Machine Learning

Machine Learning is a five-day course that is designed for technical professionals, including software engineers, data engineers, data scientists, machine learning engineers, machine learning scientists, and IT professionals.

 Prerequisites: Participants should have a relatively good understanding – at undergraduate level – of calculus, linear algebra, optimization, probability, and statistics. Participants are also expected to be familiar with coding in a high-level language (ideally Python) for the hands-on sessions.

This Machine Learning training course leads the audience into a deep dive towards modern machine learning models, algorithms, tools, and applications.

The course content is split into five parts:

• Part 1 introduces basic machine learning models and algorithms with a focus on supervised learning methods such as regression and classification
• Part 2 introduces additional machine learning models and algorithms with a focus on unsupervised learning techniques such as clustering
• Part 3 presents deep learning methods – including neural network models, convolutional neural networks, recurrent neural networks; it also presents adversarial learning methods such as GANs
• Part 4 focuses on reinforcement learning, deep reinforcement learning, and their applications
• Part 5 covers emerging topics in machine learning such as privacy, fairness, and explainability in machine learning and artificial intelligence

The course also offers – across these five parts – an overview of applications of the various machine learning approaches, in a variety of areas such as computer vision, speech recognition, speech translation, and natural language processing

Participants will be able to learn about, study and review modern aspects of machine learning; participants will also experiment with various data-oriented problems, challenges, and use-cases using Python and/or Jupyter notebooks.

• Understanding key machine learning principles, methods, and tools for supervised and unsupervised learning
• Understanding cutting-edge machine learning approaches such as deep learning, reinforcement learning, adversarial learning, and other state-of-the-art techniques
• Gaining a competitive advantage by exploring applications of cutting-edge machine learning and artificial intelligence techniques in computer vision, speech recognition, speech translation, and natural language processing
• Diving into emerging topics in AI such as Privacy, Fairness, Transparency, Explainability, and Accountability

• Equipping the engineers of your organization with the necessary knowledge to develop state-of-the-art machine learning models, algorithms, and methods
• Preparing your team for future deployments of artificial intelligence by exposing your team to topics such as AI Privacy, Fairness, Transparency, and Ethics
• Enhancing your team’s technical understanding of emerging applications of machine learning and artificial intelligence, to areas such as big data, computer vision, and natural language processing

• Offering your team a view of real-world case studies to ensure that it is ready to recognize machine learning opportunities for your organization

Instructor-Led Training

On-Site Classroom: 5 days

Web delivered (Virtual): 5 days

Excellent and descriptive course material – pdf files and associated code (Jupyter notebooks) will be provided