Skip to main content
Back to course
Log in
Get started
Someone wanted to learn this too, so Grasp built them a personal learning path.
Create your own
Speech Models Staff Engineering
·
Module 1
Applied Mathematics for Speech Machine Learning
1
Consistent Shape Notation for Scalars, Vectors, Matrices, and Tensors
Represent scalars, vectors, matrices, and tensors using consistent shape notation.
Represent scalars, vectors, matrices, and tensors using consistent shape notation.
2
Dot and Matrix Products: Computing and Checking Dimensions
Compute dot products and matrix products while checking dimensional compatibility.
Compute dot products and matrix products while checking dimensional compatibility.
3
Understanding Derivatives, Partial Derivatives, and Gradients
Interpret derivatives, partial derivatives, and gradients as measures of local change.
Interpret derivatives, partial derivatives, and gradients as measures of local change.
4
Calculating Gradients of Multivariable Functions
Calculate gradients of simple multivariable functions.
Calculate gradients of simple multivariable functions.
5
Applying the Chain Rule to Composite Functions
Apply the chain rule to a short composition of functions.
Apply the chain rule to a short composition of functions.
6
Computing and Interpreting Descriptive Statistics
Compute and interpret mean, variance, and covariance for a dataset.
Compute and interpret mean, variance, and covariance for a dataset.
7
Conditional Probability and Bayes’ Rule for Classification
Use conditional probability and Bayes’ rule in a simple classification calculation.
Use conditional probability and Bayes’ rule in a simple classification calculation.
8
Using Logarithms and Log Probabilities to Prevent Numerical Underflow
Apply logarithms and log probabilities to avoid numerical underflow.
Apply logarithms and log probabilities to avoid numerical underflow.
Next module isn't ready yet,
Back to course
Previous module
Next module