Skip to main content
grasp.study
Back to course
Log in
Get started
Someone wanted to learn this too, so Grasp built them a personal learning path.
Create your own
Deep Learning for Transformers
·
Module 1
Mathematical Language of Neural Networks
1
Output Shapes in Neural Network Vector and Matrix Multiplication
Determine the output shapes of vector and matrix multiplications used in neural networks.
2
Dot Products and Vector Alignment
Compute dot products and interpret them as measures of vector alignment.
3
Computing Weighted Sums of Vectors
Compute a weighted sum of a set of vectors.
4
Converting Logits to Probabilities with Softmax
Convert a vector of logits into a probability distribution using softmax.
5
Computing Cross-Entropy Loss for a Classification Example
Compute cross-entropy loss for a single classification example.
6
Applying the Chain Rule to Two-Operation Computation Graphs
Apply the chain rule to a two-operation computation graph.
7
Perform a Gradient-Descent Parameter Update
Perform one gradient-descent parameter update from a supplied gradient.
8
Feature Vector Normalization Using Mean and Variance
Normalize a feature vector using its mean and variance.
Next module isn't ready yet,
Back to course
Previous module
Next module