About This Course
Artificial Intelligence (AI) enables systems to learn from data and improve their performance over time without being explicitly programmed. This course will equip participants with the skills needed to harness the power of AI to solve complex problems.
Throughout this course, fundamental principles of AI will be explored, starting with the basics and progressively advancing to more sophisticated topics. Essential algorithms and methodologies will be covered, including both supervised and unsupervised learning techniques. By the end of this course, participants will have a solid foundation in AI and be proficient in using Python, one of the most popular programming languages for AI to implement these techniques.
The course will emphasise practical, hands-on learning, providing participants with numerous opportunities to apply the concepts learnt. Powerful Python libraries such as NumPy, Pandas, and Matplotlib for data manipulation and visualisation will be introduced, as well as scikit-learn and TensorFlow for building and evaluating machine learning models. These tools are widely used in the industry and mastering them will significantly enhance the ability to tackle machine learning projects.
After the traditional AI algorithms have been covered, this course will proceed to neural networks and regression. Participants will learn how to implement simple neural networks for classification and regression tasks. This will broaden participant’s machine learning expertise and enable a wide range of challenges to be addressed. Participants will also be introduced to basic image processing application development in Python and how to apply AI in image processing applications in Python.
Furthermore, this course will cover crucial aspects of model evaluation and improvement. Participants will learn how to assess the performance of models using various metrics. By the end of the course, participants will have the knowledge and skills to confidently apply machine learning techniques to their projects.
Learning Objectives
By the end of the program, participants will be able to:
- Understand the core principles and concepts of machine learning
- Differentiate between supervised and unsupervised learning techniques
- Use Python libraries (NumPy, Pandas, Matplotlib) for data manipulation and visualisation
- Implement machine learning algorithms with scikit-learn and TensorFlow
- Develop and train models for regression and classification tasks
- Apply model evaluation techniques such as Train/Test split, Cross-validation, and various performance metrics
- Build and train simple neural networks
- Apply AI algorithms in image processing applications
Prerequisites
Participants are assumed to have some knowledge about Python programming. Participants are encouraged to take the “Python Fundamentals” course prior to taking this course.
Target Audience
This course is specially designed for anyone who needs to know or is interested in learning or refreshing their knowledge on machine learning and how to use it to develop AI based Python applications.
Training Outline
- Introduction to Artificial Intelligence (AI)
- Python for Artificial Intelligence
- Exploratory Data Analysis (EDA)
- Supervised Learning
- Unsupervised Learning
- Model Evaluation and Improvement
- Introduction to Neural Networks
- Image Processing with AI Using Python