Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Zero To Mastery

Complete A.I. Machine Learning and Data Science: Zero to Mastery

via Zero To Mastery

Go to class Write review

Overview

One of the most popular, highly rated A.I., machine learning and data science bootcamps online. It's also the most modern and up-to-date. Guaranteed. You'll go from complete beginner with no prior experience to getting hired as a Machine Learning Engineer this year. You'll learn Data Science, Data Analysis, Machine Learning (Artificial Intelligence), Python, Python with Tensorflow, Pandas & more!
  • Deep Learning, Transfer Learning and Neural Networks using the latest Tensorflow 2.0
  • Present Data Science projects to management and stakeholders
  • Real life case studies and projects to understand how things are done in the real world
  • Implement Machine Learning algorithms
  • How to improve your Machine Learning models
  • Build a portfolio of work to have on your resume
  • Supervised and Unsupervised Learning
  • Explore large datasets using data visualization tools like Matplotlib and Seaborn
  • Learn NumPy and how it is used in Machine Learning
  • Learn to use the popular library Scikit-learn in your projects
  • Master Machine Learning and how use it on the job
  • Use modern tools that big tech companies like Google, Apple, Amazon and Facebook use
  • Learn which Machine Learning model to choose for each type of problem
  • Learn best practices when it comes to Data Science workflow
  • Learn how to program in Python using the latest Python 3
  • Learn to pre-process data, clean data, and analyze large data
  • Developer Environment setup for Data Science and Machine Learning
  • Machine Learning on Time Series data
  • Explore large datasets and wrangle data using Pandas
  • A portfolio of Data Science and Machine Learning projects to apply for jobs in the industry with all code and notebooks provided
  • Learn about Data Engineering and how tools like Hadoop, Spark, and Kafka are used in the industry
  • Learn how to apply Transfer Learning
  • Learn to perform Classification and Regression modelling

