Learn the syntax of Julia and its differences from Python, its strength in terms of data science and machine learning.
Read more.Instructor
PhD, programmer, researcher, designer and teacher. See more on recluze.net
Access all courses in our library for only $9/month with All Access Pass
Get Started with All Access PassBuy Only This CourseAbout This Course
Who this course is for:
- All levels of Data Science practitioners
- All levels of Machine Learning practitioners
- Those aiming to enhance their abilities and skill level in DS and ML
- Developers who want to know how to harness the power of big data
What you’ll learn:Â
- Syntax of Julia (and differences from Python)
- Strength of Julia in terms of data science and machine learning
- DataFrames (equiv. to Pandas) in Julia
- Data science case studies including, analysis and clustering
- Machine learning models, both traditional and deep
- Create ML models from scratch in a way that helps you make modifications easily
Requirements:Â
- Basic understanding of programming
- Python would be helpful but not necessary
- Understanding of basic Data Science (reading CSVs etc.) would be helpful
- Understanding of basic concepts of Deep Learning (such as classification) would be useful
In the fast-paced world of Data Science and Machine Learning, you have to stay up-to-date and keep ahead of the competition. For this, you have to constantly be on the lookout for the latest trends in tools and techniques for Data Science and Machine Learning. You don’t want to miss out on the latest trend and the tool of the future! Right now, that tool is the Julia programming language. It’s the hot new language that all ML and data science experts are very excited about. Learning Julia will open up several doors for you in your career!
That is the objective of this course: to give you a strong foundation needed to excel in Julia and learn the core of the language as well as the applied side in the shortest amount of time possible.
In this course, we take a code-oriented approach. We don’t waste time with the theory of why Julia is fast. We jump right into the details and start coding. You will quickly realize how easy it is to learn this state-of-the-art and promising language. You will see how you can start using Julia to excel in your current job without moving the whole stack to Julia immediately.Â
We take a case-study-based approach. After explaining the basic concepts, we jump to case studies in data science and then machine learning. We apply both traditional machine learning models, and then get into deep learning. You will see how Julia can help you create deep learning models from scratch in just a few lines of code and then move on to the state-of-the-art models without spending too much time.
This way, you get to learn the most important concepts in this subject in the shortest amount of time possible without having to deal with the details of the less relevant topics. Once you have developed an intuition of the important stuff, you can then learn the latest and greatest models, even on your own!
Our Promise to You
By the end of this course, you will have learned Julia programming.
Â
10 Day Money Back Guarantee. If you are unsatisfied for any reason, simply contact us and we’ll give you a full refund. No questions asked.
Â
Get started today and learn more about programming, data science and machine learning.
Course Curriculum
Section 1 - Intro And Setting Up | |||
Installing Julia (Windows, Linux and MacOS) | 00:00:00 | ||
Packages And Interactive Notebook | 00:00:00 | ||
Course Resources | 00:00:00 | ||
Section 2 - Core Language Basics | |||
Basic Syntax, Variables And Operations | 00:00:00 | ||
Control Structures, Iterations And Ranges | 00:00:00 | ||
Data Structures In Julia: Lists Or Arrays, Tuples, Named Tuples | 00:00:00 | ||
Dictionaries (Maps), Symbols In Julia | 00:00:00 | ||
Section 3 - Arrays And Matrices - Native Language Support | |||
Arrays, Matrices, Tensors, Reshaping, Helper Functions | 00:00:00 | ||
Data Type Details, Casting Among Types | 00:00:00 | ||
Section 4 - Functions And Fun Stuff | |||
Defining Functions, Overloading, Multiple-Dispatch | 00:00:00 | ||
Anonymous Functions (And Their Importance), Splatting And Slurping | 00:00:00 | ||
Functional Programming, Broadcasting – Most Important Concept In Julia | 00:00:00 | ||
Interfacing With Python And R | 00:00:00 | ||
Section 5 - Getting Started With Data Science | |||
Plotting Basics – Prettier Julia Plots | 00:00:00 | ||
Data Wrangling, Reading CSV Files, Descriptive Case Study | 00:00:00 | ||
Further Data Manipulation, Apache Arrow, Grouping And Analysis | 00:00:00 | ||
Section 6 - Case Studies In Data Science | |||
Case Study: Clustering For Housing Or Map Data | 00:00:00 | ||
Classification With Decision Trees Or Random Forests | 00:00:00 | ||
Section 7 - Deep Learning - Flux In Julia | |||
Writing A Neural Network From Scratch In A Few Lines | 00:00:00 | ||
Multiple Layers, State-Of-The-Art In A Few More Lines | 00:00:00 | ||
Case Study: MNIST, Modifying Data For Model, Avoiding Pitfalls | 00:00:00 | ||
MNIST Continued, Creating The Deep Model, Training And Testing | 00:00:00 | ||
Saving And Loading Models, Exploring More Options | 00:00:00 | ||
Section 8 - Parting Words | |||
Where To Go From Here: Pointers For Further Learning | 00:00:00 |