|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/hands-on-gen-ai-bert-for-quant-fin-python-modeling-101/
课程评论：没有评论
课程名称：生成AI在量化金融中的Python建模101 课程概述： 本课程旨在为初学者提供Python和生成AI的基础知识，重点是生成AI在量化金融建模中的应用。通过实际操作，学习如何使用ChatGPT（类似于Python中的Copilot）进行代码调试。课程介绍了基于GPT的聊天界面，用于查询、重新运行和通过手动配置调整Hugging模型。 课程内容包括： 1. 精细调优BERT模型与逻辑回归层的结合。 2. 部署模型以实现实时分析，学习如何使用Flask/FastAPI来服务文本或数据生成模型。 课程主题： - BERT与GPT简介 - Torch与张量简介 - FastAPI应用程序入门 - 内存中的逻辑回归模型 - 介绍变换器模型，如Trainer、TrainingArguments、BertTokenizer、BertForSequenceClassification - 生成AI在金融中的应用 - Hugging Face的预训练模型、在线帐户及本地训练 - 模型细调的入门，使用轻量级DistilBERT进行本地训练 - 使用Hugging Face映射指令到后端以查询模拟结果并重新运行模拟 - 将逻辑回归连接到聊天前端 - Hugging Face的当前局限性（截至2024年12月） - 设置OpenAI API和Hugging Face 未来工作重点： - 特征选择 - 基于真实数据的模型重训练 - 生成AI在数据分析中的应用（合成、异常检测） 此课程还涵盖了逻辑回归模型的输入模式定义、训练参数的优化，以及使用joblib或pickle库保存和加载逻辑回归模型。课程教授如何使用Postman、cURL或任何能够发送HTTP POST请求的客户端。 未来展望包括增加输入验证、特征追踪、超参数验证等功能，并返回预测概率。
Python & Generative AI 101 for BeginnersIn this course we do Hands-on Gen AI for Quant Fin Python Modeling 101. We often fix our code using ChatGPT which is similar to Copilot on Python but since we use notebook we use ChatGPT.Python Generative AI for Modeling with ChatGpt & Copilot. GPT-Powered Chat Interface for querying rerunning tunning using manual config for Hugging is showed. This Fine Tuning and connecting Chat feature to Logistic Regression backend can be extended with better products like Open AI. We query an already saved logistic regression model with a GPT-powered chat interface to retrain and change features and other changes. Course revolves around two projects:Fine-Tuning BERT with a Logistic Regression LayerDeploying Models for Real-Time Analytics: How to use tools like Flask/FastAPI to serve a text-based or data-generating model.Topics IntroducedIntro to BERT vs GPT Intro to Torch and TensorsIntro to FastAPI AppIn-memory Logistic Regression modelIntro to transformers like Trainer, TrainingArguments, BertTokenizer, BertForSequenceClassificationIntro to Gen AI in FinanceIntro to BERT ModelsHugging face pre trained models, online account, local trainingIntro to Fine tuning models, using the light DistilBERT, local training Using hugging face to map commands for backend to query simulated results, re-run simulationConnecting Logistic regression to front end of chatLimitation of hugging face as of today (Dec 2024Set up OpenAI API and hugging faceFuture Work:Feature Selection Model Retraining on Real DataIntro to application of Gen AI in Data Analytics (synthesis anamoly and detection). Applications of Generative AI in Analytics: Data synthesis, anomaly detection, and predictive modeling.Using open to get all spectrum of instruction to query Model (we used 4-5 cases manual)For Logsitic regression we understand what all can we do. Define the input schema for retraining. Define the training arguments with optimizations. We usse libraries like joblib or pickle to save and load the logistic regression model. Postman, cURL, or any client capable of sending HTTP POST requestsFuture work: Other Enhancements such as adding input validation, feature tracking, hyperparameter validation, and returning probabilities for predictions.
