Deep Learning for Coders。
https://course.fast.ai/
Practical Deep Learning for Coders
Deep Learning for Coders with fastai and PyTorch: AI Applications Without a PhD。
Welcome to Practical Deep Learning for Coders. This web site covers the book and the 2020 version of the course, which are designed to work closely together. If you haven't yet got the book, you can buy it here. It's also freely available as interactive Jupyter Notebooks; read on to learn how to access them..
How do I get started?
If you're ready to dive in right now, here's how to get started. If you want to know more about this course, read the next sections, and then come back here.
To watch the videos, click on the Lessons section in the navigation sidebar. The lessons all have searchable transcripts; click "Transcript Search" in the top right panel to search for a word or phrase, and then click it to jump straight to video at the time that appears in the transcript. The videos are all captioned and also translated into Chinese (简体中文) and Spanish; while watching the video click the "CC" button to turn them on and off, and the setting button to change the language.
Each video covers a chapter from the book. The entirety of every chapter of the book is available as an interactive Jupyter Notebook. Jupyter Notebook is the most popular tool for doing data science in Python, for good reason. It is powerful, flexible, and easy to use. We think you will love it! Since the most important thing for learning deep learning is writing code and experimenting, it's important that you have a great platform for experimenting with code.
To get started, we recommend using a Jupyter Server from one of the recommended online platforms (click the links for instructions on how to use these for the course):
- Colab: A popular free service from Google. Google have changed the notebook platform quite a lot, so keyboard shortcuts are different, and not everything works (e.g. much of chapter 2 doesn't work because Colab doesn't support creating web app GUIs)
- Gradient: Unlike Colab, this is a "real" Jupyter Notebook so everything in the course works. It also provides space to save your notebooks and models. However, sometimes the free servers get over-loaded, and when that happens it's impossible to connect.
If you are interested in the experience of running a full Linux server, you can consider DataCrunch.io (very new service so we don't know how good it is, no setup required, extremely good value and extremely fast GPUs), or Google Cloud (extremely popular service, very reliable, but the fastest GPUs are far more expensive). We strongly suggest using one of the recommended online platforms for running the notebooks, and to not use your own computer, unless you're very experienced with Linux system adminstration and handling GPU drivers, CUDA, and so forth.
If you need help, there's a wonderful online community ready to help you at forums.fast.ai. Before asking a question on the forums, search carefully to see if your question has been answered before. (The forum system won't let you post until you've spent a few minutes on the site reading existing topics.) One bit that many students find tricky is getting signed up for the Bing API for the image download task in lesson 2; here's a helpful forum post explaining how to get the Bing API key you'll need for downloading images.
Is this course for me?
Thank you for letting us join you on your deep learning journey, however far along that you may be! Previous fast.ai courses have been studied by hundreds of thousands of students, from all walks of life, from all parts of the world. Many students have told us about how they've become multiple gold medal winners of international machine learning competitions, received offers from top companies, and having research papers published. For instance, Isaac Dimitrovsky told us that he had "been playing around with ML for a couple of years without really grokking it... [then] went through the fast.ai part 1 course late last year, and it clicked for me". He went on to achieve first place in the prestigious international RA2-DREAM Challenge competition! He developed a multistage deep learning method for scoring radiographic hand and foot joint damage in rheumatoid arthritis, taking advantage of the fastai library.
It doesn't matter if you don't come from a technical or a mathematical background (though it's okay if you do too!); we wrote this course to make deep learning accessible to as many people as possible. The only prerequisite is that you know how to code (a year of experience is enough), preferably in Python, and that you have at least followed a high school math course. The first three chapters have been explicitly written in a way that will allow executives, product managers, etc. to understand the most important things they'll need to know about deep learning -- if that's you, just skip over the code in those sections.