Syllabus

  •   Introduction
    • Complete A.I. Machine Learning and Data Science: Zero to Mastery
    • Course Outline
    • Exercise: Meet Your Classmates and Instructor
    • Course Resources
    • Your First Day
    • ZTM Plugin + Understanding Your Video Player
    • Set Your Learning Streak Goal
    • Asking Questions + Getting Help
  •   Machine Learning 101
    • What Is Machine Learning?
    • AI/Machine Learning/Data Science
    • Exercise: Machine Learning Playground
    • How Did We Get Here?
    • Exercise: YouTube Recommendation Engine
    • Types of Machine Learning
    • Are You Getting It Yet?
    • What Is Machine Learning? Round 2
    • Section Review
    • Let's Have Some Fun (+ Free Resources)
  •   Machine Learning and Data Science Framework
    • Section Overview
    • Introducing Our Framework
    • 6 Step Machine Learning Framework
    • Types of Machine Learning Problems
    • Types of Data
    • Types of Evaluation
    • Features In Data
    • Modelling - Splitting Data
    • Modelling - Picking the Model
    • Modelling - Tuning
    • Modelling - Comparison
    • Overfitting and Underfitting Definitions
    • Experimentation
    • Tools We Will Use
    • Optional: Elements of AI
    • Unlimited Updates
  •   The 2 Paths
    • The 2 Paths
    • Python + Machine Learning Monthly
  •   Data Science Environment Setup
    • Section Overview
    • Introducing Our Tools
    • What is Conda?
    • Conda Environments
    • Mac Environment Setup
    • Mac Environment Setup 2
    • Windows Environment Setup
    • Windows Environment Setup 2
    • Linux Environment Setup
    • Sharing your Conda Environment
    • Jupyter Notebook Walkthrough
    • Jupyter Notebook Walkthrough 2
    • Jupyter Notebook Walkthrough 3
    • Course Check-In
  •   Pandas: Data Analysis
    • Section Overview
    • Downloading Workbooks and Assignments
    • Pandas Introduction
    • Series, Data Frames and CSVs
    • Data from URLs
    • Quick Note: Upcoming Videos
    • Describing Data with Pandas
    • Selecting and Viewing Data with Pandas
    • Quick Note: Upcoming Video
    • Selecting and Viewing Data with Pandas Part 2
    • Manipulating Data
    • Manipulating Data 2
    • Manipulating Data 3
    • Assignment: Pandas Practice
    • How To Download The Course Assignments
    • Implement a New Life System
  •   NumPy
    • Section Overview
    • NumPy Introduction
    • Quick Note: Correction In Next Video
    • NumPy DataTypes and Attributes
    • Creating NumPy Arrays
    • NumPy Random Seed
    • Endorsements On LinkedIn
    • Viewing Arrays and Matrices
    • Manipulating Arrays
    • Manipulating Arrays 2
    • Standard Deviation and Variance
    • Reshape and Transpose
    • Dot Product vs Element Wise
    • Exercise: Nut Butter Store Sales
    • Comparison Operators
    • Sorting Arrays
    • Turn Images Into NumPy Arrays
    • Assignment: NumPy Practice
    • Optional: Extra NumPy resources
  •   Matplotlib: Plotting and Data Visualization
    • Section Overview
    • Matplotlib Introduction
    • Importing And Using Matplotlib
    • Anatomy Of A Matplotlib Figure
    • Scatter Plot And Bar Plot
    • Histograms And Subplots
    • Subplots Option 2
    • Quick Tip: Data Visualizations
    • Plotting From Pandas DataFrames
    • Quick Note: Regular Expressions
    • Plotting From Pandas DataFrames 2
    • Plotting from Pandas DataFrames 3
    • Plotting from Pandas DataFrames 4
    • Plotting from Pandas DataFrames 5
    • Plotting from Pandas DataFrames 6
    • Plotting from Pandas DataFrames 7
    • Customizing Your Plots
    • Customizing Your Plots 2
    • Saving And Sharing Your Plots
    • Assignment: Matplotlib Practice
  •   Scikit-learn: Creating Machine Learning Models
    • Section Overview
    • Scikit-learn Introduction
    • Quick Note: Upcoming Video
    • Refresher: What Is Machine Learning?
    • Quick Note: Upcoming Videos
    • Scikit-learn Cheatsheet
    • Typical scikit-learn Workflow
    • Optional: Debugging Warnings In Jupyter
    • Getting Your Data Ready: Splitting Your Data
    • Quick Tip: Clean, Transform, Reduce
    • Getting Your Data Ready: Convert Data To Numbers
    • Note: Update to next video (OneHotEncoder can handle NaN/None values)
    • Getting Your Data Ready: Handling Missing Values With Pandas
    • Extension: Feature Scaling
    • Note: Correction in the upcoming video
    • Getting Your Data Ready: Handling Missing Values With Scikit-learn
    • NEW: Choosing The Right Model For Your Data
    • NEW: Choosing The Right Model For Your Data 2 (Regression)
    • Quick Note: Decision Trees
    • Quick Tip: How ML Algorithms Work
    • Choosing The Right Model For Your Data 3 (Classification)
    • Fitting A Model To The Data
    • Making Predictions With Our Model
    • predict() vs predict_proba()
    • NEW: Making Predictions With Our Model (Regression)
    • NEW: Evaluating A Machine Learning Model (Score) Part 1
    • NEW: Evaluating A Machine Learning Model (Score) Part 2
    • Evaluating A Machine Learning Model 2 (Cross Validation)
    • Evaluating A Classification Model 1 (Accuracy)
    • Evaluating A Classification Model 2 (ROC Curve)
    • Evaluating A Classification Model 3 (ROC Curve)
    • Reading Extension: ROC Curve + AUC
    • Evaluating A Classification Model 4 (Confusion Matrix)
    • NEW: Evaluating A Classification Model 5 (Confusion Matrix)
    • Evaluating A Classification Model 6 (Classification Report)
    • NEW: Evaluating A Regression Model 1 (R2 Score)
    • NEW: Evaluating A Regression Model 2 (MAE)
    • NEW: Evaluating A Regression Model 3 (MSE)
    • Machine Learning Model Evaluation
