Linear Algebra for Machine Learning

Home / Courses And Programs / Linear Algebra for Machine Learning

Linear Algebra for Machine Learning

Linear algebra provides a mathematical framework for organizing information and then using that information to solve problems, especially physics, math, engineering, or data analytics problems. Linear algebra is essential for understanding and creating machine learning algorithms, especially neural network and deep learning models.

In this course, you will learn the linear algebra skills necessary for machine learning and neural network modelling. You will begin by learning overview of basic matrices and vector algebra as applied to linear systems. Then you will learn advanced skills for finding the highest and lowest points of systems, quantifying the degree of learning, and optimizing the speed of learning in vector spaces and linear transformations. The hands-on lessons and assignments will equip you with the mathematical background required to build and train simple neural networks.

Key topics:

Fundamentals of matrix algebra: vectors, matrices, tensors
Multiplying matrices and vectors
Identity and inverse matrices
Linear dependence and span
Norms
Dimensions and hyperplanes
Conjugate gradients
Eigenvalues, Eigenvectors, Eigendecomposition
Principal Component Analysis
Basics of TensorFlow

Practical experience:

Hands-on lab assignments and projects using various open-source software programs

Course typically offered: Online in Fall, Winter, Spring, and Summer

Software: Students will use Octave, Caffe, and TensorFlow to complete hands-on assignments and projects. These tools are free and open-source.

Prerequisites: Strong understanding of college-level algebra and calculus required.

Next steps: Upon completion, consider taking courses in our Data Mining for Advanced Analytics program to continue learning.

Contact: For more information about this course, please contact unex-techdata@ucsd.edu.

COURSE NUMBER CSE-41287
CREDIT 3.00 unit(s)

9/25/2017 - 11/26/2017 | Online $650

SECTION ID:

126913
CLASS TYPE:

Online, Web-based instruction

INSTRUCTOR :

Aleksic, Bilyana

Bilyana Aleksic is senior staff hardware engineer with more than 20 years of experience in complex chip SOC development. She received her M.S. in Control Systems from Faculty of Electrical Engineering University of Belgrade, former Yugoslavia, and was honored student of Mathematical Gymnasium that has won many world Mathematical Olympiad Competitions. She spent 15 years in Canadian tech companies ATI Technologies where she worked on implementation of graphics CPU chips. After she moved to California she spend 7 years in mobile chips implementation and verification methodology development. During the past year she shifted her focus on Machine Learning especially for medical applications.

TEXTBOOKS:

No textbook required.

POLICIES:

No refunds after: 10/2/2017.
Note:

DATE:
LOCATION
9/25/2017-11/26/2017
ucsdextension.blackboard.com
You will have access to your course on the published start date.

There are no sections of this course currently scheduled. Please contact the Science & Technology department at 858-534-9353 or unexbio@ucsd.edu for information about when this course will be offered again.

Popular in Data Science

course