This is a 2-day course packaged with the right balance of theory and hands-on activities that will help you easily learn TensorFlow and Keras from scratch.
This course will provide you with a blueprint of how to build an application that generates predictions using a deep learning model. From there you can continue to improve the example model—either by adding more data, computing more features, or changing its architecture—continuously increasing its prediction accuracy, or create a completely new model, changing the core components of the application as you see fit.
TARGET AUDIENCE:
This course is designed for developers, analysts, and data scientists interested in developing applications using TensorFlow and Keras.
COURSE PREREQUISITES:
Hardware:
For successful completion of this course, students will require computer systems with the following:
• Processor: 2.6 GHz or higher, preferably multi-core
• Memory: 4 GB RAM
• Hard disk: 10 GB
• Projector
• Internet connection
Software:
• Operating System: Windows (8 or higher).
• Visual Studio Code: https://code.visualstudio.com/ .
• Python 3: Follow instructions in website: https://www.python.org/downloads/
• TensorFlow 1.4 or higher on Windows: Follow instructions in website: https://www.tensorflow.org/install/install_windows .
• Keras 2: Follow instructions in website (Keras only): https://keras.io/#installation .
COURSE CONTENT:
Lesson 1: Introduction to Neural Networks and Deep Learning
• What are Neural Networks?
• Configuring a Deep Learning Environment
Lesson 2: Model Architecture
• Choosing the Right Model Architecture
• Using Keras as a TensorFlow Interface
Lesson 3: Model Evaluation and Evaluation
• Model Evaluation
• Hyperparameter Optimization
Lesson 4: Productization
• Handling New Data
• Deploying a Model as a Web Application
COURSE OBJECTIVE:
• A blueprint of the complete process for deploying a deep learning application: from environment setup to model deployment.
• A hands-on introduction to TensorFlow and Keras, popular technologies for building production-grade deep learning models.
• An example web-application that uses an HTTP API interface to retrieve model predictions.
FOLLOW ON COURSES:
Not available. Please contact.