Book Image

Democratizing Artificial Intelligence with UiPath

By : Fanny Ip, Jeremiah Crowley
Book Image

Democratizing Artificial Intelligence with UiPath

By: Fanny Ip, Jeremiah Crowley

Overview of this book

Artificial intelligence (AI) enables enterprises to optimize business processes that are probabilistic, highly variable, and require cognitive abilities with unstructured data. Many believe there is a steep learning curve with AI, however, the goal of our book is to lower the barrier to using AI. This practical guide to AI with UiPath will help RPA developers and tech-savvy business users learn how to incorporate cognitive abilities into business process optimization. With the hands-on approach of this book, you'll quickly be on your way to implementing cognitive automation to solve everyday business problems. Complete with step-by-step explanations of essential concepts, practical examples, and self-assessment questions, this book will help you understand the power of AI and give you an overview of the relevant out-of-the-box models. You’ll learn about cognitive AI in the context of RPA, the basics of machine learning, and how to apply cognitive automation within the development lifecycle. You’ll then put your skills to test by building three use cases with UiPath Document Understanding, UiPath AI Center, and Druid. By the end of this AI book, you'll be able to build UiPath automations with the cognitive capabilities of intelligent document processing, machine learning, and chatbots, while understanding the development lifecycle.
Table of Contents (16 chapters)
1
Section 1: The Basics
5
Section 2: The Development Life Cycle with AI Center and Document Understanding
10
Section 3: Building with UiPath Document Understanding, AI Center, and Druid

Closing the feedback loop

As cognitive automation is moved from UAT into production, it can face data not seen from the training, evaluation, and testing test sets. We expect the deployed model to be able to handle new data based on the training performed, but there may be times where the model returns an unsatisfactory result or there are opportunities to further improve the model's performance based on the data it encounters.

This is where closing the feedback loop can play a large factor in the performance of an ML model. By closing the feedback loop on a Document Understanding or AI Center ML skill, we can capture unseen data points, using a human to send feedback to the ML skill and continuously train the skill with new data. You can see a representation of closing the feedback loop in the following screenshot:

Figure 7.11 – Closing the feedback loop

With UiPath, developers can use a confidence threshold to allow automation to continue...