Informit – Calculus for Machine Learning LiveLessons (Video Training) 2021-1

Description

Calculus for Machine Learning LiveLessons (Video Training) is an algebra training course for machine learning. These topics are necessary because derivative computations using optimization-based derivatives often include machine learning models (including those used in deep learning, such as backpropagation and stochastic gradient descent). As you learn this theory, you will gain a working understanding of how to use algebra to calculate limit and derivative functions.

What you will learn in the Calculus for Machine Learning LiveLessons (video training):

Develop an understanding of how machine learning algorithms work, including those used in deep learning.
Compute derivatives of functions using AutoDiff in popular libraries TensorFlow 2 and PyTorch
Ability to understand partial information (relative derivatives), multivariate algebra widely used in machine learning, and other topics in the machine learning subset including information theory and optimization algorithms.
Use integrals to determine the area under a curve, such as calculating the area under an ROC curve to assess model performance

Course specifications

Publisher: Informit
Instructors: Jon Krohn
French language
Average level
Course: 58
Duration: 6 hours and 14 minutes

Course topics:

Lesson 1: Numeracy Orientation

Lesson 2: Limits

Lesson 3: Differentiation

Lesson 4: Advanced Differentiation Rules

Lesson 5: Automatic differentiation

Lesson 6: Partial Derivatives

Lesson 7: Gradients

Lesson 8: Integrals

Course prerequisites:

Math: Knowledge of mathematics in high school will make it easier to follow the class. If you are comfortable with quantitative information, such as understanding graphs and rearranging simple equations, you should be well prepared to take all the math.

Programming: All code demonstrations are in Python, so experience with this or another object-oriented programming language would be helpful to follow the hands-on examples.