Eagle-Eye View of Azure Cognitive Services
What are Azure Cognitive Services? What problems do they solve in the real world? These are a few of the questions that might come to mind when we come across the term Azure Cognitive Services. This chapter will dive in and find answers to these questions
- PDF / 1,280,367 Bytes
- 29 Pages / 439.37 x 666.142 pts Page_size
- 30 Downloads / 185 Views
Eagle-Eye View of Azure Cognitive Services What are Azure Cognitive Services? What problems do they solve in the real world? These are a few of the questions that might come to mind when we come across the term Azure Cognitive Services. This chapter will dive in and find answers to these questions. We are going to explore the QnAMaker service, which is part of Azure Cognitive Services, so it’s a good idea to build the context around Azure Cognitive Services first. Let’s start by taking a look at what cognitive services are all about.
The What and Why of Cognitive Services You must have come across terms like artificial intelligence (AI), machine learning (ML), and deep learning. These are part of intelligent conversations around the industrial word. Let’s look at what these actually are.
© Kasam Shaikh 2019 K. Shaikh, Developing Bots with QnA Maker Service, https://doi.org/10.1007/978-1-4842-4185-1_1
1
Chapter 1
Eagle-Eye View of Azure Cognitive Services
Artificial Intelligence One of the simpler, smarter definitions of AI was quoted by the American computer scientist John McCarthy in 1956. He said that, “AI involves machines that can perform tasks that are characteristic of human intelligence.” This might not be the exact meaning of AI but is very close. For me, AI is about resembling human attributes like understanding, predicting, and acknowledging, which are no doubt complex tasks to emulate. There are different ways to achieve artificial intelligence, and one of them is by implementing artificial intelligence through machine learning.
Machine Learning According to Arthur Samuel in 1959, machine learning is “…a field of computer science that gives computers the ability to learn without being explicitly programmed”. So, it’s about enabling your machine to learn without having to punch in hardcoded commands. In as simple a way as possible, I will try to explain how machine learning works! Consider these phases:
2
•
You have raw data with different patterns.
•
The machine learning algorithm analyzes the patterns in the data. Techniques like deep learning are used.
•
After analyzing the patterns, the algorithm creates a machine learning model, which is an output of the process.
•
This model recognizes the patterns.
•
The application seeds the data so that the models can recognize any patterns.
Chapter 1
Eagle-Eye View of Azure Cognitive Services
This is not an easy task to perform. It requires lots of data pertaining to different cases and expert training models. The second complex part is creating a machine learning algorithm and testing it with a certain number of real-world cases. This comes with no guarantee of successful end results. The task here is to expose your new model to the application. Now this exposure should not compromise security, availability, or performance. Another set of complexity comes into existence. You need machine learning to make the application intelligent. For this, you need to have data, algorithms, and models in place. This is where Azure Cognitive Se
Data Loading...
