Classification binaire

Introduction à Deep Learning avec Keras

Miguel Esteban

Data Scientist & Founder

Quand utiliser la classification binaire ?

Notre ensemble de données

Graphiques en paires

import seaborn as sns

# Plot a pairplot
sns.pairplot(circles, hue="target")

La fonction sigmoïde

Construisons-le

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

# Instantiate a sequential model
model = Sequential()

Construisons-le

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

# Instantiate a sequential model
model = Sequential()

# Add input and hidden layer
model.add(Dense(4, input_shape=(2,),
                activation='tanh'))

Construisons-le

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

# Instantiate a sequential model
model = Sequential()

# Add input and hidden layer
model.add(Dense(4, input_shape=(2,),
                activation='tanh'))

# Add output layer, use sigmoid
model.add(Dense(1, 
                activation='sigmoid'))

Compilation, entraînement, prédiction

# Compile model
model.compile(optimizer='sgd',
              loss='binary_crossentropy')

# Train model
model.train(coordinates, labels, epochs=20)

# Predict with trained model
preds = model.predict(coordinates)

Passons à la pratique !

Introduction à Deep Learning avec Keras