 Navigation

Click to Take the FREE Crash-Course

Search... 

Need Help Getting Started with Applied Machine

Learning?
These are the Step-by-Step Guides that You’ve Been Looking For!
What do you want help with?

Foundations Beginner Intermediate Advanced

How Do I Get Python Skills Code ML Algorithms Long Short-Term
Started? Understand ML XGBoost Algorithm Memory
Step-by-Step Algorithms Imbalanced Natural Language
Process ML + Weka (no Classification (Text)
Probability code) Deep Learning Computer Vision
Statistical Methods ML + Python (scikit- (Keras) CNN/LSTM + Time
Linear Algebra learn) Deep Learning Series
Optimization ML + R (caret) (PyTorch) GANs
Calculus Time Series ML in OpenCV Attention and
Forecasting Better Deep Transformers
Data Preparation Learning
Ensemble Learning

How Do I Get Started?

The most common question I’m asked is: “how do I get started?”

My best advice for getting started in machine learning is broken down into a 5-step process:

Step 1: Adjust Mindset. Believe you can practice and apply machine learning.
What is Holding you Back From Your Machine Learning Goals?
Why Machine Learning Does Not Have to Be So Hard
How to Think About Machine Learning
Find Your Machine Learning Tribe
Step 2: Pick a Process. Use a systemic process to work through problems.
Applied Machine Learning Process
Step 3: Pick a Tool. Select a tool for your level and map it onto your process.
Beginners: Weka Workbench.
Intermediate: Python Ecosystem.
Advanced: R Platform.
Best Programming Language for Machine Learning
Step 4: Practice on Datasets. Select datasets to work on and practice the process.
Practice Machine Learning with Small In-Memory Datasets
Tour of Real-World Machine Learning Problems
Work on Machine Learning Problems That Matter To You
Step 5: Build a Portfolio. Gather results and demonstrate your skills.
Build a Machine Learning Portfolio
Get Paid To Apply Machine Learning
Machine Learning For Money

For more on this top-down approach, see:

The Machine Learning Mastery Method

Machine Learning for Programmers

Many of my students have used this approach to go on and do well in Kaggle competitions and get jobs as
Machine Learning Engineers and Data Scientists.

Applied Machine Learning Process

The benefit of machine learning are the predictions and the models that make predictions.

To have skill at applied machine learning means knowing how to consistently and reliably deliver high-quality
predictions on problem after problem. You need to follow a systematic process.

Below is a 5-step process that you can follow to consistently achieve above average results on predictive modeling
problems:

Step 1: Define your problem.

How to Define Your Machine Learning Problem
Step 2: Prepare your data.
How to Prepare Data For Machine Learning
How to Identify Outliers in your Data
Improve Model Accuracy with Data Pre-Processing
Discover Feature Engineering
An Introduction to Feature Selection
Tactics to Combat Imbalanced Classes in Your Machine Learning Dataset
Data Leakage in Machine Learning
Step 3: Spot-check algorithms.
How to Evaluate Machine Learning Algorithms
Why you should be Spot-Checking Algorithms on your Machine Learning Problems
How To Choose The Right Test Options When Evaluating Machine Learning Algorithms
A Data-Driven Approach to Choosing Machine Learning Algorithms
Step 4: Improve results.
How to Improve Machine Learning Results
Machine Learning Performance Improvement Cheat Sheet
How To Improve Deep Learning Performance
Step 5: Present results.
How to Use Machine Learning Results
How to Train a Final Machine Learning Model
How To Deploy Your Predictive Model To Production

For a good summary of this process, see the posts:

Applied Machine Learning Process

How to Use a Machine Learning Checklist to Get Accurate Predictions

Probability for Machine Learning

Probability is the mathematics of quantifying and harnessing uncertainty. It is the bedrock of many fields of
mathematics (like statistics) and is critical for applied machine learning.

Below is the 3 step process that you can use to get up-to-speed with probability for machine learning, fast.

Step 1: Discover what Probability is.

Basics of Mathematical Notation for Machine Learning
What Is Probability?
Step 2: Discover why Probability is so important for machine learning.
5 Reasons to Learn Probability for Machine Learning
A Gentle Introduction to Uncertainty in Machine Learning
Step 3: Dive into Probability topics.
Probability for Machine Learning Mini-Course
Probability for Machine Learning (my book)

You can see all of the tutorials on probability here. Below is a selection of some of the most popular tutorials.
Probability Foundations Probability Distributions
Introduction to Joint, Marginal, and Conditional A Gentle Introduction to Probability Distributions
Probability Discrete Probability Distributions for Machine
Intuition for Joint, Marginal, and Conditional Learning
Probability Continuous Probability Distributions for Machine
Worked Examples of Different Types of Probability Learning

Bayes Theorem Information Theory

A Gentle Introduction to Bayes Theorem for A Gentle Introduction to Information Entropy
Machine Learning Calculate the Divergence Between Probability
Develop a Naive Bayes Classifier from Scratch in Distributions
Python A Gentle Introduction to Cross-Entropy for
Implement Bayesian Optimization from Scratch in Machine Learning
Python

Statistics for Machine Learning

Statistical Methods an important foundation area of mathematics required for achieving a deeper understanding of
the behavior of machine learning algorithms.

Below is the 3 step process that you can use to get up-to-speed with statistical methods for machine learning, fast.

Step 1: Discover what Statistical Methods are.

What is Statistics (and why is it important in machine learning)?
Step 2: Discover why Statistical Methods are important for machine learning.
The Close Relationship Between Applied Statistics and Machine Learning
10 Examples of How to Use Statistical Methods in a Machine Learning Project
Step 3: Dive into the topics of Statistical Methods.
Statistics for Machine Learning (7-Day Mini-Course)
Statistical Methods for Machine Learning (my book)

You can see all of the statistical methods posts here. Below is a selection of some of the most popular tutorials.

