Artificial Intelligence (AI) Fundamentals Training Course

Module 1: Introduction to AI and its History

• Defining Artificial Intelligence, Machine Learning, and Deep Learning
• Key historical milestones and the evolution of AI paradigms
• Different types of AI: Weak, Strong, and Artificial Superintelligence (ASI)
• The role of Data Science and its relationship with AI
• Understanding the current state and future predictions of the AI landscape
• Practical session: Exploring and comparing various real-world applications of AI across different industries

Module 2: Core Concepts of Machine Learning (ML)

• Overview of the Machine Learning workflow (data, model, evaluation)
• Differentiating between Supervised, Unsupervised, and Reinforcement Learning
• The concept of bias-variance trade-off in model building
• Understanding generalization and the risk of overfitting/underfitting
• Introduction to fundamental mathematical concepts (linear algebra, calculus) for ML
• Practical session: Implementing a simple gradient descent visualization to illustrate model training iteration

Module 3: Data Preprocessing and Feature Engineering

• Data cleaning techniques: handling missing values and inconsistent data types
• Data transformation: normalization, standardization, and scaling
• Feature selection and extraction methods (e.g., PCA)
• Handling categorical data using encoding methods (one-hot, label encoding)
• Managing imbalanced datasets (e.g., oversampling, undersampling)
• Practical session: Performing data cleaning and feature scaling on a standard dataset (e.g., Iris or Boston Housing) using Pandas and Scikit-learn

Module 4: Supervised Learning: Regression

• Definition of Regression problems and use cases
• Detailed explanation of Linear Regression and its assumptions
• Introduction to more complex models: Polynomial and Ridge/Lasso Regression
• Understanding cost functions (e.g., Mean Squared Error - MSE)
• Assessing model fit and interpreting regression coefficients
• Practical session: Building and training a Multiple Linear Regression model to predict a continuous variable

Module 5: Supervised Learning: Classification

• Definition of Classification problems and common applications
• Logistic Regression as a core binary classification algorithm
• Decision Trees: structure, splitting criteria, and visualization
• Ensemble methods introduction: Random Forests and Gradient Boosting
• Handling multi-class classification strategies (One-vs-Rest)
• Practical session: Implementing a Decision Tree Classifier and visualizing the resulting decision boundaries

Module 6: Unsupervised Learning and Clustering

• Definition of Unsupervised Learning and its exploratory nature
• K-Means Clustering algorithm: working principle and optimization
• Hierarchical Clustering and dendrogram interpretation
• Dimensionality Reduction using Principal Component Analysis (PCA)
• Use cases for clustering (customer segmentation, anomaly detection)
• Practical session: Applying K-Means clustering to segment a simple dataset and visually interpreting the results

Module 7: Evaluation Metrics and Model Selection

• Metrics for Classification: Accuracy, Precision, Recall, F1-Score
• Understanding and interpreting the Confusion Matrix
• Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC)
• Cross-validation techniques (k-fold) for robust model testing
• Metrics for Regression: Root Mean Squared Error (RMSE) and $R^2$ score
• Practical session: Calculating and interpreting the Confusion Matrix and F1-Score for a classification model built earlier

Module 8: Deep Learning Fundamentals and Neural Networks

• Introduction to the structure of an Artificial Neural Network (ANN)
• Perceptrons, activation functions (ReLU, Sigmoid), and layers
• Backpropagation algorithm for weight adjustment
• Understanding optimizers (e.g., Adam, SGD) and learning rate
• Introduction to frameworks: TensorFlow and PyTorch
• Practical session: Building a simple feed-forward neural network from scratch using a high-level API like Keras

Module 9: Introduction to Computer Vision (CV)

• Overview of Computer Vision tasks (classification, detection, segmentation)
• Understanding image data structure and representation
• Convolutional Neural Networks (CNNs): convolutions, pooling, and filters
• Transfer Learning and using pre-trained models (e.g., VGG, ResNet)
• Applications of CV in industry (healthcare, autonomous vehicles)
• Practical session: Loading a pre-trained CNN model and using it for image classification on a new image dataset

Module 10: Introduction to Natural Language Processing (NLP)

• Fundamentals of text data: tokens, vocabulary, and corpus
• Text preprocessing techniques: stemming, lemmatization, and stop-word removal
• Representing text: Bag-of-Words and Term Frequency-Inverse Document Frequency (TF-IDF)
• Simple NLP tasks: Sentiment Analysis and Text Classification
• Introduction to Recurrent Neural Networks (RNNs) for sequence data
• Practical session: Implementing a basic sentiment analysis model using TF-IDF and a traditional ML classifier

Module 11: Reinforcement Learning (RL) Basics

• Core components of RL: Agent, Environment, State, Action, Reward
• The concept of Markov Decision Processes (MDPs)
• Q-Learning and Value Iteration algorithms
• Exploration vs. Exploitation trade-off
• Simple use cases (robotics, game playing)
• Practical session: Simulating a simple grid-world environment and applying a basic Q-Learning algorithm to find an optimal path

