Fundamentals of Machine Learning
Course focuses on the newest technologies of Microsoft Machine Learning Server and SQL Server 2017. By popular demand, second part (3 days) of this course teaches programming in R, however most of the course is also applicable to Python programmers, as the key libraries are the same.
Kirjeldus
This course has two parts: 2-day part A: Fundamentals of Machine Learning followed by 3-day Part B: Immersion into Machine Learning in R, SQL Server 2017, and Microsoft ML Server. The first part introduces the most important concepts and tools, while the second part teaches you R and how to use it for machine learning on the Microsoft platform.
Eesmärk
The course covers Machine Learning Fundamentals, Algorithms, Data preparation, Data Science process, Model Building, Model Validation. It also emphasizes the importance of validation and improvement of models in data science projects.
Sihtgrupp
Analysts, budding data scientists, data scientists, database and BI developers, programmers, power users, DBAs, predictive modellers, forecasters, consultants.
Programm
- Machine Learning Fundamentals
- Topics include:
- Machine learning vs. data mining vs. artificial intelligence
- Tool landscape: open source R vs. Microsoft R, Python, SQL Server, ML Server, Azure ML
- Teamwork
- Topics include:
- Algorithms
- Topics include:
- What do algorithms do?
- Algorithm classes in R, Python, ML Server, Azure ML, and SSAS Data Mining
- Supervised vs. unsupervised learning
- Classifiers
- Clustering
- Regressions
- Similarity Matching
- Recommenders
- Topics include:
- Data
- Topics include:
- Cases, observations, signatures
- Inputs and outputs, features, labels, regressors, independent and dependent variables, factors
- Data formats, discretization/quantizing vs. continuous
- Indicator columns
- Feature engineering
- Azure ML data preparation and manipulation modules
- Moving data around and its storage, SQL vs. NoSQL, files, data lakes, BLOBs, and Hadoop
- Topics include:
- Process of Data Science
- Topics include:
- CRISP-DM
- Stating business question in data science term
- Hypothesis testing and experiments
- Student’s t-test
- Pearson chi-squared test
- Iterative hypothesis refinement
- Topics include:
- Introduction to Model Building
- Topics include:
- Connecting to data
- Splitting data to create a holdout
- Training a decision tree
- Scoring the holdout
- Plotting accuracy
- Topics include:
- Introduction to Model Validation
- Topics include:
- Testing accuracy
- False positives vs. false negatives
- Classification (confusion) matrix
- Precision and recall
- Balancing precision with recall vs. business goals and constraints
- Introduction to lift charts and ROC curves
- Testing reliability
- Testing usefulness
- Topics include:
Omandatavad oskused
Participants will gain knowledge in Machine Learning Fundamentals, Algorithms, Data preparation, Data Science process, Model Building, and Model Validation.
Eeldused
If you have attended a prior course on Machine Learning and are well-versed in model validity, accuracy, and reliability, consider attending the 3-day course. Otherwise, it is recommended to attend both the 2-day and 3-day courses.
Lisainfo
Format: 50% lectures, 30% demos, 20% tutorials. Participants are encouraged to follow the demos and work on tutorials. Azure account is required during the course. Necessary data sets will be provided. Pre-built machines may be available in some training centers. The course is suitable for individuals with various backgrounds such as analysts, data scientists, developers, and consultants.
Investeering
Hind kokkuleppel
✨
Vajan seda oma tiimile
Aitame koostada päringu
✨
See koolitus hetkel ei toimu
Küsi lisainfot. Aitame leida sarnase koolituse või panna sinu soovi kirja.