Keras provides a wide variety of layers that can be used to build neural networks. Layers are the fundamental building blocks of neural networks and can be used to create complex architectures.
Common Layer Types
- Dense Layers: Fully connected layers.
- Convolutional Layers: Used for processing data with a grid-like topology, such as images.
- Recurrent Layers: Used for sequential data, such as time series or natural language.
Usage Example
Here is a simple example of using a Dense layer:
from keras.layers import Dense
model = Sequential()
model.add(Dense(units=64, activation='relu', input_dim=100))
This creates a dense layer with 64 units and a ReLU activation function, expecting input of dimension 100.
Further Reading
For more information on layers, you can check out the Keras Layers documentation.