Module 12: Ethical AI and Bias Mitigation

• The societal impact of AI and the importance of fairness
• Identifying sources of bias in data, algorithms, and human interpretation
• Techniques for measuring and mitigating algorithmic bias
• Transparency, accountability, and safety in AI systems
• Regulatory frameworks and principles for responsible AI development
• Practical session: Analyzing a biased dataset and discussing strategies to debias the data before model training

Module 13: Explainable AI (XAI) and Interpretability

• The "black box" problem in complex models
• Differentiating between model interpretability and explainability
• Global interpretability methods (feature importance, partial dependence plots)
• Local interpretability methods (LIME, SHAP)
• Communicating model rationale to non-technical stakeholders
• Practical session: Using SHAP to explain the predictions of a complex classification model for a single instance

Module 14: AI in the Cloud and MLOps Concepts

• Overview of major cloud AI platforms (AWS SageMaker, Azure ML, Google AI Platform)
• Defining MLOps: practices for deploying and managing ML models
• Version control for models, code, and data
• Continuous Integration and Continuous Delivery (CI/CD) for ML pipelines
• Monitoring model performance and drift in production
• Practical session: Creating a simple ML pipeline skeleton that separates training, evaluation, and deployment steps

Module 15: Tools and Libraries for AI Development

• Deep dive into the NumPy library for numerical operations
• Mastering the Pandas library for data manipulation and analysis
• Comprehensive review of Scikit-learn for classical ML
• Introduction to visualization libraries (Matplotlib, Seaborn)
• Leveraging GPUs and hardware acceleration for training
• Practical session: Implementing advanced data aggregation and grouping functions in Pandas for feature creation

Module 16: Deployment and Productionization of Models

• Model serving architectures (REST APIs, gRPC)
• Containerization of models using Docker
• Introduction to orchestration tools (e.g., Kubernetes) for scaling
• Designing a low-latency model inference service
• Edge AI deployment considerations (device constraints, optimization)
• Practical session: Creating a simple Python Flask API endpoint to load and serve predictions from a trained model

Module 17: Specialized AI Architectures (e.g., CNNs, RNNs)

• Recurrent Neural Networks (RNNs) for sequential data
• Long Short-Term Memory (LSTM) networks for capturing long-term dependencies
• Generative Adversarial Networks (GANs) for content generation
• Introduction to Transformer architecture and Attention mechanisms
• Case studies illustrating the power of specialized architectures in various domains
• Practical session: Implementing a basic RNN or LSTM for sequence prediction on a time-series dataset

Module 18: AI Case Studies and Future Trends

• In-depth analysis of AI in healthcare (diagnosis, drug discovery)
• Case study of AI in finance (fraud detection, algorithmic trading)
• Review of the latest advancements in Large Language Models (LLMs)
• Exploring Quantum Computing's potential impact on AI
• Discussion on the long-term future of AGI (Artificial General Intelligence)
• Practical session: Critically analyzing the ethical, technical, and business feasibility of a new Generative AI startup idea

Requirements:

·       Participants should be reasonably proficient in English.

·       Applicants must live up to Armstrong Global Institute admission criteria.

Terms and Conditions

1. Discounts: Organizations sponsoring Four Participants will have the 5th attend Free

2. What is catered for by the Course Fees: Fees cater for all requirements for the training – Learning materials, Lunches, Teas, Snacks and Certification. All participants will additionally cater for their travel and accommodation expenses, visa application, insurance, and other personal expenses.

3. Certificate Awarded: Participants are awarded Certificates of Participation at the end of the training.

4. The program content shown here is for guidance purposes only. Our continuous course improvement process may lead to changes in topics and course structure.

5. Approval of Course: Our Programs are NITA Approved. Participating organizations can therefore claim reimbursement on fees paid in accordance with NITA Rules.

Booking for Training

Simply send an email to the Training Officer on training@armstrongglobalinstitute.com and we will send you a registration form. We advise you to book early to avoid missing a seat to this training.

Or call us on +254720272325 / +254725012095 / +254724452588

Payment Options

We provide 3 payment options, choose one for your convenience, and kindly make payments at least 5 days before the Training start date to reserve your seat:

1. Groups of 5 People and Above – Cheque Payments to: Armstrong Global Training & Development Center Limited should be paid in advance, 5 days to the training.

2. Invoice: We can send a bill directly to you or your company.

3. Deposit directly into Bank Account (Account details provided upon request)

Cancellation Policy

1. Payment for all courses includes a registration fee, which is non-refundable, and equals 15% of the total sum of the course fee.

2. Participants may cancel attendance 14 days or more prior to the training commencement date.

3. No refunds will be made 14 days or less before the training commencement date. However, participants who are unable to attend may opt to attend a similar training course at a later date or send a substitute participant provided the participation criteria have been met.

Tailor Made Courses

This training course can also be customized for your institution upon request for a minimum of 5 participants. You can have it conducted at our Training Centre or at a convenient location. For further inquiries, please contact us on Tel: +254720272325 / +254725012095 / +254724452588 or Email training@armstrongglobalinstitute.com

Accommodation and Airport Transfer

Accommodation and Airport Transfer is arranged upon request and at extra cost. For reservations contact the Training Officer on Email: training@armstrongglobalinstitute.com or on Tel: +254720272325 / +254725012095 / +254724452588