Читать книгу Machine Learning For Dummies - John Paul Mueller, John Mueller Paul, Luca Massaron - Страница 23

Machine learning is only part of what a system requires to become an AI. The machine learning portion of the picture enables an AI to perform these tasks:

 Adapt to new circumstances that the original developer didn’t envision

 Detect patterns in all sorts of data sources

 Create new behaviors based on the recognized patterns

 Make decisions based on the success or failure of these behaviors

The use of algorithms to manipulate data is the centerpiece of machine learning. To prove successful, a machine learning session must use an appropriate algorithm to achieve a desired result. In addition, the data must lend itself to analysis using the desired algorithm, or it requires a careful preparation by scientists.

AI encompasses many other disciplines to simulate the thought process successfully. In addition to machine learning, AI normally includes

 Natural language processing: The act of allowing language input and putting it into a form that a computer can use.

 Natural language understanding: The act of deciphering the language in order to act upon the meaning it provides.

 Knowledge representation: The ability to store information in a form that makes fast access possible.

 Planning (in the form of goal seeking): The ability to use stored information to draw conclusions in near real time (almost at the moment it happens, but with a slight delay, sometimes so short that a human won’t notice, but the computer can).

 Robotics: The ability to act upon requests from a user in some physical form.

In fact, you might be surprised to find that the number of disciplines required to create an AI is huge. Consequently, this book exposes you to only a portion of what an AI contains. However, even the machine learning portion of the picture can become complex because understanding the world through the data inputs that a computer receives is a complex task. Just think about all the decisions that you constantly make without thinking about them. For example, just the concept of seeing something and knowing whether you can interact successfully with it can become a complex task.