Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 35 hours
Course Outline
Overview of AI in Python
- Core concepts and the scope of AI
- Python libraries utilised for AI development
- AI project architecture and workflow
Data Preparation for AI
- Data cleansing, transformation, and feature engineering
- Addressing missing and imbalanced data
- Feature scaling and encoding strategies
Supervised Learning Techniques
- Regression and classification algorithms
- Ensemble methods: Random Forest, Gradient Boosting
- Hyperparameter tuning and cross-validation
Unsupervised Learning Techniques
- Clustering methods: K-Means, DBSCAN, hierarchical clustering
- Dimensionality reduction: PCA, t-SNE
- Practical use cases for unsupervised learning
Neural Networks and Deep Learning
- Introduction to TensorFlow and Keras
- Constructing and training feedforward neural networks
- Optimising neural network performance
Reinforcement Learning (Introduction)
- Fundamental concepts of agents, environments, and rewards
- Implementing basic reinforcement learning algorithms
- Applications of reinforcement learning
Deploying AI Models
- Saving and retrieving trained models
- Integrating models into applications via APIs
- Monitoring and maintaining AI systems in production
Summary and Next Steps
Requirements
- A strong grasp of fundamental Python programming principles.
- Practical experience with data analysis libraries such as NumPy and pandas.
- Foundational knowledge of machine learning concepts and algorithms.
Target Audience
- Software developers looking to broaden their AI development capabilities.
- Data analysts interested in applying AI techniques to complex datasets.
- R&D professionals creating AI-powered applications.
Testimonials (2)
The trainer was very available to answer all te kind of question I did
Caterina - Stamtech
Course - Developing APIs with Python and FastAPI
Trainer develops training based on participant's pace
