Get in Touch
 Duration 35 hours

Course Outline

Introduction to AI within Python

  • Fundamental concepts and the reach of AI
  • Essential Python libraries for AI creation
  • Structuring AI projects and defining workflows

Preparing Data for AI

  • Data cleansing, manipulation, and feature creation
  • Managing missing values and data imbalance
  • Scaling features and applying encoding

Supervised Learning Methods

  • Algorithms for regression and classification
  • Ensemble strategies: Random Forest and Gradient Boosting
  • Adjusting hyperparameters and using cross-validation

Unsupervised Learning Methods

  • Clustering techniques: K-Means, DBSCAN, and hierarchical approaches
  • Reducing dimensions: PCA and t-SNE
  • Practical applications of unsupervised learning

Deep Learning and Neural Networks

  • Getting started with TensorFlow and Keras
  • Constructing and training feedforward neural networks
  • Enhancing neural network performance

Reinforcement Learning (Fundamentals)

  • Key concepts of agents, environments, and reward systems
  • Applying basic reinforcement learning algorithms
  • Use cases for reinforcement learning

Deploying AI Models

  • Persisting and retrieving trained models
  • Connecting models to applications through APIs
  • Overseeing and sustaining AI systems in live environments

Conclusion and Future Directions

Requirements

  • A strong grasp of Python programming basics
  • Proficiency with data analysis tools like NumPy and pandas
  • Familiarity with fundamental machine learning concepts and algorithms

Target Audience

  • Software engineers seeking to broaden their AI development capabilities
  • Data analysts aiming to leverage AI methods on complex data sets
  • R&D specialists developing AI-enhanced applications

Number of participants


Price per participant

Testimonials (2)

Upcoming Courses

Related Categories