Advance Python for Machine Learning


Start End Duration Location Details
January 10, 2022 January 14, 2022 KDE 3.1 Virtual Classroom (GMT+08:00)
April 18, 2022 April 22, 2022 KDE 3.1 Virtual Classroom (GMT+08:00)
July 11, 2022 July 15, 2022 KDE 3.1 Virtual Classroom (GMT+08:00)
October 10, 2022 October 14, 2022 KDE 3.1 Virtual Classroom (GMT+08:00)

Course Details

Advance Python for Machine Learning

Course code: APML 

Duration: 5 Days

Course Description:

You'll become familiar with the significant ideas, for example, exploratory information examination, information preprocessing, highlight extraction, information representation and bunching, characterization, relapse, and model execution assessment. With the assistance of the different activities included, you'll procure the mechanics of a few significant AI calculations. You'll likewise be guided bit by bit to construct your own models without any preparation. You'll figure out how to handle information driven issues and actualize your answers with the ground-breaking yet straightforward Python language. Intriguing and simple to-follow models—including news theme order, spam email location, online advertisement navigate expectation, and stock costs figures—will keep you stuck to the screen. Moving further, six diverse free ventures will assist you with acing AI in Python. At long last, you'll have a wide image of the AI biological system and aced best practices for applying AI methods.

Course Objectives:

•    Take the upside of the intensity of Python to deal with information extraction and control
•    Delve into the universe of investigation to anticipate exact circumstances
•    Implement AI arrangement and relapse calculations without any preparation with Python
•    Evaluate the exhibition of an AI show and streamline it
•    Explore and utilize Python's great AI biological system
•    Successfully assess and apply the best models to issues
•    Learn the essentials of NLP—and set up them as a regular occurrence
•    Visualize information for greatest effect and lucidity
•    Deploy AI models utilizing outsider APIs
•    Get to holds with highlight building    

Intended Audience:
•    This Learning Path is a dazzling excursion that starts from the very fundamentals and bit by bit gets pace as the story unfurls. Every idea is first briefly characterized in the bigger setting of things, trailed by an itemized clarification of their application.
•    Every idea is clarified with the assistance of a venture that takes care of a certifiable issue and includes hands-on work, giving you a profound understanding into the universe of AI. It is likewise a blend of six free ventures, each taking a one of a kind dataset, an alternate issue articulation, and an alternate arrangement.

 Course Outlines:

Chapter 1. The Machine Learning Landscape
Chapter 2. End-to-End Machine Learning Project
Chapter 3. Classification
Chapter 4. Training Models
Chapter 5. Support Vector Machines
Chapter 6. Decision Trees
Chapter 7. Ensemble Learning and Random Forests
Chapter 8. Dimensionality Reduction
Chapter 9. Up and Running with TensorFlow
Chapter 10. Introduction to Artificial NeuralNetworks
Chapter 11. Training Deep Neural Nets
Chapter 12. Distributing TensorFlow Across Devices and Servers
Chapter 13. Convolutional Neural Networks
Chapter 14. Recurrent Neural Networks
Chapter 15. Autoencoders
Chapter 16. Reinforcement Learning