Deep learning is a computer technique to extract and transform data–-with use cases ranging from human speech recognition to animal imagery classification–-by using multiple layers of neural networks. A lot of people assume that you need all kinds of hard-to-find stuff to get great results with deep learning, but as you'll see in this course, those people are wrong. Here's a few things you absolutely don't need to do world-class deep learning:
| Myth (don't need) | Truth |
|---|---|
| Lots of math | Just high school math is sufficient |
| Lots of data | We've seen record-breaking results with <50 items of data |
| Lots of expensive computers | You can get what you need for state of the art work for free |
Deep learning has power, flexibility, and simplicity. That's why we believe it should be applied across many disciplines. These include the social and physical sciences, the arts, medicine, finance, scientific research, and many more. Here's a list of some of the thousands of tasks in different areas at which deep learning, or methods heavily using deep learning, is now the best in the world:
- Natural language processing (NLP) Answering questions; speech recognition; summarizing documents; classifying documents; finding names, dates, etc. in documents; searching for articles mentioning a concept
- Computer vision Satellite and drone imagery interpretation (e.g., for disaster resilience); face recognition; image captioning; reading traffic signs; locating pedestrians and vehicles in autonomous vehicles
- Medicine Finding anomalies in radiology images, including CT, MRI, and X-ray images; counting features in pathology slides; measuring features in ultrasounds; diagnosing diabetic retinopathy
- Biology Folding proteins; classifying proteins; many genomics tasks, such as tumor-normal sequencing and classifying clinically actionable genetic mutations; cell classification; analyzing protein/protein interactions
- Image generation Colorizing images; increasing image resolution; removing noise from images; converting images to art in the style of famous artists
- Recommendation systems Web search; product recommendations; home page layout
- Playing games Chess, Go, most Atari video games, and many real-time strategy games
- Robotics Handling objects that are challenging to locate (e.g., transparent, shiny, lacking texture) or hard to pick up
- Other applications Financial and logistical forecasting, text to speech, and much more...
Who we are
We are Sylvain Gugger and Jeremy Howard, your guides on this journey. We're the co-authors of fastai, the software that you'll be using throughout this course.
Jeremy has been using and teaching machine learning for around 30 years. He started using neural networks 25 years ago. During this time, he has led many companies and projects that have machine learning at their core, including founding the first company to focus on deep learning and medicine, Enlitic, and taking on the role of President and Chief Scientist of the world's largest machine learning community, Kaggle. He is the co-founder, along with Dr. Rachel Thomas, of fast.ai, the organization that built the course this course is based on.
Sylvain has written 10 math textbooks, covering the entire advanced French maths curriculum! He is now a researcher at Hugging Face, and was previously a researcher at fast.ai.
We care a lot about teaching. In this course, we start by showing how to use a complete, working, very usable, state-of-the-art deep learning network to solve real-world problems, using simple, expressive tools. And then we gradually dig deeper and deeper into understanding how those tools are made, and how the tools that make those tools are made, and so on… We always teach through examples. We ensure that there is a context and a purpose that you can understand intuitively, rather than starting with algebraic symbol manipulation.
The software you will be using
In this course, you'll be using PyTorch and fastai.
We've completed hundreds of machine learning projects using dozens of different packages, and many different programming languages. At fast.ai, we have written courses using most of the main deep learning and machine learning packages used today. We spent over a thousand hours testing PyTorch before deciding that we would use it for future courses, software development, and research. PyTorch is now the world's fastest-growing deep learning library and is already used for most research papers at top conferences.
PyTorch works best as a low-level foundation library, providing the basic operations for higher-level functionality. The fastai library is the most popular library for adding this higher-level functionality on top of PyTorch. In this course, as we go deeper and deeper into the foundations of deep learning, we will also go deeper and deeper into the layers of fastai. This course covers version 2 of the fastai library, which is a from-scratch rewrite providing many unique features.