    • NEW: Evaluating A Model With Cross Validation and Scoring Parameter
    • NEW: Evaluating A Model With Scikit-learn Functions
    • Improving A Machine Learning Model
    • Tuning Hyperparameters
    • Tuning Hyperparameters 2
    • Tuning Hyperparameters 3
    • Note: Metric Comparison Improvement
    • Quick Tip: Correlation Analysis
    • Saving And Loading A Model
    • Saving And Loading A Model 2
    • Putting It All Together
    • Putting It All Together 2
    • Scikit-Learn Practice
  •   Supervised Learning: Classification + Regression
    • Milestone Projects!
  •   Milestone Project 1: Supervised Learning (Classification)
    • Section Overview
    • Project Overview
    • Project Environment Setup
    • Step 1~4 Framework Setup
    • Note: Code update for next video
    • Getting Our Tools Ready
    • Exploring Our Data
    • Finding Patterns
    • Finding Patterns 2
    • Finding Patterns 3
    • Preparing Our Data For Machine Learning
    • Choosing The Right Models
    • Experimenting With Machine Learning Models
    • Tuning/Improving Our Model
    • Tuning Hyperparameters
    • Tuning Hyperparameters 2
    • Tuning Hyperparameters 3
    • Quick Note: Confusion Matrix Labels
    • Evaluating Our Model
    • Evaluating Our Model 2
    • Evaluating Our Model 3
    • Finding The Most Important Features
    • Reviewing The Project
    • Exercise: Imposter Syndrome
  •   Milestone Project 2: Supervised Learning (Time Series Data)
    • Section Overview
    • Project Overview
    • Downloading the data for the next two projects
    • Project Environment Setup
    • Step 1~4 Framework Setup
    • Exploring Our Data
    • Exploring Our Data 2
    • Feature Engineering
    • Turning Data Into Numbers
    • Filling Missing Numerical Values
    • Filling Missing Categorical Values
    • Fitting A Machine Learning Model
    • Splitting Data
    • Challenge: What's wrong with splitting data after filling it?
    • Custom Evaluation Function
    • Reducing Data
    • RandomizedSearchCV
    • Improving Hyperparameters
    • Preproccessing Our Data
    • Making Predictions
    • Feature Importance
  •   Data Engineering
    • Data Engineering Introduction
    • What Is Data?
    • What is a Data Engineer?
    • What is A Data Engineer 2?
    • What is a Data Engineer 3?
    • What is a Data Engineer 4?
    • Types of Databases
    • Quick Note: Upcoming Video
    • Optional: OLTP Databases
    • Optional: Learn SQL
    • Hadoop, HDFS and MapReduce
    • Apache Spark and Apache Flink
    • Kafka and Stream Processing
  •   Neural Networks: Deep Learning, Transfer Learning and TensorFlow 2
    • Section Overview
    • Deep Learning and Unstructured Data
    • Setting Up With Google
    • Setting Up Google Colab
    • Google Colab Workspace
    • Uploading Project Data
    • Setting Up Our Data
    • Setting Up Our Data 2
    • Importing TensorFlow 2
    • Optional: TensorFlow 2.0 Default Issue
    • Using A GPU
    • Optional: GPU and Google Colab
    • Optional: Reloading Colab Notebook
    • Loading Our Data Labels
    • Preparing The Images
    • Turning Data Labels Into Numbers
    • Creating Our Own Validation Set
    • Preprocess Images
    • Preprocess Images 2
    • Turning Data Into Batches
    • Turning Data Into Batches 2
    • Visualizing Our Data
    • Preparing Our Inputs and Outputs
    • Optional: How machines learn and what's going on behind the scenes?
    • Building A Deep Learning Model
    • Building A Deep Learning Model 2
    • Building A Deep Learning Model 3
    • Building A Deep Learning Model 4
    • Summarizing Our Model
    • Evaluating Our Model
    • Preventing Overfitting
    • Training Your Deep Neural Network
    • Evaluating Performance With TensorBoard
    • Make And Transform Predictions
    • Transform Predictions To Text
    • Visualizing Model Predictions
    • Visualizing And Evaluate Model Predictions 2
    • Visualizing And Evaluate Model Predictions 3
    • Saving And Loading A Trained Model
    • Training Model On Full Dataset
    • Making Predictions On Test Images
    • Submitting Model to Kaggle
    • Making Predictions On Our Images
    • Finishing Dog Vision: Where to next?
  •   Storytelling + Communication: How To Present Your Projects
    • Section Overview
    • Communicating Your Work
    • Communicating With Managers
    • Communicating With Co-Workers
    • Weekend Project Principle
    • Communicating With Outside World
    • Storytelling
  •   Career Advice + Extra Bits
    • Endorsements On LinkedIn
    • Quick Note: Upcoming Video
    • What If I Don't Have Enough Experience?
    • Learning Guideline
    • Quick Note: Upcoming Videos
    • JTS: Learn to Learn
    • JTS: Start With Why
    • Coding Challenges
  •   Learn Python
    • Watch Learn Python Section
  •   Learn Python Part 2
    • Watch Python Basics 2 Section
    • Pure Functions
    • map()
    • filter()
    • zip()
    • reduce()
    • List Comprehensions
    • Set Comprehensions
    • Exercise: Comprehensions
    • Modules in Python
    • Quick Note: Upcoming Videos
    • Optional: PyCharm
    • Packages in Python
    • Different Ways To Import
    • Next Steps
  •   Bonus: Learn Advanced Statistics and Mathematics
    • Statistics and Mathematics
  •   Where To Go From Here?
    • Thank You
    • Review This Course!
    • Become An Alumni
    • Learning Guideline
    • ZTM Events Every Month
    • LinkedIn Endorsements

Taught by

Andrei Neagoie and Daniel Bourke

Reviews

Start your review of Complete A.I. Machine Learning and Data Science: Zero to Mastery

Go to class

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.