deep-learning-book-series-home Deep Learning Book Series | Code · Data Science

The Deep Learning Book Series is a set of 12 blog posts and Python notebooks going through the chapter on linear algebra from the Deep Learning Book by Goodfellow, I., Bengio, Y., and Courville, A. (2016).

1. Scalars, Vectors, Matrices and Tensors An example of a scalar, a vector, a matrix and a tensor

2. Multiplying Matrices and Vectors An example of how to calculate the dot product

3. Identity and Inverse Matrices Example of an identity matrix

4. Linear Dependence and Span Examples of systems of equations with 0, 1 and an infinite number of solutions

5. Norms Representation of the squared L2 norm in 3 dimensions

6. Special Kinds of Matrices and Vectors Example of a diagonal matrix and of a symmetric matrix

7. Eigendecomposition Plot of the unit circle and its transformation by the matrix A

8. Singular Value Decomposition The unit circle transformed by the matrix A

9. The Moore-Penrose Pseudoinverse Example of three linear equations in 2 dimensions: this is an overdetermined system

10. The Trace Operator Calculating the trace of a matrix

11. The Determinant Comparison of positive and negative determinant

12. Principal Components Analysis (PCA) Mechanism of the gradient descent algorithm