|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/data-science-transformers-nlp/
课程评论：没有评论
课程名称：数据科学：自然语言处理中的变压器 课程概述： 您是否曾好奇如OpenAI的ChatGPT、GPT-4、Gemini Pro、Llama 3、DALL-E、Midjourney和Stable Diffusion等人工智能技术的实际工作原理？在本课程中，您将学习这些开创性应用的基础知识。自从变压器技术出现以来，深度学习的面貌发生了巨变。机器学习能够生成与人类撰写的文本几乎无法区分的内容。在诸多自然语言处理（NLP）任务中，诸如机器翻译、问答、蕴含、命名实体识别等，我们已经达到了新的最先进水平。此外，我们还创建了能够仅通过文本提示生成惊人艺术作品的多模态（文本和图像）模型，并解决了生物分子领域一个长期存在的问题——蛋白质结构预测。 在本课程中，您将学习应用变压器的实用技能，以及变压器和注意力机制的详细理论，课程分为三个主要部分： 第一部分：使用变压器 在这一部分，您将学习如何使用已经为您训练好的变压器。这种训练的成本高达数百万美元，您自己动手尝试并不现实。我们将看到这些预训练模型如何应用于广泛的任务，包括文本分类（如垃圾邮件检测、情感分析、文档分类）、命名实体识别、文本摘要、机器翻译、问答、生成（可信的）文本、屏蔽语言建模（文章改写）以及零样本分类等。 第二部分：微调变压器 在这一部分，您将学习如何在自己的自定义数据集上提高变压器的性能。通过“迁移学习”，您可以利用已经投入数百万美元训练的变压器，使其表现更佳。您将学习如何为现实世界中最常见的任务（如文本分类、实体识别和机器翻译）微调变压器。 第三部分：变压器深入 在这一部分，您将深入学习变压器的真实工作原理。虽然前面的部分已经非常实用，但如果您希望进行创新工作，仅依赖现有库是不够的。全面理解这些模型的人能够从事其他人无法做到的工作，并在竞争激烈的机器学习领域中占得先机。本节将探讨编码器、解码器、BERT、GPT系列（包括GPT-4）的内部工作原理，并学习如何从零开始实现变压器。 建议的先修知识： - 一定的Python编程技能 - 虽然不强制，但CNN和RNN的深度学习知识会有帮助 - 对于深入部分，理解CNN、RNN和Seq2Seq背后的理论非常有用 独特特性： - 每一行代码都有详细讲解，欢迎随时通过邮件提出异议 - 不浪费时间在键盘上“敲打”无谓的代码 - 不惧怕大学水平的数学，掌握其他课程常常忽略的重要算法细节 感谢您的阅读，希望很快见到您！
Ever wondered how AI technologies like OpenAI ChatGPT, GPT-4, Gemini Pro, Llama 3, DALL-E, Midjourney, and Stable Diffusion really work? In this course, you will learn the foundations of these groundbreaking applications.Hello friends!Welcome to Data Science: Transformers for Natural Language Processing.Ever since Transformers arrived on the scene, deep learning hasn't been the same.Machine learning is able to generate text essentially indistinguishable from that created by humansWe've reached new state-of-the-art performance in many NLP tasks, such as machine translation, question-answering, entailment, named entity recognition, and moreWe've created multi-modal (text and image) models that can generate amazing art using only a text promptWe've solved a longstanding problem in molecular biology known as "protein structure prediction"In this course, you will learn very practical skills for applying transformers, and if you want, detailed theory behind how transformers and attention work.This is different from most other resources, which only cover the former.The course is split into 3 major parts:Using TransformersFine-Tuning TransformersTransformers In-DepthPART 1: Using TransformersIn this section, you will learn how to use transformers which were trained for you. This costs millions of dollars to do, so it's not something you want to try by yourself!We'll see how these prebuilt models can already be used for a wide array of tasks, including:text classification (e.g. spam detection, sentiment analysis, document categorization)named entity recognitiontext summarizationmachine translationquestion-answeringgenerating (believable) textmasked language modeling (article spinning)zero-shot classificationThis is already very practical.If you need to do sentiment analysis, document categorization, entity recognition, translation, summarization, etc. on documents at your workplace or for your clients - you already have the most powerful state-of-the-art models at your fingertips with very few lines of code.One of the most amazing applications is "zero-shot classification", where you will observe that a pretrained model can categorize your documents, even without any training at all.PART 2: Fine-Tuning TransformersIn this section, you will learn how to improve the performance of transformers on your own custom datasets. By using "transfer learning", you can leverage the millions of dollars of training that have already gone into making transformers work very well.You'll see that you can fine-tune a transformer with relatively little work (and little cost).We'll cover how to fine-tune transformers for the most practical tasks in the real-world, like text classification (sentiment analysis, spam detection), entity recognition, and machine translation.PART 3: Transformers In-DepthIn this section, you will learn how transformers really work. The previous sections are nice, but a little too nice. Libraries are OK for people who just want to get the job done, but they don't work if you want to do anything new or interesting.Let's be clear: this is very practical.How practical, you might ask?Well, this is where the big bucks are.Those who have a deep understanding of these models and can do things no one has ever done before are in a position to command higher salaries and prestigious titles. Machine learning is a competitive field, and a deep understanding of how things work can be the edge you need to come out on top.We'll look at the inner workings of encoders, decoders, encoder-decoders, BERT, GPT, GPT-2, GPT-3, GPT-3.5, ChatGPT, and GPT-4 (for the latter, we are limited to what OpenAI has revealed).We'll also look at how to implement transformers from scratch.As the great Richard Feynman once said, "what I cannot create, I do not understand".SUGGESTED PREREQUISITES:Decent Python coding skillsDeep learning with CNNs and RNNs useful but not requiredDeep learning with Seq2Seq models useful but not requiredFor the in-depth section: understanding the theory behind CNNs, RNNs, and seq2seq is very usefulUNIQUE FEATURESEvery line of code explained in detail - email me any time if you disagreeNo wasted time "typing" on the keyboard like other courses - let's be honest, nobody can really write code worth learning about in just 20 minutes from scratchNot afraid of university-level math - get important details about algorithms that other courses leave outThank you for reading and I hope to see you soon!
