Samsung Innovation Campus: Artificial intelligence
Course Objectives
• Understand the foundational math behind data science and machine learning: linear algebra, probability and
statistics.
• Be able to do data preprocessing with the Python libraries (NumPy and Pandas) for the execution of optimal
machine learning models and data visualization.
• Explore supervised and unsupervised learning and be able to apply the most suitable machine learning
algorithm.
• Learn to process textual data to derive high quality information from text and apply new insights to real-world
business (NLP)
• Build and train deep neural networks, use the deep learning libraries such as TensorFlow and Keras to gain
proficiency, as well as handle various deep learning techniques.
Course Breakdown
Lecture (215hrs.) + Capstone Project (50hrs.)
Lecture covers most subject areas in general concepts of each technology.
Focuses on building fundamental capabilities of AI modeling on a concrete foundation of mathematics,
including linear algebra, probability and statistics.
Introduces A to Z in Machine Learning tools, from NumPy to Keras, and techniques including CNN and
practice with hands-on exercises.
Offers 50 hours of real-world problem-solving experience as a capstone project, handling open-source
data with participants' own AI
Course Content Duration
Week 1: Math for Data Science & Probability and Statistics 53H
Unit 1: Introduction 2H
Unit 2: Basic Math for Data Science 5H
Unit 3: Understanding Data Science: Vector 6H
Unit 4: Understanding Data Science: Matrix 6H
Unit 5: Understanding Deep Learning: Derivatives 6H
Unit 6: Understanding of Probability 6H
Unit 7: Understanding of Statistics I 6H
Unit 8: Understanding of Statistics II 6H
Unit 9: Statistical Hypothesis Testing 6H
Quiz 4H
Week 2: Introduction to Artificial Intelligence & Exploratory Data Analysis: 33H
NumPy Arrays for Optimized Numerical Computation & Pandas
Unit 1: The Concept of Artificial Intelligence 1H
Unit 2: Applications of Artificial Intelligence 1H
Unit 3: Techniques in Artificial Intelligence 1H
Unit 4: Artificial Intelligence: Trends and Markets 1H
Unit 5: Course Roadmap 1H
Unit 6: NumPy Array Data Structure for Optimal Computational Performance 6H
Unit 7: Optimal Data Exploration Through Pandas 7H
Unit 8: Pandas Data Preprocessing for Optimal Model Execution 7H
Unit 9: Data Visualization for Various Data Scales 7H
Quiz 4H
Week 3: Machine Learning 1 – Supervised Learning 29H
Unit 1: Machine Learning Based Data Analysis 3H
Unit 2: Application of Supervised Learning Model for Numerical Prediction 3H
Unit 3: Application of Supervised Learning Model for Classification 3H
Unit 4: Decision Tree 3H
Unit 5: Naïve Bayes Algorithm 3H
Unit 6: KNN Algorithm 4H
Unit 7: SVM Algorithm 4H
Unit 8: Ensemble Algorithm 4H
Quiz 2H
Week 4: Machine Learning 2 – Unsupervised Learning 29H
Unit 1: Unsupervised Machine Learning Algorithm 6H
Unit 2: Hierarchical Clustering 7H
Unit 3: Non-Hierarchical Clustering 7H
Unit 4: Linear Factor Model for Dimensionality Reduction 7H
Quiz 2H
Week 5: Neural Network and Deep Learning & Various Deep Learning Topics 46H
Unit 1: Basics of Neural Network 7H
Unit 2: Basics of TensorFlow 7H
Unit 3: Deep Learning Methods using TensorFlow and Keras 7H
Unit 4: CNN Model 7H
Unit 5: RNN for Sequential Data Modeling 7H
Unit 6: Generative Adversarial Neural Network to Create Non-Existent Images 7H
Quiz 4H
Week 6: Natural Language Processing and Language Models for Text Mining 25H
Unit 1: Text Mining 5H
Unit 2: Text Preprocessing 6H
Unit 3: Language Model 6H
Unit 4: Natural Language Processing with Keras 6H
Quiz 2H
Total Class Hours 215H
Course Assessment:
The scoring assessments of the students will follow the below criteria:
Criteria Weight
Quiz 40 %
- Quiz will be placed at the end of each week
- Approximately 5 ~ 20 questions per quiz
Capstone Project 60 %
- Project is measured based on the quality of final product, presentation
and teamwork
Participation +α
- Participation is measured by the instructor throughout the course
Total 100%
Certification:
The students will be eligible for a certification when both qualifications below are met.
Qualification Cut-off Rate
1. Attendance higher than 90 %
2. Total grade for assessment higher than 50 %
▶ Certified when both qualifications are met -
