Julia Programming Language for Data Science and Machine Learning - Best-seller video course
Julia programming language is widely considered one of the best and most elegant programming languages for data science, machine learning, and numerical computing. Check out the beauty of this language in this best-seller course preview.
Full course can be seen here: https://recluze.net/course-full-julia for just $25 (lifetime access) or $5/month.
Get more courses like this on: https://recluze.net/learn
0:00 Course Promo
02:51 Installation and Notebook Setup
06:17 Syntax of Julia
21:23 Arrays, Matrices and Tensors
36:36 Functions and Methods
50:00 Plotting and Visualization
55:20 Traditional Machine Learning (Classification)
1:05:20 Neural Networks with Julia
1:21:30 Generative Adversarial Networks (GANs)
The full course on https://recluze.net/course-full-julia has the following contents.
Section 0
Intro and Setting up
Installing Julia (Windows, Linux and MacOS)
Packages and Interactive Notebook
Section 1
Core Language Basics
Basic Syntax, Variables and Operations
Control Structures, Iterations and Ranges
Data Structures in Julia: Lists/Arrays, Tuples, Named Tuples
Dictionaries (Maps), Symbols in Julia
Section 2
Arrays and Matrices: Native Language Support
In this section, we will see one of the core strengths of Julia - matrices.
Arrays, Matrices, Tensors, Reshaping, Helper Functions
See why arrays are the most powerful structures in Julia.
Data Type Details, Casting Among Types
Learn how data types affect your code in Julia.
Section 3
Functions and Fun Stuff
In this section, we will create Julia functions using different syntaxes and see which ones are suitable for which situation.
Defining Functions, Overloading, Multiple-Dispatch
Learn basic function definitions and the differences between methods and functions.
Anonymous Functions (and their importance), Splatting and Slurping
See some novel features of Julia when it comes to function definitions.
Functional Programming, Broadcasting - Most Important Concept in Julia
Learn one of the most elegant ways Julia makes data science and ML code beautiful - broadcasting!
Interfacing with Python and R
See how you can call your existing Python or R code from within Julia with just a couple of lines of code.
Section 4
Getting Started with Data Science
In this section, we will start with some basic data science tools provided by Julia such as plotting and manipulating CSV files.
Plotting Basics - Prettier Julia Plots
See different plotting options in Julia.
Data Wrangling, Reading CSV Files, Descriptive Case Study
Learn how to work with CSV files easily.
Further Data Manipulation, Apache Arrow, Grouping and analysis
See how you can handle large, several gigabyte files with Julia.
Section 5
Case Studies in Data Science
In this section, we will start with the most common case studies in Julia. Data science is extremely popular and Julia is extremely good at it. In these lectures, you'll see why that is.
Case Study: Clustering for Housing/Map Data
Real-world case study for performing clustering on map data.
Classification with Decision Trees/Random Forests
Use ML libraries in Julia to perform traditional machine learning.
Section 6
Deep Learning - Flux in Julia
In this section, we will take a look at the awesome Flux framework in Julia. We will see how we can create state-of-the-art ML models using minimal effort in Julia.
Writing a Neural Network from Scratch in a Few Lines
See the awesome Flux library and how it handles most of the grunt work in deep learning automatically for you.
Multiple Layers, State-of-the-Art in a Few More Lines
Scale up your ML model to several layers easily with absolutely elegant code.
Case Study: MNIST, Modifying Data for Model, Avoiding Pitfalls
Real-world case study with in-depth analysis of code.
Saving and Loading Models, Exploring More Options
Learn how to handle training of models that take a long time and must be reused later on.
Section 7
Parting Words
Where to Go from Here: Pointers for Further Learning
Section 8
Basics of GANs - Motivation and Architecture
Study the background, rationale, and core idea behind Generative Adversarial Networks (GANs).
Using Google Colaboratory for GPU Usage in Julia
Learn how to get the free GPU on Google Colab working Julia. Set it up in just a couple of minutes and save/load data from Google Drive for persistent storage.