As a recent graduate of the GIAC Machine Learning Engineer (GMLE) certification program, I've been frequently asked about my experience and recommendations for those considering or currently pursuing this new course (SEC595). In this article, I'll share my insights and a curated list of supplemental resources that I found invaluable during my studies.
My Learning Approach
I believe in reinforcing concepts through diverse explanations and examples. While the SANS SEC 595 course material is comprehensive, I sought additional resources to deepen my understanding. This approach may be more than necessary for some, but for those who desire a broader perspective or struggle with certain concepts, these supplemental materials can be incredibly helpful.
General Recommendations
Before diving into specific resources, I highly recommend exploring the work of Andrew Ng. His explanations of machine learning, deep learning, and AI concepts are exceptional and complement the SANS course material well. You can find his content on platforms like deeplearning.ai.
Originally this course description specifically stated you did not need to know much Python or mathematics prior to taking the course. However, it appears they have now updated it (probably based on some passionate feedback) to say "Intermediate Python fluency is important. Pre-calculus mathematics skills are important but not required." I included Python resources below that cover from absolute beginner to intermediate learners.
That said, the course still claims that they will show you math but not expect you to do it. That is not strictly true. You will still need to be able to perform things like calculations of mean, median, mode and standard deviations on datasets using Python. Hypothetically, you could argue you are not required to do the math because Python performs the calculations, but you do need to understand the math. If I said "Find the most common grade for these three tests" you should be able to say you're looking for the mode. I recommend when making your index that you create a separate index of just the mathematical equations and what page numbers they can be found on.
Section-by-Section Supplemental Resources
Below, I've mapped out supplemental learning resources to each section of the GMLE course. Most of these are free, though some may require a subscription. These are the courses and resources I used to help me pass the certification and more fully understand the material.
1. Introduction and Foundations
1.1-1.2: Course Overview and Technology Terms
YouTube: What is Machine Learning?
Medium Article: Unveiling the Depths of AI/ML
DeepLearning.AI: AI for Everyone
1.3: Python Refresher
For beginners: CodeCombat Python Courses
For refreshers: Codecademy: Learn Python 3
Recommended pre-course: Codecademy: Data and Programming Foundations for AI
1.4-1.7: Data Visualization, SQL, Document Stores, and Web Scraping
Codecademy: Intro to Data Visualization with Python
Codecademy: Analyze Data With Python
TutorialsPoint: MongoDB Query Document
Codecademy: Learn Web Scraping
2. Statistics and Data Exploration
2.1-2.3: Statistics, Data Exploration, and Probability
Codecademy: Statistics - Mean, Median and Mode
Codecademy: Learn Statistics with Python
Codecademy: Fundamental Math for Data Science
2.4: Time Domain vs Frequency Domain
YouTube: Time and Frequency Domains Explained
3. Machine Learning Algorithms
3.1-3.4: Clustering, Support Vector Machines, Decision Trees, and Random Forests
Codecademy: Build a Machine Learning Model
Codecademy: Machine Learning - Clustering with K-Means
YouTube: Support Vector Machines Explained
Codecademy: Machine Learning - Random Forests and Decision Trees
4. Advanced Machine Learning Concepts
4.1-4.4: Linear Regression, Neural Networks, Feature Selection, and Categorical Outputs
Codecademy: Linear Regression in Python
Codecademy: Introduction to Deep Learning with Tensorflow
Codecademy: Principal Component Analysis Intro
Codecademy: Deep Learning with Tensorflow Classification
5. Advanced Topics in AI/ML
5.2-5.4: Convolutional Neural Networks, Embeddings, and Autoencoders
Codecademy: Deep Learning with TensorFlow - Image Classification
Codecademy: Intro to Language Models in Python
YouTube: Autoencoders in Deep Learning
6. Advanced Applications
6.1-6.2: Convolutional Neural Networks and Genetic Algorithms
DeepLearning.AI: Deep Learning Specialization
Codecademy: Intro to Hyperparameter Tuning with Python
Conclusion
While these resources greatly enhanced my learning experience, it's important to note that the SANS course material alone is sufficient for most students to pass the GMLE certification. These supplemental materials are for those who, like me, benefit from multiple perspectives or seek a deeper understanding of the concepts.
Remember, the key to success in this course is consistent practice and hands-on application of the concepts. Don't just passively consume the material – engage with it, experiment, and most importantly, enjoy the learning process!
Good luck on your #GMLE #SEC595 journey!
No comments:
Post a Comment