Session 1 – 04:00:00 – A Short Course in Python Basics I.
This session provides participants with the foundational Python skills required for machine learning tasks. This session is designed for beginners or those needing a refresher in Python programming.
Python Essentials for Machine Learning: This section focuses on Python syntax, variables, data types, conditionals (`if`, `else`, `elif`), loops (`for`, `while`), and writing reusable code using functions.
Session 2 – 04:00:00 – A Short Course in Python Basics II.
This session provides participants with the foundational Python skills required for machine learning tasks. This session is designed for beginners or those needing a refresher in Python programming.
Data Structures and File Handling in Python: Focuses on lists, dictionaries, tuples, sets, and reading/writing files (e.g., CSVs) for data manipulation.
Session 3 – 04:00:00 – Fundamentals of Machine Learning.
This session focuses on the theoretical foundations of machine learning, detailing the application of learning algorithms in preparation for the practical examples in Python.
Introduction to Machine Learning: This section covers the definition of Machine learning, types of Learning (Supervised, Unsupervised, Reinforcement, Semi-Supervised), applications of Machine Learning and an overview of Python libraries for ML (NumPy, scikit-learn)
Session 4 – 04:00:00 – Fundamentals of Machine Learning.
This session focuses on the theoretical foundations of machine learning, detailing the application of learning algorithms in preparation for the practical examples in Python.
Fundamental learning algorithms: This section explores the available learning algorithms and focuses on their applications. We will also discuss the application of different algorithms with practical examples in Ecology.
Session 5 – 04:00:00 – Statistical Learning Theory.
This session focuses on the theoretical foundations of Statistical Learning Theory (SLT) and illustrates their practical implications.
Important Definitions on SLT: In this section, we will explore the concept of Statistical Learning Theory and its implications for classification tasks in supervised learning settings, highlighting its importance for machine learning practitioners.
Session 6 – 04:00:00 – Statistical Learning Theory.
This session focuses on the theoretical foundations of Statistical Learning Theory (SLT) and illustrates their practical implications.
Practical implications of the SLT: This section provides a detailed explanation of the practical consequences of statistical learning theory based on Vapniks’ findings and using Support Vector Machines as a helpful example in Python
Session 7 – 04:00:00 – Classification boundaries and the power of Deep Neural networks.
This session introduces participants to the core libraries used in machine learning tasks. scikit-learn is used to implement machine learning algorithms, and TensorFlow is used to build deep learning models.
Classification with various learning algorithms: Offers a step-by-step guide to building learning algorithms using scikit-learn.
Session 8 – 04:00:00 – Classification boundaries and the power of Deep Neural networks.
This session introduces participants to the core libraries used in machine learning tasks. scikit-learn is used to implement machine learning algorithms, and TensorFlow is used to build deep learning models.
Building Deep Learning Models with TensorFlow/Keras: Offers a step-by-step guide to building CNN models for image classification using TensorFlow/Keras.
Session 9 – 04:00:00 – The Machine Learning Pipeline.
Participants will learn about the end-to-end workflow of a typical machine learning project using ecological datasets as an illustration.
Preprocessing data and selecting algorithms: This section focuses on preprocessing techniques in OpenCV before feeding images into TensorFlow models for training. An entomological example illustrating the Machine Learning Pipeline will be used.
Session 10 – 04:00:00 – The Machine Learning Pipeline.
Participants will learn about the end-to-end workflow of a typical machine learning project using ecological datasets as an illustration.
The Complete Machine Learning Pipeline: From Classification to Evaluating Learning: Covers the end-to-end machine learning workflow, including using the data preprocessed data and creating scikit-learn pipelines to automate critical aspects of the workflow.
5.0
