Python for Robotic Process Automation

Best Tool To Streamline/Automate Business Processes: Python RPA.

24

9 Hours

Navigate

Data Analytics Tutorial for Beginners

Artificial Intelligence for Beginners

Machine Learning Tutorial for Beginners

Building Your First Deep Learning Model with Keras

  • Updated on 10/09/2024
  • 450 Views

Step-by-Step Guide

  • Import Libraries:

  • Prepare the Data:

  • Build the Model:

  • Compile the Model:

  • Train the Model:

  • Evaluate the Model:

Explanation

  • Import Libraries:tensorflow and keras are used for building and training the model. mnist is a dataset of handwritten digits.

  • Prepare the Data:Load the MNIST dataset. Normalize the data by dividing by 255.0 to scale the pixel values between 0 and 1.

  • Build the Model:Sequential: A linear stack of layers. Flatten: Converts each 28x28 image into a 784-dimensional vector. Dense: Fully connected layer. The first Dense layer has 128 neurons with ReLU activation. The second Dense layer has 10 neurons (one for each digit) with softmax activation.

  • Compile the Model:optimizer='adam': Optimizer for training. loss='sparse_categorical_crossentropy': Loss function for multi-class classification. metrics=['accuracy']: Metric to evaluate during training and testing.

  • Train the Model:Fit the model to the training data for 5 epochs.

  • Evaluate the Model:Evaluate the model on the test data to see how well it performs.

Activity

  • Activity: Build and train your own deep learning model using the MNIST dataset. Experiment with different configurations and observe how the accuracy changes.

Quiz

1. What function is used to load the MNIST dataset in TensorFlow?

  • a) tf.keras.datasets.mnist.load_data()
  • b) tf.keras.datasets.cifar10.load_data()
  • c) tf.keras.datasets.load_mnist()
  • d) tf.keras.datasets.load_data()

2. What activation function is used in the output layer for a classification problem with multiple classes?

  • a) ReLU
  • b) Sigmoid
  • c) Softmax
  • d) Tanh

3. Which optimizer is commonly used for training deep learning models?

  • a) SGD
  • b) Adam
  • c) RMSprop
  • d) Adagrad

4. How many epochs are typically used for training a model in an introductory example?

  • a) 1
  • b) 5
  • c) 10
  • d) 50

5. True or False: The fit method is used to evaluate the model.

  • a) True
  • b) False

Unlock Expert Career Advice For Free

Form Illustration
+91

Join 5M+ Learners & Transform Your Career

Learn on a personalised AI-powered platform that offers
best-in-class content, live sessions & mentorship from
leading industry experts.

Top Resources

Recommended Programs

Post Graduate Programme in Data Science & AI (Executive)

Post Graduate Programme in Data Science & AI (Executive)

  • Executive PG Program
  • 12 Months
  • Complimentary Python Bootcamp
Post Graduate Programme in Data Analytics (Executive)

Post Graduate Programme in Data Analytics (Executive)

  • Executive PG Program
  • 12 Months
  • Complimentary Python Bootcamp
Post Graduate Programme in Digital Marketing

Post Graduate Programme in Digital Marketing

  • Executive PG Program
  • 12 Months
  • Complimentary Python Bootcamp

© 2025 LEJHRO. All Rights Reserved.