How to create your FIRST NEURAL NETWORK with TensorFlow!

How to Create Your FIRST NEURAL NETWORK with TensorFlow!

Creating your first neural network with TensorFlow is an exciting journey. In this article, we'll guide you through the process step-by-step. By the end, you'll know how to import TensorFlow, load and prepare data, create and compile a model, and finally train and evaluate it. Let's dive in!

Step 1: Import TensorFlow

First, you need to import TensorFlow. This can be done simply by using the following code:

import tensorflow as tf

Step 2: Load the MNIST Dataset

TensorFlow comes with several built-in datasets. Here, we'll use the MNIST dataset, which consists of handwritten digits. We need to load the data and split it into training and test sets:

mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()

Step 3: Normalize the Data

It is important to normalize the data to be between 0 and 1 for faster convergence:

x_train, x_test = x_train / 255.0, x_test / 255.0

Step 4: Build the Neural Network

We'll use the Sequential API from TensorFlow to build our neural network. This allows us to stack layers in a straightforward manner:

model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(input_shape=(28, 28)),  # Flatten input
    tf.keras.layers.Dense(128, activation='relu'), # Dense layer with ReLU activation
    tf.keras.layers.Dense(10, activation='softmax') # Output layer with 10 classes
])

Step 5: Compile the Model

Next, we compile the model by specifying the optimizer, loss function, and metrics:

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

Step 6: Train the Model

We then train the model using the training data and specify the number of epochs:

model.fit(x_train, y_train, epochs=5)

Step 7: Evaluate the Model

Finally, we evaluate the model to see how it performs on the test data:

model.evaluate(x_test, y_test)

Results

After running the code, we obtained an accuracy of 97%. Not bad for our first neural network!

Keyword

• TensorFlow
• Neural Network
• MNIST Dataset
• Normalization
• Sequential API
• Compile Model
• Train Model
• Evaluate Model

FAQ

Q: What is the purpose of normalizing the data? A: Normalizing the data to be between 0 and 1 helps in faster convergence during training.

Q: What is the MNIST dataset? A: The MNIST dataset is a collection of 70,000 handwritten digits used for training image processing systems.

Q: Why do we use the Sequential API? A: The Sequential API allows for an easy and straightforward way to build deep learning models by stacking layers.

Q: What is the role of the Flatten layer in the neural network? A: The Flatten layer transforms the input data into a 1D array, making it suitable for the Dense layer.

Q: Which optimizer and loss function are used in this example? A: We use the 'adam' optimizer and 'sparse_categorical_crossentropy' loss function.

Q: How do we measure the performance of the model? A: The performance of the model is measured using the accuracy metric during the evaluation phase.