# Machine Learning and AI?

Machine Learning and Artificial Intelligence refer to the study of computational systems that are able to automatically **learn** from data and perform complex tasks usually attributed to human intelligence

## Suggested Courses

In addition to completing the course requirements for your degree, you can opt for taking courses that will give you in-depth knowledge and experience in Machine Learning/Artificial Intelligence (ML/AI). Below you can find a *list of suggested courses* to take if you want to study the *fundamentals* of Machine Learning and Deep Learning.

Code | Course | Description |
---|---|---|

MTH 215 | Introduction to Linear Algebra | Detailed study of finite dimensional vector spaces, linear transformations, matrices, determinants and systems of linear equations. (Lec. 3/Online) Pre: C- or better in MTH 131, 141, 180, or equivalent. |

MTH 243 | Calculus for Functions of Several Variables | Topics include coordinates for space, vector geometry, partial derivatives, directional derivatives, extrema, Lagrange multipliers, and multiple integrals. (Lec. 3/Online) Pre: C- or better in MTH 142. |

MTH 451 | Introduction to Probability and Statistics | Theoretical basis and fundamental tools of probability and statistics. Probability spaces, properties of probability, distributions, expectations, some common distributions and elementary limit theorems. (Lec. 3) Pre: MTH 243 or equivalent. |

STA 308 | Introductory Statistics | Descriptive statistics, presentation of data, averages, measures of variation. Elementary probability, binomial and normal distributions. Sampling distributions. Statistical inference, estimation, confidence intervals, testing hypotheses, linear regression, and correlation. (Lec. 3, Rec. 1) Pre: MTH 107 or 110 or 111 or 131 or 141 or BAI (BUS) 111 or permission of instructor. Not open to students with credit in STA 307 or 409. |

CSC 310 | Programming for Data Science | Cross-listed as (CSC), DSP 310. Data driven programming; data sets, file formats and meta-data; descriptive statistics, data visualization, and foundations of predictive data modeling; accessing web data and data bases; distributed data management. (Lec. 3, Lab. 2) Pre: CSC201 or CSC211 or equivalent, or permission of instructor. Computer Science majors must take as CSC 310; Data Science majors must take as DSP 310. |

CSC 461 | Machine Learning | Cross-listed as (CSC), DSP 461. Broad introduction to fundamental concepts in machine learning. Survey of traditional and newly developed learning algorithms, as well as, their application to real-world problems. (Lec. 3, Lab. 1) Pre: CSC 310 and MTH 215. Computer Science majors must take as CSC 461. Data Science majors must take as DSP 461. |

CSC 561 | Neural Networks and Deep Learning | Survey of traditional and newly developed deep learning methods, including multilayer perceptrons, convolutional networks, recurrent networks, auto-encoders, generative adversarial networks, graph neural networks, deep reinforcement learning, as well as, their application to real-world problems. Pre: CSC 461 or permission by instructor. |

If you complete most of these courses, a minor in Data Science may be available to you.

## Prerequisite Network

The graph belows shows the same courses listed above and their suggested prerequisites.

```
graph TD
classDef mth stroke:black;
classDef csc fill:lightyellow, stroke:black;
classDef sta fill:aliceblue, stroke:black;
A[CSC 461]:::csc --> B[CSC 561]:::csc
C[CSC 310]:::csc --> A
D[MTH 215]:::mth --> A
E[MTH 243]:::mth --> F[MTH 451]:::mth
G[MTH 141]:::mth --> H[STA 308]:::sta
G --> I[MTH 142]:::mth
I --> E
G --> D
J[CSC 211]:::csc --> C
```