Summary Statistics
Introduction to the 5 Number Summary
Introduction to Data Visualization
Correlation to Understand the Relationship
Between Variables
Introduction to Calculating Normal Summary
Statistics

Statistical Hypothesis Tests

15 Statistical Hypothesis Tests in Python (Cheat
Sheet)
Introduction to Statistical Hypothesis Tests
Introduction to Nonparametric Statistical Resampling Methods
Significance Tests
Introduction to Statistical Sampling and
Introduction to Parametric Statistical Significance
Resampling
Tests
Introduction to the Bootstrap
Statistical Significance Tests for Comparing
Introduction to Cross-Validation
Algorithms
Estimation Statistics
Introduction to Estimation Statistics
Introduction to Confidence Intervals
Introduction to Prediction Intervals
Introduction to Tolerance Intervals

Linear Algebra for Machine Learning

Linear algebra is an important foundation area of mathematics required for achieving a deeper understanding of
machine learning algorithms.

Below is the 3 step process that you can use to get up-to-speed with linear algebra for machine learning, fast.

Step 1: Discover what Linear Algebra is.

Basics of Mathematical Notation for Machine Learning
A Gentle Introduction to Linear Algebra
Step 2: Discover why Linear Algebra is important for machine learning.
5 Reasons to Learn Linear Algebra for Machine Learning
10 Examples of Linear Algebra in Machine Learning
Linear Algebra for Machine Learning
Step 3: Dive into Linear Algebra topics.
Linear Algebra for Machine Learning Mini-Course
Linear Algebra for Machine Learning (my book)

You can see all linear algebra posts here. Below is a selection of some of the most popular tutorials.

Linear Algebra in Python Vectors

Introduction to N-Dimensional Arrays in Python Introduction to Vectors
How to Index, Slice and Reshape NumPy Arrays Introduction to Vector Norms

Matrices Matrix Factorization

Introduction to Matrices and Matrix Arithmetic Introduction to Matrix Factorization
Introduction to Matrix Types in Linear Algebra Introduction to Eigendecomposition
Introduction to Matrix Operations for Machine Introduction to Singular-Value Decomposition
Learning (SVD)
Introduction to Tensors for Machine Learning Introduction to Principal Component Analysis
(PCA)
Optimization for Machine Learning

Optimization is the core of all machine learning algorithms. When we train a machine learning model, it is doing
optimization with the given dataset.

You can get familiar with optimization for machine learning in 3 steps, fast.

Step 1: Discover what Optimization is.

A Gentle Introduction to Applied Machine Learning as a Search Problem
A Gentle Introduction to Function Optimization
Step 2: Discover the Optimization Algorithms.
Function Optimization With SciPy
Basin Hopping Optimization in Python
How to Implement Gradient Descent Optimization from Scratch
Step 3: Dive into Optimization Topics.
How to Manually Optimize Machine Learning Model Hyperparameters
Optimization for Machine Learning (my book)

You can see all optimization posts here. Below is a selection of some of the most popular tutorials.

Local Optimization Gradient Descent

Function Optimization With SciPy How to Implement Gradient Descent Optimization
Basin Hopping Optimization in Python from Scratch
Stochastic Hill Climbing in Python from Scratch Code Adam Optimization Algorithm From Scratch
Gradient Descent Optimization With Nadam From
Global Optimization Scratch
Random Search and Grid Search for Function
Applications of Optimization
Optimization
Simulated Annealing From Scratch in Python How to Manually Optimize Machine Learning
Dual Annealing Optimization With Python Model Hyperparameters
Differential Evolution Global Optimization With How to Manually Optimize Neural Network Models
Python

Calculus for Machine Learning

Calculus is the hidden driver for the success of many machine learning algorithms. When we talk about the
gradient descent optimization part of a machine learning algorithm, the gradient is found using calculus.

You can get familiar with calculus for machine learning in 3 steps.

Step 1: Discover what Calculus is about.

What is Calculus?
Key Concepts in Calculus: Rate of Change
Step 2: Discover the rules of differentiation.
A Gentle Introduction to Derivatives of Powers and Polynomials
The Power, Product and Quotient Rules
The Chain Rule of Calculus for Univariate and Multivariate Functions
Step 3: Dive into Calculus Topics.
Calculus in Action: Neural Networks
Application of differentiations in neural networks
Calculus for Machine Learning (my book)

You can see all calculus posts here. Below is a selection of some of the most popular tutorials.

Basic Calculus Calculus for Optimization

Calculus in Machine Learning: Why it Works A Gentle Introduction to Optimization /
Key Concepts in Calculus: Rate of Change Mathematical Programming
A Gentle Introduction to Slopes and Tangents A Gentle Introduction to Method of Lagrange
The Power, Product, and Quotient Rules Multipliers

Multivariate Calculus Applications of Calculus

A Gentle Introduction to Multivariate Calculus A Gentle Introduction To Gradient Descent
A Gentle Introduction To Partial Derivatives and Procedure
Gradient Vectors Application of differentiations in neural networks
Higher-Order Derivatives Method of Lagrange Multipliers: The Theory
A Gentle Introduction to the Jacobian Behind Support Vector Machines (Part 1: The
Separable Case)

Python for Machine Learning

Python is the lingua franca of machine learning projects. Not only a lot of machine learning libraries are in Python,
but also it is effective to help us finish our machine learning projects quick and neatly. Having good Python
programming skills can let you get more done in shorter time!

You can get familiar with Python for machine learning in 3 steps.

Step 1: Learn the language.

