Jaringan saraf pertama Anda

Pengantar Deep Learning dengan Keras

Miguel Esteban

Data Scientist & Founder

Apa itu jaringan saraf?

Parameter

Penurunan gradien

API Sequential

Mendefinisikan jaringan saraf

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Dense

# Create a new sequential model
model = Sequential()

# Add and input and dense layer
model.add(Dense(2, input_shape=(3,)))

# Add a final 1 neuron layer
model.add(Dense(1))

Menambahkan aktivasi

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Dense

# Create a new sequential model
model = Sequential()

# Add and input and dense layer
model.add(Dense(2, input_shape=(3,)))

# Add a final 1 neuron layer
model.add(Dense(1))

Menambahkan aktivasi

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Dense

# Create a new sequential model
model = Sequential()

# Add and input and dense layer
model.add(Dense(2, input_shape=(3,),
                activation="relu"))

# Add a final 1 neuron layer
model.add(Dense(1))

Ringkas model Anda

model.summary()

Layer (type)                 Output Shape              Param #   
=================================================================
dense_3 (Dense)              (None, 2)                 8         
_________________________________________________________________
dense_4 (Dense)              (None, 1)                 3         
=================================================================
Total params: 11
Trainable params: 11
Non-trainable params: 0
_________________________________________________________________

Visualisasikan parameter

Ringkas model Anda

model.summary()

Layer (type)                 Output Shape              Param #   
=================================================================
dense_3 (Dense)              (None, 2)             --> 8 <--       
_________________________________________________________________
dense_4 (Dense)              (None, 1)                 3         
=================================================================
Total params: 11
Trainable params: 11
Non-trainable params: 0
_________________________________________________________________

Mari menulis kode!

Pengantar Deep Learning dengan Keras