How deeply does Deep Learning with Python, Third Edition cover variable?

Defines mutability and demonstrates whole-value, subset, additive, and subtractive assignment before applying updates in a classifier.

Variable

As explained in Deep Learning with Python, Third Edition

A mutable TensorFlow value that stores learnable parameters such as weights and bias in this example.

TensorFlow tensors are immutable, but training must update model state. A tf.Variable supplies that mutable state for learnable values such as weights and bias. section 3.3.1

Updating a linear classifier

A linear classifier creates W with random values and b with zeros, then computes predictions as tf.matmul(inputs, W) + b. During each training step, GradientTape computes gradients, and W.assign_sub(...) and b.assign_sub(...) update the variables. section 3.3.2

Use variable assignment methods when changing stored state:

Call assign to replace the complete value. section 3.3.1
Assign a subset through indexed assignment, such as v[0, 0].assign(3.). section 3.3.1
Use assign_add and assign_sub for efficient incremental updates. section 3.3.1

Listing 3.5 Creating a `tf.Variable`

>>> v = tf.Variable(initial_value=tf.random.normal(shape=(3, 1)))
>>> print(v)
array([[-0.75133973],
       [-0.4872893 ],
       [ 1.6626885 ]], dtype=float32)>

Inspect a minimal tf.Variable creation example, then compare it with assign-based updates. section 3.3.1

How Deep Learning with Python, Third Edition covers it

Cover of Deep Learning with Python, Third Edition

liveBook manning.com

Read Deep Learning with Python, Third Edition on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Deep Learning with R, Third EditionA TensorFlow variable is a mutable tensor-like object that stores modifiable model state and can be updated by assignment.

Compare how 2 books explain variable →

Related concepts

model parallelismused by · Model parallelism is a distributed-computing technique that partitions a machine-learning model’s parameters, layers, or computations across multiple devices.
tensoruses · A tensor is a multidimensional, array-like structure of values indexed along zero or more dimensions and used for numerical computation.
mathematical variableimplements · A mathematical variable is a symbol or quantity representing a value or attribute that can vary or be determined within a defined domain.
variablekind of · A variable is a named program binding or entity associated with a value that can be accessed and, when permitted, changed during computation.

This explainer was generated by Manning's knowledge graph from the text of Deep Learning with Python, Third Edition. The section links point to the parts of the book it draws on.