How to Learn Python for Machine Learning?
Some Language Features in Python
Step 2: Learn how to work with the language.
Python Debugging Tools
Profiling Python Code
Static Analyzers in Python
Step 3: Learn what you can do in Python ecosystem.
A Guide to Obtaining Time Series Datasets in Python
Data Visualization in Python with matplotlib, Seaborn, and Bokeh
Web Frameworks for Your Python Projects

You can see all Python posts here. But don’t miss Python for Machine Learning (my book). Below is a selection of
some of the most popular tutorials.
Basic Language Language Techniques
Some Language Features in Python Command Line Arguments for Your Python Script
More Special Features in Python A Gentle Introduction to Decorators in Python
Python Classes and Their Use in Keras Techniques to Write Better Python Code

Troubleshooting Libraries
Python Debugging Tools Multiprocessing in Python
Profiling Python Code A Guide to Obtaining Time Series Datasets in
Static Analyzers in Python Python
Web Frameworks for Your Python Projects

Understand Machine Learning Algorithms

Machine learning is about machine learning algorithms.

You need to know what algorithms are available for a given problem, how they work, and how to get the most out of
them.

Here’s how to get started with machine learning algorithms:

Step 1: Discover the different types of machine learning algorithms.

A Tour of Machine Learning Algorithms
Step 2: Discover the foundations of machine learning algorithms.
How Machine Learning Algorithms Work
Parametric and Nonparametric Algorithms
Supervised and Unsupervised Algorithms
The Bias-Variance Trade-Off
Overfitting and Underfitting With Algorithms
Step 3: Discover how top machine learning algorithms work.
Machine Learning Algorithms Mini-Course
Master Machine Learning Algorithms (my book)

You can see all machine learning algorithm posts here. Below is a selection of some of the most popular tutorials.

Linear Algorithms Ensemble Algorithms

Gradient Descent Bagging and Random Forest
Linear Regression Boosting and AdaBoost
Logistic Regression
Linear Discriminant Analysis How to Study/Learn ML Algorithms
5 Ways To Understand Machine Learning
Nonlinear Algorithms
Algorithms
Classification And Regression Trees How to Learn a Machine Learning Algorithm
Naive Bayes How to Study Machine Learning Algorithms
K-Nearest Neighbors How to Research a Machine Learning Algorithm
Learning Vector Quantization
Support Vector Machines How To Investigate Machine Learning Algorithm
Behavior
Take Control By Creating Lists of Machine
Learning Algorithms
6 Questions To Understand Any Machine Learning
Algorithm

Weka Machine Learning (no code)

Weka is a platform that you can use to get started in applied machine learning.

It has a graphical user interface meaning that no programming is required and it offers a suite of state of the art
algorithms.

Here’s how you can get started with Weka:

Step 1: Discover the features of the Weka platform.

What is the Weka Machine Learning Workbench
Step 2: Discover how to get around the Weka platform.
How to Download and Install the Weka Machine Learning Workbench
A Tour of the Weka Machine Learning Workbench
Step 3: Discover how to deliver results with Weka.
How to Run Your First Classifier in Weka
Applied Machine Learning With Weka Mini-Course
Machine Learning Mastery With Weka (my book)

You can see all Weka machine learning posts here. Below is a selection of some of the most popular tutorials.

Prepare Data in Weka Weka Algorithm Tutorials

How To Load CSV Machine Learning Data in How to Use Machine Learning Algorithms in Weka
Weka How To Estimate The Performance of Machine
How to Better Understand Your Machine Learning Learning Algorithms in Weka
Data in Weka How To Use Regression Machine Learning
How to Normalize and Standardize Your Machine Algorithms in Weka
Learning Data in Weka How To Use Classification Machine Learning
How To Handle Missing Values In Machine Algorithms in Weka
Learning Data With Weka How to Tune Machine Learning Algorithms in
How to Perform Feature Selection With Machine Weka
Learning Data in Weka

Python Machine Learning (scikit-learn)

Python is one of the fastest growing platforms for applied machine learning.

You can use the same tools like pandas and scikit-learn in the development and operational deployment of your
model.

Below are the steps that you can use to get started with Python machine learning:

Step 1: Discover Python for machine learning

A Gentle Introduction to Scikit-Learn: A Python Machine Learning Library
Step 2: Discover the ecosystem for Python machine learning.
Crash Course in Python for Machine Learning Developers
Python Ecosystem for Machine Learning
Python is the Growing Platform for Applied Machine Learning
Step 3: Discover how to work through problems using machine learning in Python.
Your First Machine Learning Project in Python Step-By-Step
Python Machine Learning Mini-Course
Machine Learning Mastery With Python (my book)

You can see all Python machine learning posts here. Below is a selection of some of the most popular tutorials.

Prepare Data in Python Machine Learning in Python

How To Load Machine Learning Data in Python Evaluate the Performance of Machine Learning
Understand Your Machine Learning Data With Algorithms
Descriptive Statistics in Python Metrics To Evaluate Machine Learning Algorithms
Visualize Machine Learning Data in Python With in Python
Pandas Spot-Check Classification Machine Learning
How To Prepare Your Data For Machine Learning Algorithms in Python with scikit-learn
in Python with Scikit-Learn Spot-Check Regression Machine Learning
Feature Selection For Machine Learning in Python Algorithms in Python with scikit-learn
How To Compare Machine Learning Algorithms in
Python with scikit-learn

R Machine Learning (caret)

R is a platform for statistical computing and is the most popular platform among professional data scientists.

It’s popular because of the large number of techniques available, and because of excellent interfaces to these
methods such as the powerful caret package.

Here’s how to get started with R machine learning:

Step 1: Discover the R platform and why it is so popular.

