Революция Нейросетей

# Создание простой нейронной сети
import tensorflow as tf
from tensorflow.keras import layers
model = tf.keras.Sequential([
layers.Dense(128, activation='relu', input_shape=(784,)),
layers.Dropout(0.2),
layers.Dense(64, activation='relu'),
layers.Dense(10, activation='softmax')
])
model.compile(
optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy']
)
# Обучение модели
history = model.fit(
x_train, y_train,
epochs=50,
batch_size=32,
validation_split=0.2
)

// Neural Network на JavaScript
class NeuralNetwork {
constructor(inputSize, hiddenSize, outputSize) {
this.weights1 = this.randomMatrix(inputSize, hiddenSize);
this.weights2 = this.randomMatrix(hiddenSize, outputSize);
this.learningRate = 0.1;
}
sigmoid(x) {
return 1 / (1 + Math.exp(-x));
}
predict(input) {
const hidden = this.multiply(input, this.weights1)
.map(x => this.sigmoid(x));
const output = this.multiply(hidden, this.weights2)
.map(x => this.sigmoid(x));
return output;
}
}

# TensorFlow 2.0 Advanced Model
import tensorflow as tf
class CustomNeuralNetwork(tf.keras.Model):
def __init__(self, num_classes=10):
super(CustomNeuralNetwork, self).__init__()
self.conv1 = tf.keras.layers.Conv2D(32, 3, activation='relu')
self.flatten = tf.keras.layers.Flatten()
self.fc1 = tf.keras.layers.Dense(128, activation='relu')
self.dropout = tf.keras.layers.Dropout(0.1)
self.fc2 = tf.keras.layers.Dense(num_classes)
def call(self, x, training=False):
x = self.conv1(x)
x = self.flatten(x)
x = self.fc1(x)
if training:
x = self.dropout(x, training=training)
return self.fc2(x)