Evergreen Alliance Training Program for GIAC Machine Learning Engineer (GMLE)

Anomaly Detection and Optimization
The candidate will gain a basic understanding of autoencoders and their use in anomaly detection problems. Additionally, the candidate will learn how genetic algorithms are applied to automate the optimization of neural networks.

Clustering
The candidate will learn fundamental machine learning concepts like clustering and unsupervised learning methods.

Convolutional Neural Networks
The candidate will gain an understanding of how convolutional neural networks (CNNs) are used for solving classification problems and for predictive analytics.

Data Acquisition
The candidate will learn about data acquisition, cleaning, and manipulation, including the necessary steps to prepare threat data for further analysis. The candidate will become familiar with methods for accessing data from SQL databases, document stores, and web scraping.

Leveraging Python
The candidate will acquire a basic understanding of Python and its modules, including NumPy, Pandas, and TensorFlow, and how to use them for extracting, visualizing, transforming, and loading data.

Neural Networks
The candidate will gain a fundamental understanding of deep learning concepts using neural networks for supervised learning, including loss and error functions, and an introduction to vectors, matrices, and tensors.

Probability and Frequency
The candidate will develop a basic understanding of probability theory, inference, Bayes’ theorem, and Fourier series.

Regressions
The candidate will learn about regressions and their application in deep learning, with an emphasis on understanding how they are used to model relationships between variables.

Statistics Fundamentals
The candidate will learn essential statistics concepts and how they apply to data science, especially in the context of threat hunting. The candidate will become familiar with terms like mean and median.

Supervised Learning
The candidate will learn about supervised learning techniques, including support vector classifiers, kernel functions, support vector machines, decision trees, and random forests.