What is R
Use R For Machine Learning
Super Fast Crash Course in R
Step 2: Discover machine learning algorithms in R.
How To Get Started With Machine Learning Algorithms in R
Step 3: Discover how to work through problems using machine learning in R.
Your First Machine Learning Project in R Step-By-Step
R Machine Learning Mini-Course
Machine Learning Mastery With R (my book)

You can see all R machine learning posts here. Below is a selection of some of the most popular tutorials.

Data Preparation in R Applied Machine Learning in R

How To Load Your Machine Learning Data Into R How to Evaluate Machine Learning Algorithms with
Better Understand Your Data in R Using R
Descriptive Statistics Spot Check Machine Learning Algorithms in R
Better Understand Your Data in R Using Tune Machine Learning Algorithms in R
Visualization How to Build an Ensemble Of Machine Learning
Feature Selection with the Caret R Package Algorithms in R
Get Your Data Ready For Machine Learning in R Compare The Performance of Machine Learning
with Pre-Processing Algorithms in R

Code Algorithm from Scratch (Python)

You can learn a lot about machine learning algorithms by coding them from scratch.

Learning via coding is the preferred learning style for many developers and engineers.

Here’s how to get started with machine learning by coding everything from scratch.

Step 1: Discover the benefits of coding algorithms from scratch.

Benefits of Implementing Machine Learning Algorithms From Scratch
Understand Machine Learning Algorithms By Implementing Them From Scratch
Step 2: Discover that coding algorithms from scratch is a learning tool only.
Stop Coding Machine Learning Algorithms From Scratch
Don’t Start with Open-Source Code When Implementing Machine Learning Algorithms
Step 3: Discover how to code machine learning algorithms from scratch in Python.
Machine Learning Algorithms From Scratch (my book)

You can see all of the Code Algorithms from Scratch posts here. Below is a selection of some of the most popular
tutorials.

Prepare Data Algorithm Evaluation

How to Load Machine Learning Data From Scratch How to Code Resampling Methods From Scratch
How to Scale Machine Learning Data From How To Code Algorithm Performance Metrics
Scratch From Scratch

Linear Algorithms Nonlinear Algorithms

How To Implement Simple Linear Regression How to Code the Backpropagation Algorithm From
From Scratch Scratch
How To Implement The Perceptron Algorithm From How To Code The Decision Tree Algorithm From
Scratch Scratch

Introduction to Time Series Forecasting (Python)

Time series forecasting is an important topic in business applications.

Many datasets contain a time component, but the topic of time series is rarely covered in much depth from a
machine learning perspective.

Here’s how to get started with Time Series Forecasting:

Step 1: Discover Time Series Forecasting.

What Is Time Series Forecasting?
Step 2: Discover Time Series as Supervised Learning.
Time Series Forecasting as Supervised Learning
Step 3: Discover how to get good at delivering results with Time Series Forecasting.
Time Series Forecasting With Python Mini-Course
Time Series Forecasting With Python (my book)

You can see all Time Series Forecasting posts here. Below is a selection of some of the most popular tutorials.

Data Preparation Tutorials Forecasting Tutorials

7 Time Series Datasets for Machine Learning How to Make Baseline Predictions for Time Series
How to Load and Explore Time Series Data in Forecasting with Python
Python How to Check if Time Series Data is Stationary
How to Normalize and Standardize Time Series with Python
Data in Python How to Create an ARIMA Model for Time Series
Basic Feature Engineering With Time Series Data Forecasting with Python
in Python How to Grid Search ARIMA Model
How To Backtest Machine Learning Models for Hyperparameters with Python
Time Series Forecasting How to Work Through a Time Series Forecast
Project

Data Preparation for Machine Learning (Python)

The performance of your predictive model is only as good as the data that you use to train it.

As such data preparation may the most important parts of your applied machine learning project.

Here’s how to get started with Data Preparation for machine learning:

Step 1: Discover the importance of data preparation.

What Is Data Preparation in a Machine Learning Project
Why Data Preparation Is So Important in Machine Learning
Step 2: Discover data preparation techniques.
Tour of Data Preparation Techniques for Machine Learning
Framework for Data Preparation Techniques in Machine Learning
Step 3: Discover how to get good at delivering results with data preparation.
How to Choose Data Preparation Methods for Machine Learning
Data Preparation for Machine Learning (7-Day Mini-Course)
Data Preparation for Machine Learning (my book)

You can see all Data Preparation tutorials here. Below is a selection of some of the most popular tutorials.

Data Cleaning Data Transforms

How to delete Duplicate Rows and Useless How to use Normalization and Standardization
Features How to use Ordinal and One Hot Encoding
How to identify and Delete Outliers How to use Power Transforms
How to impute Missing Values
Dimensionality Reduction
Feature Selection
Introduction to Dimensionality Reduction Methods
Introduction to Feature Importance Methods How to use PCA for Dimensionality Reduction
How to use Recursive Feature Selection (RFE) How to use LDA for Dimensionality Reduction
How to Use Feature Selection for Regression

XGBoost in Python (Stochastic Gradient Boosting)

XGBoost is a highly optimized implementation of gradient boosted decision trees.

It is popular because it is being used by some of the best data scientists in the world to win machine learning
competitions.

Here’s how to get started with XGBoost:

Step 1: Discover the Gradient Boosting Algorithm.

A Gentle Introduction to the Gradient Boosting Algorithm for Machine Learning
Step 2: Discover XGBoost.
A Gentle Introduction to XGBoost for Applied Machine Learning
Step 3: Discover how to get good at delivering results with XGBoost.
How to Develop Your First XGBoost Model in Python with scikit-learn
XGBoost With Python Mini-Course
XGBoost With Python (my book)

You can see all XGBoosts posts here. Below is a selection of some of the most popular tutorials.

