×

Status message

There is no scheduled class for this course. If you are interested in purchasing this course please click on the "Express Interest" button, fill in your contact information and submit a request for the course.
  • Course Length:
  • 0.5 Day Instructor Led

Artificial Intelligence (AI) is revolutionizing all aspects of the computer industry. Designing and using AI models required an understanding of data science principles. This course provides an overview of the key data science principles needed for AI from a telecom perspective. Data science is explored from a definition and role perspective. The course then moves to key AI use cases and the data science techniques used in Machine Learning and Deep learning like linear algebra and deriviatives. The course concludes with a discussion on how neurons within an AI model work and the different activation functions.

A high-level technical overview to personnel involved in product management, marketing, planning, design, engineering, and operating wireless (4G, 5G) and wireline access networks

After completing this course, the student will be able to:
• Define Data Science
• List the key Linear Algebra techniques used in AI
• Describe the math funcitons used in AI
• List the actions performed by a neuron

1. Data Science and AI
1.1. Role of Data Science
1.2. Data Science vs. AI Model Building
1.3. Data Science and Input Data

2. Basics of Linear algebra
2.1. Vector Operations
2.1.1. Orthogonal vectors
2.1.2. Vector dot products
2.2. Matrix Operations
2.3. Intuitive description of n-dimensional vector space
2.4. Eigendecomposition

3. Math concepts
3.1. Composite Functions
3.2. Derivatives
3.2.1. Partial derivative
3.2.2. Directional derivative
3.2.3. Chain rule
3.2.4. Gradient
3.3. Rules for minimization (maximization) of a function

4. Actions performed by a Neuron
4.1. Types of Neurons
4.2. Affine transformation
4.3. Activation Functions
4.3.1. Rectified Linear Unit (ReLU)
4.3.2. Sigmoid
4.3.3. SoftPLus
4.3.4. Tanh