Input layer

As explained in Data Without Labels

An input layer is the first neural-network layer that receives input data and distributes it to subsequent layers.

An input layer is the first neural-network layer. It receives input data and passes it to hidden layers, where processing, feature extraction, and learning occur before the output layer makes a prediction. section 8.2.3

Information moves through the network in a directed sequence:

• The input layer consumes raw or processed data, such as images. section 8.2.3 section 8.3.2
• Hidden layers transform the data using weights, bias terms, and activation functions. section 8.3.2
• The output layer uses the transformed information to produce a prediction. section 8.2.3 section 8.3.2

Image and face recognition

For image classification, the input layer receives raw or processed images. In a face-recognition task, it receives face images from different angles, which flow through transformation layers to produce a probability for a person’s identity. section 8.2.3 section 8.3.2

In a convolutional neural network, the input is generally an image tensor represented by width, height, and color channels. Convolution layers then scan it for visual patterns. section 8.6.1

Figure 8.4 A typical neural network with neurons and input, hidden, and output layers

Use the network diagram to trace connections from input units through hidden layers to the output layer. section 8.2.3

How Data Without Labels covers it

How deep it goes

Explains the layer’s position and data flow, but defers specialized connection patterns beyond the basic network structure.

Examples

Uses image classification, face recognition, raw images, processed images, and image tensors with color channels.

What you can do after

Evaluate/understand how data enters a neural network and flows toward image or identity predictions.

How it connects

Connects input layers with neural networks, hidden layers, output layers, feed-forward propagation, and convolutional neural networks.

liveBookmanning.com

Read Data Without Labels on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Classic Computer Science Problems in Swift: Essential techniques for practicing programmersAn input layer is the first neural-network layer that receives input signals and passes them into the network.
• 

  liveBookmanning.com
  Grokking Machine LearningThe neural-network layer that receives the input features or input representation.
• 

  liveBookmanning.com
  Inside AIAn input layer is the neural-network layer that receives the input data.

Compare how 4 books explain input layer →

Related concepts

• deep learningpart of · Deep learning is a machine-learning approach that uses neural networks with multiple computational layers to learn representations from data.
• neural network layerkind of · A neural network layer is a computational stage or component that transforms input representations into outputs within a neural network.
• convolutional neural networkpart of · A convolutional neural network is a neural-network architecture that applies learned convolutional operations to extract patterns from structured data.
• Mapconfigured by · A map is an associative data structure that stores key-value pairs and supports retrieving values by key.
• hidden layercontrasts with · A hidden layer is an internal neural-network layer between the input and output layers that transforms intermediate representations.

This explainer was generated by Manning's knowledge graph from the text of Data Without Labels. The section links point to the parts of the book it draws on.