XGBoost Basics XGBoost Tuning

Data Preparation for Gradient Boosting with How to Configure the Gradient Boosting Algorithm
XGBoost in Python
How to Evaluate Gradient Boosting Models with Tune Learning Rate for Gradient Boosting with
XGBoost in Python XGBoost in Python
Avoid Overfitting By Early Stopping With XGBoost Stochastic Gradient Boosting with XGBoost and
In Python scikit-learn in Python
Feature Importance and Feature Selection With How to Tune the Number and Size of Decision
XGBoost in Python Trees with XGBoost in Python
How to Best Tune Multithreading Support for
XGBoost in Python

Imbalanced Classification

Imbalanced classification refers to classification tasks where there are many more examples for one class than
another class.

These types of problems often require the use of specialized performance metrics and learning algorithms as the
standard metrics and methods are unreliable or fail completely.

Here’s how you can get started with Imbalanced Classification:

Step 1: Discover the challenge of imbalanced classification

A Gentle Introduction to Imbalanced Classification
Step 2: Discover the intuition for skewed class distributions.
Develop an Intuition for Severely Skewed Class Distributions
Step 3: Discover how to solve imbalanced classification problems.
Step-By-Step Framework for Imbalanced Classification Projects
Imbalanced Classification With Python (7-Day Mini-Course)
Imbalanced Classification with Python (my book)

You can see all Imbalanced Classification posts here. Below is a selection of some of the most popular tutorials.

Performance Measures Data Sampling

Tour of Evaluation Metrics for Imbalanced Tour of Data Sampling Methods for Imbalanced
Classification Classification
Failure of Classification Accuracy Random Oversampling and Undersampling
How to Calculate Precision, Recall, and F- SMOTE Oversampling for Imbalanced
Measure Classification

Cost-Sensitive Algorithms Advanced Methods

Cost-Sensitive Logistic Regression Threshold Moving Methods
Cost-Sensitive Decision Trees One-Class Classification
How to Configure XGBoost for Imbalanced Customised Ensemble Algorithms
Classification
Deep Learning (Keras)

Deep learning is a fascinating and powerful field.

State-of-the-art results are coming from the field of deep learning and it is a sub-field of machine learning that
cannot be ignored.

Here’s how to get started with deep learning:

Step 1: Discover what deep learning is all about.

What is Deep Learning?
8 Inspirational Applications of Deep Learning
Step 2: Discover the best tools and libraries.
Introduction to the Python Deep Learning Library Theano
Introduction to the Python Deep Learning Library TensorFlow
Introduction to Python Deep Learning with Keras
Step 3: Discover how to work through problems and deliver results.
Develop Your First Neural Network in Python With Keras Step-By-Step
Applied Deep Learning in Python Mini-Course
Deep Learning With Python (my book)

You can see all deep learning posts here. Below is a selection of some of the most popular tutorials.

Background Convolutional Neural Networks

Crash Course On Multi-Layer Perceptron Neural Handwritten Digit Recognition using Convolutional
Networks Neural Networks in Python with Keras
Crash Course in Convolutional Neural Networks Object Recognition with Convolutional Neural
for Machine Learning Networks in the Keras Deep Learning Library
Crash Course in Recurrent Neural Networks for Predict Sentiment From Movie Reviews Using
Deep Learning Deep Learning

Multilayer Perceptrons Recurrent Neural Networks

5 Step Life-Cycle for Neural Network Models in Time Series Prediction with LSTM Recurrent
Keras Neural Networks in Python with Keras
How to Grid Search Hyperparameters for Deep Understanding Stateful LSTM Recurrent Neural
Learning Models in Python With Keras Networks in Python with Keras
Save and Load Your Keras Deep Learning Models Text Generation With LSTM Recurrent Neural
Display Deep Learning Model Training History in Networks in Python with Keras
Keras
Dropout Regularization in Deep Learning Models
With Keras

Deep Learning (PyTorch)

Besides Keras, PyTorch is another library for deep learning with a huge market-share. It is important to know about
PyTorch and become familiar with its syntax.

Here’s how to get started with deep learning in PyTorch:

Step 1: Discover what deep learning is all about.

What is Deep Learning?
8 Inspirational Applications of Deep Learning
Step 2: Discover PyTorch
Overview of Some Deep Learning Libraries
PyTorch Tutorial: How to Develop Deep Learning Models with Python
Step 3: Discover how to work through problems and deliver results.
Develop Your First Neural Network with PyTorch, Step by Step
Deep Learning with PyTorch Mini-Course
Deep Learning With PyTorck (my book)

You can see all PyTorch deep learning posts here. Below is a selection of some of the most popular tutorials.

Background Model Building Techniques

Two Dimensional Tensors in PyTorch Use PyTorch Deep Learning Models with scikit-
Training a Linear Regression Model in PyTorch learn
Save and Load Your PyTorch Models
Multilayer Perceptrons Using Dropout Regularization in PyTorch Models
Develop Your First Neural Network with PyTorch,
Advanced Networks
Step by Step
Creating a Training Loop for PyTorch Models Building a Convolutional Neural Network in
Building a Multiclass Classification Model in PyTorch
PyTorch LSTM for Time Series Prediction in PyTorch
Text Generation with LSTM in PyTorch

Machine Learning in OpenCV

OpenCV is the most popular library for image processing but its machine learning module is less well-known.

If you are already using OpenCV, adding machine learning to your project should be at no additional cost. You can
make use of the experiences you learned in scikit-learn or Keras to bring your image processing project to the next
level.

