Machine Learning and Generative AI
Description
In this course we will investigate exciting world of Machine Learning and Generative AI, focusing on popular models of ML and their implementation in Python, Language Learning Models (LLM) like OpenAI's GPT-4, GPT4All, Llama, Alpaca and much more. The purpose of the course is to offer theoretical understanding along with hands-on experience in working with these sophisticated models, from tweaking their parameters to mastering prompt engineering for a variety of applications, such as building an interactive ChatBot.
Intended audience
The course is designed for programmers with a basic knowledge of Python. Programmers with limited Python experience will comprehensive set of practice exercises in order to help participants bridge the knowledge gap and reach the necessary proficiency level for the course. The goal of these materials is to ensure that all participants have the foundational knowledge required to succeed in the course.
Topics
Introduction to ML – applications, various types of ML
What is ML and what are the problems this field intends to solve?
What are the different types of ML algorithms?
How does ML algorithm differ from a standard algorithm?
Data preparation and cleaning.
The problem with huge amount of data.
Data Visualization – gaining insights from graphs.
Data cleaning – removing duplications, handling missing values, identifying outliers.
Data enrichment – add valuable information.
Features engineering – reducing the dimensionality of the data set.
Linear regression using Scikit-learn
What is linear regression?
The theory behind regression.
Cost functions.
Implementing linear regression in scikit-learn.
Classification using scikit-learn.
What is classification?
The theory behind classification.
The logistic regression function.
Implementing classification in scikit-learn.
Overview of some other ML models – decision trees, SVM, ensemble methods.
Present some well known and popular ML algorithms, their pros and cons.
Overview the scikit-learn classes that implement these algorithms.
Introduction to AI and LLM (GPT)
Theory and Intro to LLM and AI
GPT under the hood with practical examples
Hands-on excipients tweaking GPT
Prompt Engineering
Introduction Prompt Engineering
Guidelines for working with Prompt Engineering
Iterative Prompt Development
Working with prompts
Summarizing with Prompt Engineering
Inferring with Prompt Engineering
Transforming Information with Prompts
Using LLMs to Expanding on ideas and information
Building a ChatBot
Mastering the OpenAI API
Introduction to OpenAI API
Building a ChatGPT in JavaScript
Exploring DALL-E: AI-Driven Image Generator
Building an AI SQL Query Generator
Integrating Natural Language Processing with OpenAI library
Summary
LangChain
Introduction to LangChain
LangChain Modules
Prompts with LangChain
Using Index and Embeddings
Controlling LLM Memory
Chaining LLM and actions
Building LangChain Agents
האם אתה בטוח שאתה רוצה לסגור את הטופס ולאבד את כל השינויים?
