Mathematics for AI & Engineering — Skills Plan
Planned skill map for Mathematics for AI & Engineering. The curriculum will be developed and released in stages.
Practice the linear algebra, calculus, probability, statistics, optimization, and numerical reasoning used to understand data and machine-learning methods.
Potential roles: AI/ML Learner · Data Scientist · Software Engineer
Before you start
- Arithmetic and algebra
- Functions, graphs, and notation
What you’ll build
- Implement vector operations
- Explore optimization behavior
- Analyze uncertainty in a small dataset
Prerequisites
PLANNED- Arithmetic and algebra
Build the Arithmetic and algebra knowledge needed to follow the Mathematics for AI & Engineering foundations.
- Functions, graphs, and notation
Build the Functions, graphs, and notation knowledge needed to follow the Mathematics for AI & Engineering foundations.
Foundations
PLANNED- Vectors, matrices, and tensors
Explain how Vectors, matrices, and tensors works and where it fits in the Mathematics for AI & Engineering learning path.
- Linear transformations
Explain how Linear transformations works and where it fits in the Mathematics for AI & Engineering learning path.
- Derivatives and gradients
Explain how Derivatives and gradients works and where it fits in the Mathematics for AI & Engineering learning path.
- Probability and distributions
Explain how Probability and distributions works and where it fits in the Mathematics for AI & Engineering learning path.
Core Skills
PLANNED- Matrix multiplication and decompositions
Use Matrix multiplication and decompositions to implement a working capability and verify its behavior in Mathematics for AI & Engineering.
- Optimization and gradient descent
Use Optimization and gradient descent to implement a working capability and verify its behavior in Mathematics for AI & Engineering.
- Bayes theorem and conditional probability
Use Bayes theorem and conditional probability to implement a working capability and verify its behavior in Mathematics for AI & Engineering.
- Statistics and sampling
Use Statistics and sampling to implement a working capability and verify its behavior in Mathematics for AI & Engineering.
- Entropy and information theory
Use Entropy and information theory to implement a working capability and verify its behavior in Mathematics for AI & Engineering.
Advanced / Production
PLANNED- Numerical stability
Evaluate Numerical stability trade-offs against the performance, reliability, and safety needs of Mathematics for AI & Engineering systems.
- Convexity and optimization trade-offs
Evaluate Convexity and optimization trade-offs trade-offs against the performance, reliability, and safety needs of Mathematics for AI & Engineering systems.
- Statistical testing and uncertainty
Evaluate Statistical testing and uncertainty trade-offs against the performance, reliability, and safety needs of Mathematics for AI & Engineering systems.
- Mathematical reasoning for model evaluation
Evaluate Mathematical reasoning for model evaluation trade-offs against the performance, reliability, and safety needs of Mathematics for AI & Engineering systems.
Real-World Projects
PLANNED- Implement vector operations
Deliver a working outcome with Implement vector operations, then test it against the project requirements.
- Explore optimization behavior
Deliver a working outcome with Explore optimization behavior, then test it against the project requirements.
- Analyze uncertainty in a small dataset
Deliver a working outcome with Analyze uncertainty in a small dataset, then test it against the project requirements.
Career / Interview Preparation
PLANNED- Linear algebra intuition
Explain your approach to Linear algebra intuition, defend key trade-offs, and discuss what you learned.
- Probability and statistics questions
Explain your approach to Probability and statistics questions, defend key trade-offs, and discuss what you learned.
- Explain model mathematics clearly
Explain your approach to Explain model mathematics clearly, defend key trade-offs, and discuss what you learned.
Discussion
0Have a better approach? Found something outdated? Share it — your knowledge helps everyone learning here.