Statistical Machine Learning, Week 3: Tensor, Gradient, and Automatic Differentiation (GradientTape)

#tensorflow #gradient #coding
Tensors provide a unified and efficient data structure to represent and process different types of data (tabular, image, time series) in machine learning, allowing for seamless integration with mathematical operations and optimization algorithms essential for training models.
tensors
tensor operations
differentiation: finding the derivative, or rate of change, of a function
Tensors are a generalization of vectors and matrices to an arbitrary number of dimensions
In the context of tensors, a dimension is often called an "axis"
The number of axes of a tensor is called its "rank"
Scalars: rank-0 tensors
Vectors: rank-1 tensors
Matrices: rank-2 tensors
Higher-rank tensors are very useful for representing complex data sets