Below are the steps that you can use to get started with machine learning in OpenCV:

Step 1: Refresher on what OpenCV offers

A Gentle Introduction to OpenCV
Step 2: Discover how to present images for the consumption by machine learning models
Image Feature Extraction in OpenCV: Keypoints and Description Vectors
Image Datasets for Practicing Machine Learning in OpenCV
Image Vector Representation for Machine Learning Using OpenCV
Step 3: Discover how to use machine learning in OpenCV
Random Forest for Image Classification Using OpenCV
Machine Learning in OpenCV (7-Day Mini-Course)
Machine Learning in OpenCV (my book)

You can see all OpenCV machine learning posts here. Below is a selection of some of the most popular tutorials.

Foundations on OpenCV and Image Processing Machine Learning in Python

How to Read, Write, Display Images in OpenCV How to Train a Object Detection Engine with HOG
and Converting Color Spaces in OpenCV
How to Transform Images and Create Video with K-Means Clustering for Image Classification Using
OpenCV OpenCV
Image Datasets for Practicing Machine Learning in Training a Haar Cascade Object Detector in
OpenCV OpenCV
Image Feature Extraction in OpenCV: Keypoints Using Haar Cascade for Object Detection
and Description Vectors Normal Bayes Classifier for Image Segmentation
Image Vector Representation for Machine Using OpenCV
Learning Using OpenCV

Better Deep Learning Performance

Although it is easy to define and fit a deep learning neural network model, it can be challenging to get good
performance on a specific predictive modeling problem.

There are standard techniques that you can use to improve the learning, reduce overfitting, and make better
predictions with your deep learning model.

Here’s how to get started with getting better deep learning performance:

Step 1: Discover the challenge of deep learning.

Why Training a Neural Network Is Hard
The Challenge of Training Deep Learning Neural Network Models
Step 2: Discover frameworks for diagnosing and improving model performance.
How To Improve Deep Learning Performance
Framework for Better Deep Learning
Introduction to Learning Curves for Diagnosing Model Performance
Step 3: Discover techniques that you can use to improve performance.
How to Get Better Deep Learning Results (7-Day Mini-Course)
Better Deep Learning (my book)

You can see all better deep learning posts here. Below is a selection of some of the most popular tutorials.

Better Learning (fix training) Better Predictions (ensembles)

How to Control Model Capacity With Nodes and Ensemble Methods for Deep Learning Neural
Layers Networks
How to Develop Model Averaging Ensembles
How to Choose Loss Functions When Training How to Develop a Cross-Validation and Bagging
Neural Networks Ensembles
Understand the Impact of Learning Rate on Model How to Develop a Stacking Deep Learning
Performance Ensemble
How to Fix Vanishing Gradients Using the ReLU
Tips, Tricks, and Resources
Better Generalization (fix overfitting) 8 Tricks for Configuring Backpropagation
Regularization to Reduce Overfitting of Neural Tricks of the Trade Review
Networks Three Must-Own Books for Deep Learning
How to Use Weight Decay to Reduce Overfitting Practitioners
How to Reduce Overfitting With Dropout Impact of Dataset Size on Deep Learning Model
Regularization Skill
How to Stop Training At the Right Time Using
Early Stopping

Ensemble Learning

Predictive performance is the most important concern on many classification and regression problems. Ensemble
learning algorithms combine the predictions from multiple models and are designed to perform better than any
contributing ensemble member.

Here’s how to get started with getting better ensemble learning performance:

Step 1: Discover ensemble learning.

A Gentle Introduction to Ensemble Learning
Why Use Ensemble Learning
Step 2: Discover ensemble learning algorithms.
A Gentle Introduction to Ensemble Learning Algorithms
Step 3: Discover techniques that you can use to improve performance.
Ensemble Machine Learning With Python (7-Day Mini-Course)
Ensemble Learning Algorithms With Python (my book)

You can see all ensemble learning posts here. Below is a selection of some of the most popular tutorials.

Ensemble Basics Bagging Ensembles

Ensemble Learning Algorithm Complexity Bagging Ensemble With Python
What Is Meta Learning Bagging Data Transformations
How Ensemble Learning Works Random Subspace Ensemble

Stacking Ensembles Boosting Ensembles

Essence of Stacking Gradient Boosting Machine
Stacking Ensemble Algorithms Extreme Gradient Boosting
Blending Ensemble Algorithms Histogram-based Gradient Boosting
Long Short-Term Memory Networks (LSTMs)

Long Short-Term Memory (LSTM) Recurrent Neural Networks are designed for sequence prediction problems and
are a state-of-the-art deep learning technique for challenging prediction problems.

Here’s how to get started with LSTMs in Python:

Step 1: Discover the promise of LSTMs.

The Promise of Recurrent Neural Networks for Time Series Forecasting
Step 2: Discover where LSTMs are useful.
Making Predictions with Sequences
A Gentle Introduction to Long Short-Term Memory Networks by the Experts
Introduction to Models for Sequence Prediction
Step 3: Discover how to use LSTMs on your project.
The 5 Step Life-Cycle for Long Short-Term Memory Models in Keras
Long Short-Term Memory Networks (Mini-Course)
Long Short-Term Memory Networks With Python (my book)

You can see all LSTM posts here. Below is a selection of some of the most popular tutorials using LSTMs in Python
with the Keras deep learning library.

