Duration
21 hours (usually 3 days including breaks)
Requirements
- Python programming experience
- An understanding of basic principles of machine learning
Audience
- Developers
- Analysts
- Data scientists
Overview
In this instructor-led, live training, participants will learn the most relevant and cutting-edge machine learning techniques in Python as they build a series of demo applications involving image, music, text, and financial data.
By the end of this training, participants will be able to:
- Implement machine learning algorithms and techniques for solving complex problems.
- Apply deep learning and semi-supervised learning to applications involving image, music, text, and financial data.
- Push Python algorithms to their maximum potential.
- Use libraries and packages such as NumPy and Theano.
Format of the course
- Part lecture, part discussion, exercises and heavy hands-on practice
Course Outline
Introduction
Describing the Structure of Unlabled Data
- Unsupervised Machine Learning
Recognizing, Clustering and Generating Images, Video Sequences and Motion-capture Data
- Deep Belief Networks (DBNs)
Reconstructing the Original Input Data from a Corrupted (Noisy) Version
- Feature Selection and Extraction
- Stacked Denoising Auto-encoders
Analyzing Visual Images
- Convolutional Neural Networks
Gaining a Better Understanding of the Structure of Data
- Semi-Supervised Learning
Understanding Text Data
- Text Feature Extraction
Building Highly Accurate Predictive Models
- Improving Machine Learning Results
- Ensemble Methods
Summary and Conclusion