The introduction of AI and Machine Learning with Python

Take a look at AI and Machine Learning (ML) and learn how to use advanced algorithms to solve real-world problems. This class will show you how to do a lot of different things with data, like make advanced models and test them.

By the end of the course the students will be able to:

– Make a lot of different AI systems and models.

– Determine how AI can work, including how it interacts with people and the environment.

– Use ideas and methods from natural language processing to automatically extract information from the text (NLP).

– Make deep learning models in Python with TensorFlow and Keras and train them with real-world datasets to make them better.

Machine Learning

• Examples of Machine Learning Algorithms are shown.
• Machine Learning: There are different types of machine learning.
• Supervised
• Unsupervised
• Reinforcement
• There are different types of supervised learning, like the following:
• Classification
• Regression

Learning under supervision – Regression

• Knowing how to use Boxplot and the features of the Boxplot function.
• Using the train test split function, you can learn more about training and testing data.
• Creating a machine learning model to solve a regression problem of predicting weight by using python programming to train and test the model.

An example: Supervised Learning – Binary Classification

• In this lesson, we’ll learn about Binary Classification.
• All about the Decision Tree Algorithm.
• A look at the Random Forest Algorithm.
• Use of a Confusion Matrix to see how well the classification model works.
• Using python programming, I’m going to use the Decision Tree and Random Forest algorithms to build a classification model that can predict diabetic patients, and I’m going to use a confusion matrix to see how well both algorithms work.

This is what happens when someone watches you learn.

• Knowing how to solve Multi-class Classification problems.
• One-on-one method:
• One-vs.Many methods:
• The goal of this project is to use both a One-vs. One and One-vs.Rest approach to solving a multi-class classification problem for Iris flower prediction. Also, using a confusion matrix to see how well both methods worked.

Clustering is a method for learning without being told how to do it.

• Getting to know Unsupervised Learning.
• It is important to use unsupervised learning.
• Unsupervised learning: There are different types of this.
• Clustering
• Association
• A KMeans Algorithm class is going on right now.
• To figure out K, use the Elbow method.
• Using python, I’m going to standardize the data and use the KMeans algorithm to make groups in the dataset.

An example of unsupervised learning: customer segmentation

• Getting to know customer segmentation.
• Types of characteristics that can be used to separate things.
• The idea of targeting.
• To do: Use the KMeans algorithm for this project. Then, look at the clusters to find the right customers to target.

Association Rule Mining is a method for unsupervised learning.

• Recognizing the problems with the association.
• This is called “Market Basket Analysis.”
• Apriori Algorithm is being worked on.
• Metrics to look for when evaluating the rules:
• Support
• Confidence
• Lift
• Steps to find Association Rules.
• Project: Use python programming to make the Apriori algorithm work for Market Basket Analysis.

Recommendation System – A Content-Based System

• Getting to know Recommendation Systems.
• I’m working on systems that make suggestions.
• These are some of the different types of systems that can help you find what you want.
• Working together
• In this project, you’ll build a content-based recommendation system that uses the K Nearest Neighbor (KNN) algorithm to help you find the best car for you based on what you like about cars.

– Collaborative Filtering – Recommendation System

• Understanding the Collaborative filtering method.
• In collaborative filtering, there are different ways to do it.
• Users-based:
• Item-based:
• Building a movie recommendation system with item-based collaborative filtering and data from a movie rating matrix is the goal of this project.

Sentiment Analysis is part of Natural Language Processing.

• There are many different kinds of Natural Language Processing (NLP)
• There are a lot of things that NLP can be used for.
• These are some of the most important NLP tasks.
• Creating a machine learning model that can figure out the mood of a sentence is the goal of this project (Application of NLP).

Deep Learning – Computer Vision

• Getting to know Deep Learning.
• Networks that use Neural Networks and that use Deep Neural Networks.

Images can be classed with a bonus class.

• Take a look at the people who have already been trained.
• ResNet50 model was built with data from ImageNet.
• Project: Use the ResNet50 model to group images (predicting what the image represents).