Data Preparation for LSTMs Modeling with LSTMs

How to Reshape Input Data for Long Short-Term Generative Long Short-Term Memory Networks
Memory Networks Stacked Long Short-Term Memory Networks
How to One Hot Encode Sequence Data Encoder-Decoder Long Short-Term Memory
How to Remove Trends and Seasonality with a Networks
Difference Transform CNN Long Short-Term Memory Networks
How to Scale Data for Long Short-Term Memory Diagnose Overfitting and Underfitting of LSTM
Networks Models
How to Prepare Sequence Prediction for How to Make Predictions with Long Short-Term
Truncated BPTT Memory Models
How to Handle Missing Timesteps in Sequence
Prediction Problems LSTM for Time Series
On the Suitability of LSTMs for Time Series
LSTM Behaviour
Forecasting
A Gentle Introduction to Backpropagation Through Time Series Forecasting with the Long Short-Term
Time Memory Network
Demonstration of Memory with a Long Short-Term Multi-step Time Series Forecasting with Long
Memory Network Short-Term Memory Networks
How to Use the TimeDistributed Layer for Long Multivariate Time Series Forecasting with LSTMs
Short-Term Memory Networks in Keras
How to use an Encoder-Decoder LSTM to Echo
Sequences of Random Integers
Attention in Long Short-Term Memory Recurrent
Neural Networks
Deep Learning for Natural Language Processing (NLP)

Working with text data is hard because of the messy nature of natural language.

Text is not “solved” but to get state-of-the-art results on challenging NLP problems, you need to adopt deep learning
methods

Here’s how to get started with deep learning for natural language processing:

Step 1: Discover what deep learning for NLP is all about.

What is Natural Language Processing?
What is Deep Learning?
Promise of Deep Learning for Natural Language Processing
Step 2: Discover standard datasets for NLP.
7 Applications of Deep Learning for Natural Language Processing
Datasets for Natural Language Processing
Step 3: Discover how to work through problems and deliver results.
Crash-Course in Deep Learning for Natural Language Processing
Deep Learning for Natural Language Processing (my book)

You can see all deep learning for NLP posts here. Below is a selection of some of the most popular tutorials.

Bag-of-Words Model Word Embeddings

What is the Bag-of-Words Model? What are Word Embeddings?
How to Prepare Text Data for Machine Learning How to Develop Word Embeddings in Python with
with scikit-learn Gensim
How to Develop a Bag-of-Words Model for How to Use Word Embedding Layers for Deep
Predicting Sentiment Learning with Keras

Language Modeling Photo Captioning

Gentle Introduction to Statistical Language How to Automatically Generate Textual
Modeling and Neural Language Models Descriptions for Photographs with Deep Learning
How to Develop a Character-Based Neural A Gentle Introduction to Deep Learning Caption
Language Model in Keras Generation Models
How to Develop a Word-Level Neural Language How to Develop a Deep Learning Photo Caption
Model and Use it to Generate Text Generator from Scratch

Text Summarization Text Translation

A Gentle Introduction to Text Summarization A Gentle Introduction to Neural Machine
How to Prepare News Articles for Text Translation
Summarization How to Configure an Encoder-Decoder Model for
Encoder-Decoder Models for Text Summarization Neural Machine Translation
in Keras How to Develop a Neural Machine Translation
System from Scratch
Text Classification
Best Practices for Text Classification with Deep
Learning
How to Develop a Bag-of-Words Model for
Sentiment Analysis
How to Develop a CNN for Sentiment Analysis

Deep Learning for Computer Vision

Working with image data is hard because of the gulf between raw pixels and the meaning in the images.

Computer vision is not solved, but to get state-of-the-art results on challenging computer vision tasks like object
detection and face recognition, you need deep learning methods.

Here’s how to get started with deep learning for computer vision:

Step 1: Discover what deep learning for Computer Vision is all about.
What is Computer Vision?
What is the Promise of Deep Learning for Computer Vision?
Step 2: Discover standard tasks and datasets for Computer Vision.
9 Applications of Deep Learning for Computer Vision
How to Load and Visualize Standard Computer Vision Datasets With Keras
How to Develop and Demonstrate Competence With Deep Learning for Computer Vision
Step 3: Discover how to work through problems and deliver results.
How to Get Started With Deep Learning for Computer Vision (7-Day Mini-Course)
Deep Learning for Computer Vision (my book)

You can see all deep learning for Computer Vision posts here. Below is a selection of some of the most popular
tutorials.

Image Data Handling Image Data Preparation

How to Load and Manipulate Images With How to Manually Scale Image Pixel Data for Deep
PIL/Pillow Learning
How to Load, Convert, and Save Images With the How to Evaluate Pixel Scaling Methods for Image
Keras API Classification
Introduction to hannels First and Channels Last How to Normalize, Center, and Standardize
Image Formats Images in Keras

Image Data Augmentation Basics of Convolutional Neural Networks

How to Load Large Datasets From Directories Gentle Introduction to Convolutional Layers in
How to Configure and Use Image Data CNNS
Augmentation Gentle Introduction to Padding and Stride in CNNs
Introduction to Test-Time Data Augmentation Gentle Introduction to Pooling Layers in CNNs

Image Classification Object Recognition

How to Develop a CNN for CIFAR-10 Photo A Gentle Introduction to Object Recognition
Classification How to Perform Object Detection with Mask R-
How to Develop a CNN to Classify Photos of Dogs CNN
and Cats
How to Develop a CNN to Classify Satellite Photos How to Perform Object Detection With YOLOv3 in
Keras

Deep Learning for Time Series Forecasting

Deep learning neural networks are able to automatically learn arbitrary complex mappings from inputs to outputs
and support multiple inputs and outputs.

Methods such as MLPs, CNNs, and LSTMs offer a lot of promise for time series forecasting.

Here’s how to get started with deep learning for time series forecasting:

Step 1: Discover the promise (and limitations) of deep learning for time series.
The Promise of Recurrent Neural Networks for Time Series Forecasting
On the Suitability of Long Short-Term Memory Networks for Time Series Forecasting
Results From Comparing Classical and Machine Learning Methods for Time Series Forecasting
Step 2: Discover how to develop robust baseline and defensible forecasting models.
Taxonomy of Time Series Forecasting Problems
How to Develop a Skillful Machine Learning Time Series Forecasting Model
Step 3: Discover how to build deep learning models for time series forecasting.
How to Get Started with Deep Learning for Time Series Forecasting (7-Day Mini-Course)
Deep Learning for Time Series Forecasting (my book)

You can see all deep learning for time series forecasting posts here. Below is a selection of some of the most
popular tutorials.

