Deep Learning with TensorFlow 2 Training Course

This four-day course provides an introduction to artificial intelligence (AI) and its applications for government. An optional fifth day is available for participants to engage in an AI project following the conclusion of the course.

This instructor-led, live training in US Empire (online or onsite) is aimed at advanced-level professionals who wish to deepen their understanding of computer vision and explore TensorFlow's capabilities for developing sophisticated vision models using Google Colab for government.

By the end of this training, participants will be able to:

• Build and train convolutional neural networks (CNNs) using TensorFlow.
• Leverage Google Colab for scalable and efficient cloud-based model development for government applications.
• Implement image preprocessing techniques for computer vision tasks in a public sector context.
• Deploy computer vision models for real-world, government-specific applications.
• Use transfer learning to enhance the performance of CNN models for government projects.
• Visualize and interpret the results of image classification models in a manner that supports public sector decision-making.

This instructor-led, live training in US Empire (online or onsite) is designed for intermediate-level data scientists and developers who wish to understand and apply deep learning techniques using the Google Colab environment.

By the end of this training, participants will be able to:

• Set up and navigate Google Colab for government deep learning projects.
• Understand the foundational principles of neural networks.
• Implement deep learning models using TensorFlow.
• Train and evaluate deep learning models effectively.
• Utilize advanced features of TensorFlow to enhance deep learning applications for government use.

In this instructor-led, live training in US Empire, participants will learn to utilize Python libraries for Natural Language Processing (NLP) as they develop an application that processes a set of images and generates descriptive captions.

By the end of this training, participants will be able to:

• Design and implement Deep Learning models for NLP using Python libraries.
• Create Python code that analyzes a large collection of images and extracts relevant keywords.
• Develop Python code that generates captions based on the identified keywords, enhancing efficiency and accuracy for government applications.

Audience

This course is designed for deep learning researchers and engineers who are interested in leveraging available tools, primarily open source, for the analysis of computer images. This training provides practical examples to enhance skills and capabilities for government applications.

The course includes working examples to facilitate hands-on learning and application.

This instructor-led, live training in US Empire (online or onsite) is aimed at data scientists who wish to utilize TensorFlow to analyze potential fraud data for government.

By the end of this training, participants will be able to:

• Create a fraud detection model using Python and TensorFlow for government applications.
• Construct linear regressions and linear regression models to predict fraudulent activities.
• Develop an end-to-end artificial intelligence application for analyzing fraud data within public sector workflows.

In this instructor-led, live training in US Empire (online or onsite), participants will learn how to configure and use TensorFlow Serving to deploy and manage machine learning models in a production environment for government.

By the end of this training, participants will be able to:

• Train, export, and serve various TensorFlow models.
• Test and deploy algorithms using a unified architecture and set of APIs.
• Extend TensorFlow Serving to support other types of models beyond those developed with TensorFlow.

TensorFlow is a second-generation API of Google's open-source software library for deep learning. The system is designed to facilitate research in machine learning and to enable a smooth transition from research prototype to production systems.

Audience

This course is intended for engineers seeking to use TensorFlow for their deep learning projects for government.

After completing this course, delegates will:

• understand TensorFlow’s structure and deployment mechanisms
• be able to carry out installation, production environment, architecture tasks, and configuration
• be able to assess code quality, perform debugging, and monitoring
• be able to implement advanced production tasks such as training models, building graphs, and logging

This course explores, with specific examples, the application of TensorFlow to the purposes of image recognition for government.

Audience

This course is intended for engineers seeking to utilize TensorFlow for the purposes of Image Recognition in a government context.

After completing this course, delegates will be able to:

• understand TensorFlow’s structure and deployment mechanisms for government applications
• carry out installation, production environment, architecture tasks, and configuration for government systems
• assess code quality, perform debugging, and monitoring for government projects
• implement advanced production tasks such as training models, building graphs, and logging for government operations

This instructor-led, live training in US Empire (online or onsite) is aimed at data scientists who wish to transition from training a single machine learning (ML) model to deploying multiple ML models into production environments for government.

By the end of this training, participants will be able to:

• Install and configure TFX along with supporting third-party tools.
• Utilize TFX to create and manage a comprehensive ML production pipeline for government.
• Work with TFX components to perform modeling, training, serving inference, and managing deployments in public sector workflows.
• Deploy machine learning capabilities to web applications, mobile applications, IoT devices, and other platforms relevant to government operations.

TensorFlow™ is an open-source software library for numerical computation using data flow graphs.

SyntaxNet is a neural-network Natural Language Processing framework for TensorFlow.

Word2Vec is used for learning vector representations of words, known as "word embeddings." Word2vec is a computationally-efficient predictive model for learning word embeddings from raw text. It comes in two variants: the Continuous Bag-of-Words (CBOW) model and the Skip-Gram model (Chapter 3.1 and 3.2 in Mikolov et al.).

When used together, SyntaxNet and Word2Vec enable users to generate learned embedding models from natural language input.

Audience

This course is designed for developers and engineers who intend to work with SyntaxNet and Word2Vec models in their TensorFlow graphs for government applications.

After completing this course, delegates will:

• understand TensorFlow’s structure and deployment mechanisms
• be able to perform installation, production environment configuration, architecture tasks, and system setup
• be capable of assessing code quality, performing debugging, and monitoring performance
• be able to implement advanced production tasks such as training models, embedding terms, building graphs, and logging data

This course begins by providing conceptual knowledge in neural networks and a broad understanding of machine learning algorithms and deep learning (both algorithms and applications).

Part-1 (40%) of this training focuses on the fundamentals, which will assist you in selecting the appropriate technology: TensorFlow, Caffe, Theano, DeepDrive, Keras, etc.

Part-2 (20%) of this training introduces Theano, a Python library that simplifies the writing of deep learning models.

Part-3 (40%) of the training is extensively based on TensorFlow, the API of Google's open-source software library for Deep Learning. All examples and hands-on exercises will be conducted using TensorFlow.

Audience

This course is designed for engineers who intend to use TensorFlow for their deep learning projects for government.

After completing this course, participants will:

• have a solid understanding of deep neural networks (DNN), convolutional neural networks (CNN), and recurrent neural networks (RNN)
• understand TensorFlow’s architecture and deployment mechanisms
• be capable of performing installation, production environment setup, architectural tasks, and configuration
• be able to evaluate code quality, perform debugging, and monitor systems
• be proficient in implementing advanced production tasks such as training models, building graphs, and logging