Technologies / Artificial Intelligence

Auto-sklearn - automatic machine learning

The training provides a practical introduction to Auto-sklearn, an advanced tool that automates the machine learning process in the scikit-learn ecosystem. The workshop program enables participants to learn the mechanisms of automatic algorithm selection and parameter tuning. The class combines theory with intensive practice, allowing participants to carry out ML projects on their own from conception to implementation.

Issues

Auto-sklearn architecture and components
Meta-learning and knowledge transfer
Automatic selection of models
Optimization of hyperparameters
Ensemble learning
Strategies for searching the space
Data preprocessing techniques
Validation and evaluation of models
Serialization and implementation
Performance monitoring
Integration with production systems
AutoML best practices

Benefits

The participant will develop the ability to effectively use Auto-sklearn in machine learning projects
Will gain the knowledge to automate the processes of selecting and tuning ML algorithms
Will learn to optimize the process of creating predictive models using meta-learning
Will learn techniques for creating and managing ensembles of models
Will be able to implement and monitor AutoML solutions in a production environment
Will master methods for integrating Auto-sklearn with existing analytical systems

Who is this training for?

Data analysts working in Python environment

Programmers looking to expand competencies with AutoML

Machine learning specialists looking to automate

Data engineers interested in optimizing ML processes

Scientists working with data

Data scientists aiming to speed up work

Field experts implementing ML solutions

Prerequisites

Knowledge of the basics of machine learning
Experience in Python programming
Ability to work with the scikit-learn library
Basic statistical knowledge

Training program

Integration with scikit-learn
Comparison with other AutoML tools

Environment and data preparation
Auto-sklearn configuration
Strategies for data preparation
Input and output formats

Automation of the modeling process
Configuring the search space
Optimization strategies

Ensemble learning
Implementation and maintenance of models
Export and serialization of models
Integration with production systems

Update and maintenance

Delivery Methods

Online

Convenience of participating from anywhere
Interactive live sessions with trainer
Materials available for 30 days
No travel costs

On-site

Direct contact with trainer and group
Intensive hands-on workshops
Networking with other participants
Full focus on learning

Frequently asked questions

What are the prerequisites for this training?

For Auto-sklearn - automatic machine learning we recommend: Knowledge of the basics of machine learning; Experience in Python programming; Ability to work with the scikit-learn library.

What is the format and duration of this training?

The training lasts 2 days and is available in online and on-site format. Sessions run from 9:00 AM to 4:00 PM. We can also customize the schedule to fit your team's needs.

Who is this training designed for?

This training is designed for: Data analysts working in Python environment; Programmers looking to expand competencies with AutoML; Machine learning specialists looking to automate.

What practical skills will I gain from this training?

You will develop the ability to effectively use Auto-sklearn in machine learning projects, automate the selection and tuning of ML algorithms, optimize predictive model creation using meta-learning, and implement AutoML solutions in production.

What is the difference between online and on-site formats?

Both formats cover the same content and are led by the same expert instructors. Online training offers flexibility and convenience, while on-site training provides direct interaction and hands-on lab access. Choose the format that best suits your team's needs.

How does Auto-sklearn differ from Auto-Keras for machine learning automation?

Auto-sklearn automates classical machine learning within the scikit-learn ecosystem, handling algorithm selection, hyperparameter optimization, and ensemble construction for structured/tabular data. Auto-Keras focuses on automating deep neural network architecture search. This training is ideal for those working with traditional ML problems on structured datasets.