Reading time: 2 minutes
Today I’m going to show you an example of how to create a neural network using Python and the Keras library:
from keras.models import Sequential from keras.layers import Dense # Create the model model = Sequential() # Add an input layer with 16 neurons model.add(Dense(16, input_dim=8, activation='relu')) # Add a hidden layer with 8 neurons model.add(Dense(8, activation='relu')) # Add an output layer with 1 neuron model.add(Dense(1, activation='sigmoid')) # Compile the model model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy']) # Train the model with the training data model.fit(X_train, y_train, epochs=10, batch_size=32) # Make predictions with the test data predictions = model.predict(X_test)
In this example, we have created a neural network with an input layer of 16 neurons, a hidden layer of 8 neurons, and an output layer of 1 neuron. The activation function used in the input layer and the hidden layer is the Rectified Linear Unit (ReLU) function, and the activation function used in the output layer is the sigmoid function.
Then, we compile the model using the binary_crossentropy loss function and the Adam optimizer.
Finally, we train the model with the training data using the fit method and make predictions with the test data using the predict method.
This is just a basic example of how to create a neural network using Keras. You can add more layers and modify the hyperparameters to improve the performance of your model.
With a little bit of experimentation and effort, you can create powerful and accurate neural networks!
How is AI revolutionizing our lives?
