Practical Machine Learning by Example in Python
A Deep Dive into Building Machine Learning and Deep Learning models
- Develop complete machine learning/deep learning solutions in Python
- Write and test Python code interactively using Jupyter notebooks
- Build, train, and test deep learning models using the popular Tensorflow 2 and Keras APIs
- Neural network fundamentals by building models from the ground up using only basic Python
- Manipulate multidimensional data using NumPy
- Load and transform structured data using Pandas
- Build high quality, eye catching visualizations with Matplotlib
- Reduce training time using free Google Colab GPU instances in the cloud
- Recognize images using Convolutional Neural Networks (CNNs)
- Make recommendations using collaborative filtering
- Detect fraud using autoencoders
- Improve model accuracy and eliminate overfitting
- Basic software development skills
- Basic high school math, such as trigonometry and algebra
Are you a developer interested in building machine learning and deep learning models? Do you want to be proficient in the rapidly growing field of artificial intelligence? One of the fastest and easiest ways to learn these skills is by working through practical hands-on examples.
LinkedIn released it’s annual “Emerging Jobs” list, which ranks the fastest growing job categories. The top role is Artificial Intelligence Specialist, which is any role related to machine learning. Hiring for this role has grown 74% in the past few years!
In this course, you will work through several practical, machine learning examples, such as image recognition, sentiment analysis, fraud detection, and more. In the process, you will learn how to use modern frameworks, such as Tensorflow 2/Keras, NumPy, Pandas, and Matplotlib. You will also learn how use powerful and free development environments in the cloud, like Google Colab.
Each example is independent and follows a consistent structure, so you can work through examples in any order. In each example, you will learn:
- The nature of the problem
- How to analyze and visualize data
- How to choose a suitable model
- How to prepare data for training and testing
- How to build, test, and improve a machine learning model
- Answers to common questions
- What to do next
Of course, there are some required foundations you will need for each example. Foundation sections are presented as needed. You can learn what interests you, in the order you want to learn it, on your own schedule.
Why choose me as your instructor?
- Practical experience. I actively develop real world machine learning systems. I bring that experience to each course.
- Teaching experience. I’ve been writing and teaching for over 20 years.
- Commitment to quality. I am constantly updating my courses with improvements and new material.
- Ongoing support. Ask me anything! I’m here to help. I answer every question or concern promptly.
clear explanations..to the point and no jargon..neat presentation of notebooks with codes..it’s a step by step guide on creating machine learning models using Google colab..the models explained here are basic and thus perfect for beginners ,to understand how machine learning models are created based on the given problem and about techniques used to improve the accuracy..with the resources shared and Mr.Madhu’s immediate response to messages/QA,one can learn more about a topic..highly recommended to all machine learning enthusiasts. – Ashraf UI
The cours is easy to understand and well presented, same thing for the practical examples Using google colab was a very good idea to present the course and to do the exercices , we can easily test a function or a line of code. The last three sections are very intresting, they are practical exercices for deep learning well presented and commented – Iheb GANDOUZ
The way it is explained is really cool. I used to be bored after an hour during lectures, but the guide somehow makes it very interesting…. – Anu Priya J
January 2020 updates:
- New mathematics and machine learning foundation section including
- Logistic regression, loss and cost functions, gradient descent, and backpropagation
- All examples updated to use Tensorflow 2 (Tensorflow 1 examples are available also)
- Jupyter note introduction
- Python quick start
- Basic linear algebra
March 2020 updates:
- A sentiment and natural language processing section
- This includes a modern BERT classification model with surprisingly high accuracy
April/May 2020 updates:
- Numerous assignment improvements, e.g. self-paced or guided approach
- Add lectures on Google Colab, Python quick start, classify your own images and more!
- Anyone interesting in developing machine learning and deep learning skills
Created by Madhu Siddalingaiah
Last updated 5/2020
Size: 2.70 GB