Input layer

As explained in Grokking Machine Learning

The neural-network layer that receives the input features or input representation.

The input layer is the first layer in a neural network and receives its input features or representation. Its size is the number of non-bias nodes; hidden layers follow it, with the output layer at the end. section 10.1

Setting an input shape

For a dataset with two features, a Keras dense layer can declare `input_shape=(2,)`. For handwritten digits, images are flattened into 784 values before the input shape is set to `(28*28,)`. section 10.3

Figure 10.21 The architecture that we will use to classify our dataset. It contains two hidden layers: one of 128 and one of 64 nodes. The activation function between them is a ReLU, and the final activation function is a softmax.

The diagram shows a two-node input layer followed by two hidden layers and a two-node output layer. section 10.3

How Grokking Machine Learning covers it

How deep it goes

Defines its position and layer size, then demonstrates declaring input shapes in Keras.

Examples

Uses two-feature data and flattened handwritten-digit images as input representations.

What you can do after

Apply it via Keras by setting `input_shape` to match the dataset's feature representation.

How it connects

Connects the input layer to hidden layers, the output layer, and fully connected neural-network architecture.

liveBookmanning.com

Read Grokking Machine Learning 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
  Inside AIAn input layer is the neural-network layer that receives the input data.
• 

  liveBookmanning.com
  Data Without LabelsAn input layer is the first neural-network layer that receives input data and distributes it to subsequent layers.

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 Grokking Machine Learning. The section links point to the parts of the book it draws on.