Choose Artificial Intelligence & Machine Learning Course in Malaysia

Module 1: Foundations of Artificial Intelligence

​

Introduction to AI: A look at AI applications and their effects

Python for Data Analysis:

• Writing Python Code for Data Analysis and Manipulation

• Utilizing Python libraries (like matplotlib and seaborn) for data visualization

• Statistical Analysis with Excel: Applying statistical techniques and analyses

Exploratory Data Analysis (EDA):

• Performing EDA in Python to discover business opportunities

• Visualizing data to reveal insights

​

Module 2: Supervised Learning Techniques

Introduction to Supervised Learning: Fundamentals and applications

Regression Techniques:

• Linear Regression

• Multiple Regression

• Logistic Regression

Classification Techniques:

• k-Nearest Neighbors (k-NN)

• Naive Bayes

Decision Trees:

• Creating and interpreting decision trees

Case Study:

• Hands-On: Build a model to classify credit risks for loan approval using classification techniques

​

Module 3: Unsupervised Learning Methods

Introduction to Unsupervised Learning: Concepts and applications

Clustering Techniques:

• K-Means Clustering

• Hierarchical Clustering

• High-dimensional Clustering

Evaluation Methods:

• Elbow Method

• Silhouette Method

Case Study:

• Hands-On: Employ K-Means clustering to segment social media posts for targeted marketing campaigns

 

Module 4: Ensemble Learning Techniques

Understanding Ensemble Methods:

• Benefits of bootstrap sampling and bagging

• Boosting techniques to enhance model performance

Key Ensemble Techniques:

• Bagging

• Boosting

• Random Forest

Case Study:

• Hands-On: Use AdaBoost, Gradient Boosting Machines (GBM), and Random Forest to predict loan statuses and compare the performance of ensemble methods with individual models

 

Module 5: Reinforcement Learning

Introduction to Reinforcement Learning (RL): Basics and applications

Markov Decision Processes (MDP): Modeling and solving optimization challenges

Value-Based Methods:

 

Module 6: Deep Learning

Introduction to Neural Networks:

• Fundamentals of Neural Networks and their algorithms

Deep Neural Networks:

• Architecture and Training Techniques for Deep Neural Networks

TensorFlow and Keras:

• Leveraging TensorFlow and Keras for deep learning projects

Activation Functions:

• Exploring Sigmoid, Hyperbolic Tangent, Rectified Linear Units (ReLU), and Leaky ReLU

Case Study:

• Hands-On: Examine customer default payment data to assess risk using deep learning methods

 

Module 7: Natural Language Processing (NLP)

Introduction to NLP: Fundamentals and uses in text analysis

Text Processing with Python:

• Extracting features from unstructured text

NLP Techniques:

• Text Summarization

• Syntax and Parsing

• Semantics and Generation

Case Study:

• Hands-On: Apply NLP to evaluate social media data for stock market forecasting

 

Module 8: Computer Vision

Introduction to Computer Vision: Key concepts and applications

Convolutional Neural Networks (CNNs):

• Overview and architecture of CNNs

Image Data Preprocessing: Methods and tools

Object and Face Recognition:

• Utilizing OpenCV for detecting objects and faces

Case Study:

• Hands-On: Execute face detection using Haar cascades and various computer vision techniques