This course gives an in-depth understanding of data analysis and the machine learning concept. Understand the difference between types of machine learning (unsupervised, supervised, and reinforcement learning). Get introduced to different supervised learning algorithms for regression and classification problems, as well as to different unsupervised learning algorithms for data clustering and dimensionality reduction problems. Get into the topic of neural networks and deep learning. Finally, the course provides the background of convolutional neural networks and their application to different real-world problems.
Course Topics:
- Introduction to data analysis and machine learning concept
- Supervised learning – regression
- Supervised learning – classification
- Supervised learning – non-linear models
- Good practice for data preparation and training process
- Unsupervised learning – dimensionality reduction
- Unsupervised learning – data clustering
- Introduction to neural networks
- Introduction to convolutional neural networks (CNN)
- Popular and widely-used CNN structures and applications
Requirements
Software: Python, Scikit-learn, Keras and Chrome browser.
Hardware: Computer with an Internet connection, working speakers, and microphone.
Prior knowledge: Students should have basic knowledge of Python language, and be able to write simple programs. Students should have basic knowledge in digital image processing or have previously attended the course Basics of Image Processing and Computer Vision.
