Vanishing gradient problem

As explained in Grokking AI Algorithms, Second Edition

The vanishing gradient problem is a training difficulty in which derivatives become extremely small and cause neural-network parameter updates to become ineffective.

The vanishing gradient problem occurs when derivatives become extremely small, making parameter updates ineffective and causing a network to stop learning. With sigmoid or hyperbolic-tangent activations, inputs near the extremes flatten the curve, so its gradient approaches zero. section 9.10 section 9.2

Common causes and responses include:

• Using sigmoid or hyperbolic tangent at extreme values can produce tiny derivatives; hyperbolic tangent has steeper derivatives but can still vanish at its extremes. section 9.10
• Initializing weights too small can weaken the signal across layers until learning stops, while overly large weights create the contrasting exploding-gradient problem. section 9.14
• ReLU allows some neurons not to activate and can reduce computation, while smart initialization aims to keep activation variance consistent across layers. section 9.10 section 9.14

The Telephone Analogy

Imagine a 100-layer game of Telephone. If each layer passes along a slightly weaker whisper because the weights are too small, the final listener hears nothing. That fading signal represents the vanishing gradient; balanced initialization keeps the signal at roughly the same strength as it travels through the network. section 9.14

Figure 9.29 Common used activation functions

Compare sigmoid, hyperbolic tangent, and ReLU visually to see which activation curves flatten and which permit stronger learning behavior. section 9.10

How Grokking AI Algorithms, Second Edition covers it

How deep it goes

Explains flat activation curves, small derivatives, initialization effects, and practical mitigations without deriving gradient propagation mathematically.

Examples

Uses flat sigmoid extremes, a 100-layer telephone whisper, and activation-function comparisons as concrete teaching examples.

What you can do after

Evaluate activation functions and weight initialization choices when diagnosing ineffective neural-network learning.

How it connects

Connects sigmoid, hyperbolic tangent, ReLU, activation functions, weight initialization, and the exploding-gradient problem.

liveBookmanning.com

Read Grokking AI Algorithms, Second Edition on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Sutskever's ListA vanishing gradient is an optimization failure in which derivatives become too small to support effective parameter updates during neural-network training.
• 

  liveBookmanning.com
  Grokking Machine LearningA neural-network training problem in which gradients become extremely small as they are propagated through layers, slowing or preventing learning.
• 

  liveBookmanning.com
  Math and Architectures of Deep LearningThe training difficulty in deep networks where repeated multiplication of small derivatives makes early-layer gradients nearly zero.
• 

  liveBookmanning.com
  Deep Learning with R, Third EditionA vanishing gradient is a training condition in which gradients become extremely small as they propagate through a deep network, slowing or preventing parameter updates in earlier layers.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionA training problem in deep networks where gradient signals become too small to effectively update earlier layers.
• 

  liveBookmanning.com
  Inside Deep Learning: Math, Algorithms, ModelsA training instability in which gradients become too small for effective learning updates.
• 

  liveBookmanning.com
  Graph Neural Networks in ActionAn optimization problem in which gradients become progressively smaller as they are propagated through many computational steps, hindering learning of long-range dependencies.
• 

  liveBookmanning.com
  Evolutionary Deep Learning: Genetic algorithms and neural networksA neural-network training failure in which backpropagated gradients become extremely small across successive layers, limiting effective parameter updates.
• 

  liveBookmanning.com
  Deep Learning with PyTorch, Second EditionThe difficulty in training deep networks when gradients become too small as they propagate backward through many layers.
• 

  liveBookmanning.com
  Learn Generative AI with PyTorchA training failure mode in deep networks where gradient signals become too small to effectively update early layers.
• 

  liveBookmanning.com
  LLMs in ProductionA vanishing gradient is a training condition in which propagated derivatives become increasingly small and impede parameter updates.
• 

  liveBookmanning.com
  Data Without LabelsThe vanishing gradient problem is an optimization difficulty in which gradients become extremely small during learning, hindering the retention of information across many sequence steps.
• 

  liveBookmanning.com
  Build a Large Language Model (From Scratch)A training difficulty in deep neural networks where gradients shrink as they propagate backward, hindering learning in early layers.

Compare how 14 books explain vanishing gradient problem →

Related concepts

• ReLUaddressed by · ReLU, or rectified linear unit, is an activation function that maps an input x to max(0, x).
• residual connectionaddressed by · A residual connection is a neural-network pathway that carries an earlier representation around one or more transformations to a later computation, where it can be combined with the transformed representation.
• LSTMaddressed by · An LSTM is a recurrent neural network architecture with gated memory mechanisms that control information flow and help retain or update information across sequences.
• ResNetaddressed by · ResNet is a family of deep neural-network architectures built from residual blocks with shortcut connections that facilitate information flow and optimization.
• GRUaddressed by · A gated recurrent unit (GRU) is a recurrent neural-network architecture that uses learned gates to regulate information flow and update a hidden state across sequence steps.
• normalizationaddressed by · Normalization is the process of transforming a value, representation, or data structure to satisfy a specified standard, scale, or structural constraint.

This explainer was generated by Manning's knowledge graph from the text of Grokking AI Algorithms, Second Edition. The section links point to the parts of the book it draws on.