Hier geht es zur Version auf deutsch / link to the German version
You receive the knowledge from real projects and top notch technologies for, e.g., Big Data (e.g. with Apache Spark, PySpark, databricks), Security Incident and Event Management (e.g. with Splunk), Machine Learning and Data Science with Python.
Contact training(at)buhlmeier.com for details and competitive pricing.
Courses can be online or on location and are in German or English, slides are mostly in English
Machine Learning with Python – from basics to Large Language Models (LLM)
Machine Learning context
Machine Learning basics
Supervised Learning
Unsupervised Learning
Reinforcement Learning
Exercises
Supervised Learning for pattern recognition: Video and Tensorflow.js
Network architecture
Deeper into Machine Learning
Some Math
Reinforcement Learning
Exercise (Taxi Game Q-Learner)
Machine Learning mit Tensorflow
Backpropagation Algorithmn in more detail
Coding with tensorflow
Monte Carlo simulation
Neural Network with TF
Keras Tensorboard
Data processing steps, from source to prediction
Convolutional Layers in Tensorflow and their application
Time Series predictions with deep learning (Long – short term memory NN)
Explain-ability
Text classification: IMDB sentiment analysis
Generative models
For image creation (exercise with own picture)
For text creation
LLMs
Architecture
Refinements and success factors
Summary and Outlook
Big Data Analysis with Apache Spark, PySpark, databricks, Python, Scala
Overview Apache Spark/PySpark and databricks
Install Apache Spark, PyCharm or VSCode
First exercises
Pandas Dataframes vs. PySpark Dataframes, Best practices
Exercises Dataframes
Spark Streaming
Spark ML Lib
PySpark and SQL
Graph Theory
Scala Overview, Motivation
Installation and tests
Scala simple Exercises
Object Oriented Programminng with Scala
GraphX (Context, History, Restrictions)
Exercises
Elastic Search Integration
Operations Research with Python
Definition, Problems and Solutions
Linear Models, Algebra and their Geometry with Exercise
Model Overview
MIP Library: (Mixed) Integer Programmierung with exercises (Knapsack, Scheduling)
More on the MIP Library: (Mixed) Integer Programmierung
Network Models, Network-Algorithmns, dynamic Models
Simplex-Method
Sensitivity analysis
Dynamic Programming
Neural Networks
Non-linear Programming
Queueing theory
Deterministic logistic
Probabilistic logistic
Python packages comparison
Conclusion and outlook
Optional advanced topics:
non-linear target function
advanced non-linear programming
SIEM and other applications with Splunk
Introduction and expectations
The context of Splunk
Splunk components
Splunk’s GUI basics
Search basics
Search using fields
The search language in more detail
Exercises
Transformations
Pivots
Questions & Feedback
Exercises:
Create reports
Lookups
Scheduled reports and alerts
Dashboards
The common information model
Installation assessment (queries that help to check your setup)
Splunk Apps/Add ons, e.g.:
Enterprise Security
Machine Learning Toolkit
Implement your requirements
Splunk Dashboard Studio and Dashboard Classic(see video in German)
Current Frameworks
Recap XML Dashboards
Classic vs. Dashboard Studio
Using Dasboard Studio
Chain Searches, Maps, ..
Exercise
What are Tokens used for
Token Examples with XML Dashboards and Dasboard Studio
Exercise
Compatibility
Summary
Database data ingestion and visualization with Splunk (see teaser on you tube in German)
Introduction
Prerequisites/Requirements
Configuration
Using DB Connect
Creating Identities
Creating Connections
Creating Database Outputs/Inputs
Creating and managing Database Lookups
Further Functions and Troubleshooting
Using SQL Explorer to make Live Reports
Executing SQL statements and stored procedures with the dbxquery Command
Monitoring Splunk DB Connect Health
Splunk Live Demonstration
