以及“用途”有基本理解。 **重要提示**：本课程是作者“从零实现机器学习算法”系列课程的基石，有助于真正理解算法的运行机制，而非仅仅完成简单的库调用。
Ever wondered how AI technologies like OpenAI ChatGPT, GPT-4, DALL-E, Midjourney, and Stable Diffusion really work? In this course, you will learn the foundations of these groundbreaking applications.Welcome! This is Deep Learning, Machine Learning, and Data Science Prerequisites: The Numpy Stack in Python.One question or concern I get a lot is that people want to learn deep learning and data science, so they take these courses, but they get left behind because they don't know enough about the Numpy stack in order to turn those concepts into code.Even if I write the code in full, if you don't know Numpy, then it's still very hard to read.This course is designed to remove that obstacle - to show you how to do things in the Numpy stack that are frequently needed in deep learning and data science.So what are those things?Numpy. This forms the basis for everything else. The central object in Numpy is the Numpy array, on which you can do various operations.The key is that a Numpy array isn't just a regular array you'd see in a language like Java or C++, but instead is like a mathematical object like a vector or a matrix.That means you can do vector and matrix operations like addition, subtraction, and multiplication.The most important aspect of Numpy arrays is that they are optimized for speed. So we're going to do a demo where I prove to you that using a Numpy vectorized operation is faster than using a Python list.Then we'll look at some more complicated matrix operations, like products, inverses, determinants, and solving linear systems.Pandas. Pandas is great because it does a lot of things under the hood, which makes your life easier because you then don't need to code those things manually.Pandas makes working with datasets a lot like R, if you're familiar with R.The central object in R and Pandas is the DataFrame.We'll look at how much easier it is to load a dataset using Pandas vs. trying to do it manually.Then we'll look at some dataframe operations useful in machine learning, like filtering by column, filtering by row, and the apply function.Pandas dataframes will remind you of SQL tables, so if you have an SQL background and you like working with tables then Pandas will be a great next thing to learn about.Since Pandas teaches us how to load data, the next step will be looking at the data. For that we will use Matplotlib.In this section we'll go over some common plots, namely the line chart, scatter plot, and histogram.We'll also look at how to show images using Matplotlib.99% of the time, you'll be using some form of the above plots.Scipy.I like to think of Scipy as an addon library to Numpy.Whereas Numpy provides basic building blocks, like vectors, matrices, and operations on them, Scipy uses those general building blocks to do specific things.For example, Scipy can do many common statistics calculations, including getting the PDF value, the CDF value, sampling from a distribution, and statistical testing.It has signal processing tools so it can do things like convolution and the Fourier transform.In sum:If you've taken a deep learning or machine learning course, and you understand the theory, and you can see the code, but you can't make the connection between how to turn those algorithms into actual running code, this course is for you."If you can't implement it, you don't understand it"Or as the great physicist Richard Feynman said: "What I cannot create, I do not understand".My courses are the ONLY courses where you will learn how to implement machine learning algorithms from scratchOther courses will teach you how to plug in your data into a library, but do you really need help with 3 lines of code?After doing the same thing with 10 datasets, you realize you didn't learn 10 things. You learned 1 thing, and just repeated the same 3 lines of code 10 times...Suggested Prerequisites:matrix arithmeticprobabilityPython coding: if/else, loops, lists, dicts, setsyou should already know "why" things like a dot product, matrix inversion, and Gaussian probability distributions are useful and what they can be used forWHAT ORDER SHOULD I TAKE YOUR COURSES IN?:Check out the lecture "Machine Learning and AI Prerequisite Roadmap" (available in the FAQ of any of my courses)