Forecast Trends and Seasonality (univariate) Models Types

Grid Search SARIMA Models for Time Series How to Develop MLPs for Time Series Forecasting
Forecasting How to Develop CNNs for Time Series Forecasting
Grid Search Exponential Smoothing for Time How to Develop LSTMs for Time Series
Series Forecasting Forecasting
Develop Deep Learning Models for Univariate
Forecasting Time Series Case Studies
Indoor Movement Time Series Classification
Human Activity Recognition (multivariate
Probabilistic Forecasting Model to Predict Air
classification) Pollution Days
How to Model Human Activity From Smartphone Predict Room Occupancy Based on Environmental
Data Factors
How to Develop CNN Models for Human Activity Predict Whether Eyes are Open or Closed Using
Recognition Brain Waves
How to Develop RNN Models for Human Activity
Recognition
Forecast Air Pollution (multivariate, multi-step)
Load, Visualize, and Explore a Air Pollution
Forecast Electricity Usage (multivariate, multi- Forecasting
step) Develop Baseline Forecasts for Air Pollution
Forecasting
How to Load and Explore Household Electricity Develop Autoregressive Models for Air Pollution
Usage Data Forecasting
Multi-step Time Series Forecasting with Machine Develop Machine Learning Models for Air Pollution
Learning Forecasting
How to Develop CNNs for Multi-Step Time Series
Forecasting

Generative Adversarial Networks (GANs)

Generative Adversarial Networks, or GANs for short, are an approach to generative modeling using deep learning
methods, such as convolutional neural networks.

GANs are an exciting and rapidly changing field, delivering on the promise of generative models in their ability to
generate realistic examples across a range of problem domains, most notably in image-to-image translation tasks.

Here’s how to get started with deep learning for Generative Adversarial Networks:

Step 1: Discover the promise of GANs for generative modeling.

18 Impressive Applications of Generative Adversarial Networks
Step 2: Discover the GAN architecture and different GAN models.
A Gentle Introduction to Generative Adversarial Networks
A Tour of Generative Adversarial Network Models
Step 3: Discover how to develop GAN models in Python with Keras.
How to Get Started With Generative Adversarial Networks (7-Day Mini-Course)
Generative Adversarial Networks with Python (my book)

You can see all Generative Adversarial Network tutorials listed here. Below is a selection of some of the most
popular tutorials.

GAN Fundamentals Develop Simple GAN Models

How to Code the GAN Training Algorithm and Loss How to Develop a 1D GAN From Scratch
Functions How to Develop a GAN for Generating MNIST
How to use the UpSampling2D and Digits
Conv2DTranspose Layers How to Develop a GAN to Generate CIFAR10
How to Implement GAN Hacks in Keras to Train Photos
Stable Models
GANs for Image Translation
GAN Loss Functions
How to Implement Pix2Pix GAN Models From
How to Implement Wasserstein Loss (WGAN) Scratch
How to Develop a Least Squares GAN (LSGAN) How to Implement CycleGAN Models From
Scratch
Attention and Transformers

Attention mechanisms are the techniques invented to mitigate the issue where recurrent neural networks failed to
work well with long sequences of input. We learned that the attention mechanism itself can be used as a building
block of neural networks and therefore we now have the transformer architecture.

Attention mechanisms and transformer models are shown to deliver amazing results, especially in natural language
processing. There are examples of using transformer models in one way or another that make computers
understand human language and perform tasks such as translation or summarizing a paragraph, in human-like
quality.

Here’s how to get started to understand attention mechanisms and transformers:

Step 1: Learn about what attention is and what it can do.

A Bird’s Eye View of Research on Attention
Step 2: Discover how to use attention in a neural network model.
Adding a Custom Attention Layer to a Recurrent Neural Network in Keras
Step 3: Learn how the transformer model is built from the attention mechanism.
The Transformer Model
Building Transformer Models with Attention (my book)

You can see all Attention and Transformer tutorials listed here. Below is a selection of some of the most popular
tutorials.

Attention Fundamentals Building a Transformer Model from Scratch

What Is Attention? How to Implement Scaled Dot-Product Attention
A Bird’s Eye View of Research on Attention from Scratch in TensorFlow and Keras
A Tour of Attention-Based Architectures How to Implement Multi-Head Attention from
The Luong Attention Mechanism Scratch in TensorFlow and Keras
Implementing the Transformer Encoder from
Transformer Fundamentals Scratch in TensorFlow and Keras
The Transformer Attention Mechanism Implementing the Transformer Decoder from
The Transformer Model Scratch in TensorFlow and Keras
The Transformer Positional Encoding Layer in Joining the Transformer Encoder and Decoder
Keras, Part 2 Plus Masking
Training the Transformer Model

Need More Help?

I’m here to help you become awesome at applied machine learning.

If you still have questions and need help, you have some options:

Ebooks: I sell a catalog of Ebooks that show you how to get results with machine learning, fast.
Machine Learning Mastery EBook Catalog
Blog: I write a lot about applied machine learning on the blog, try the search feature.
Machine Learning Mastery Blog
Frequently Asked Questions: The most common questions I get and their answers
Machine Learning Mastery FAQ
Contact: You can contact me with your question, but one question at a time please.
Machine Learning Mastery Contact

© 2024 Guiding Tech Media. All Rights Reserved.

LinkedIn | Twitter | Facebook | Newsletter | RSS

Privacy | Disclaimer | Terms | Contact | Sitemap | Search