What you will learn
After finishing this course you will know:
- How to train models that achieve state-of-the-art results in:
- Computer vision, including image classification (e.g., classifying pet photos by breed), and image localization and detection (e.g., finding where the animals in an image are)
- Natural language processing (NLP), including document classification (e.g., movie review sentiment analysis) and language modeling
- Tabular data (e.g., sales prediction) with categorical data, continuous data, and mixed data, including time series
- Collaborative filtering (e.g., movie recommendation)
- How to turn your models into web applications, and deploy them
- Why and how deep learning models work, and how to use that knowledge to improve the accuracy, speed, and reliability of your models
- The latest deep learning techniques that really matter in practice
- How to implement stochastic gradient descent and a complete training loop from scratch
- How to think about the ethical implications of your work, to help ensure that you're making the world a better place and that your work isn't misused for harm
Here are some of the techniques covered (don't worry if none of these words mean anything to you yet--you'll learn them all soon):
- Random forests and gradient boosting
- Affine functions and nonlinearities
- Parameters and activations
- Random initialization and transfer learning
- SGD, Momentum, Adam, and other optimizers
- Convolutions
- Batch normalization
- Dropout
- Data augmentation
- Weight decay
- Image classification and regression
- Entity and word embeddings
- Recurrent neural networks (RNNs)
- Segmentation
- And much more
from https://github.com/fastai/course20
-----
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被55个国家的300所大学用于教学。
http://zh.d2l.ai/
动手学深度学习（Dive into Deep Learning，D2L.ai）
第一版：zh-v1.D2L.ai | 第二版预览版：zh.D2L.ai | 安装和使用书中源代码：第一版 第二版 | 当前版本: v2.0.0-alpha2
理解深度学习的最佳方法是学以致用。
本开源项目代表了我们的一种尝试：我们将教给读者概念、背景知识和代码；我们将在同一个地方阐述剖析问题所需的批判性思维、解决问题所需的数学知识，以及实现解决方案所需的工程技能。
我们的目标是创建一个为实现以下目标的统一资源：
- 所有人均可在网上免费获取；
- 提供足够的技术深度，从而帮助读者实际成为深度学习应用科学家：既理解数学原理，又能够实现并不断改进方法；
- 包含可运行的代码，为读者展示如何在实际中解决问题。这样不仅直接将数学公式对应成实际代码，而且可以修改代码、观察结果并及时获取经验；
- 允许我们和整个社区不断快速迭代内容，从而紧跟仍在高速发展的深度学习领域；
- 由包含有关技术细节问答的论坛作为补充，使大家可以相互答疑并交换经验。
本书的第二版
虽然纸质书第一版已经出版，但深度学习领域依然在迅速发展。为了得到来自更广泛的英文开源社区的帮助，从而提升本书质量，本书的第二版正在用英文写。英文版正不断被搬回中文版中。
目前，英文版已超过160节（中文版共96节），例如增加了理论背景（如优化收敛分析）、硬件设计（如参数服务器）、全新篇章（如注意力机制、推荐系统、深度学习的数学、生成对抗网络）、应用种类（如自然语言推断）、模型种类（如Transformer、BERT）等，并优化重组了大量章节（如将自然语言处理篇章按从预训练表征、到模型设计、再到下游应用重构）。
欢迎关注本书第二版的英文开源项目。
中英文教学资源
加州大学伯克利分校 2019 年春学期 Introduction to Deep Learning 课程教材（同时提供含教学视频地址的中文版课件）。
学术界推荐
"Dive into this book if you want to dive into deep learning!"
— 韩家炜，ACM 院士、IEEE 院士，美国伊利诺伊大学香槟分校计算机系 Michael Aiken Chair 教授
"This is a highly welcome addition to the machine learning literature."
— Bernhard Schölkopf，ACM 院士、德国国家科学院院士，德国马克斯•普朗克研究所智能系统院院长
"书中代码可谓‘所学即所用’。"
— 周志华，ACM 院士、IEEE 院士、AAAS 院士，南京大学计算机科学与技术系主任
"这本书可以帮助深度学习实践者快速提升自己的能力。"
— 张潼，ASA 院士、IMS 院士，香港科技大学计算机系和数学系教授
工业界推荐
"一本优秀的深度学习教材，值得任何想了解深度学习何以引爆人工智能革命的人关注。"
— 黄仁勋，NVIDIA创始人 & CEO
"《动手学深度学习》是最适合工业界研发工程师学习的。我毫无保留地向广大的读者们强烈推荐。"
— 余凯，地平线公司创始人 & CEO
"强烈推荐这本书！我特别赞赏这种手脑一体的学习方式。"
— 漆远，蚂蚁金服副总裁、首席AI科学家
"《动手学深度学习》是一本很容易让学习者上瘾的书。"
— 沈强，将门创投创始合伙人
from https://github.com/d2l-ai/d2l-zh
-------
https://github.com/scutan90/DeepLearning-500-questions
No comments:
Post a Comment