Obviously we are all experimenting with ChatGpt and the other flood of AI tools that are rushing to own some of our head space at the moment.
But as someone who was worked in this space for quite a few years with Sentia, I am often asked ‘What Exactly is AI?”
Artificial Intelligence (AI) is a way of teaching computers to think and learn like humans do. Just like you learn from your experiences, AI can learn from the data it is given.
When you want to teach a computer to do something, (as in program it), you first have to give it a set of rules to follow. These rules are called algorithms. They tell the computer what to do in different situations.
For example, if you want to teach a computer to recognize a picture of a cat, you would give it a set of rules that help it identify the features of a cat, such as its ears, whiskers, and nose. Then, when the computer sees a new picture, it can use those rules to determine whether it is a cat or not.
But sometimes the rules aren’t enough to teach the computer what to do.
That’s where machine learning comes in. Machine learning is a type of AI that allows the computer to learn from the data it is given.
When you use machine learning, you give the computer a large set of examples, such as pictures of cats and pictures of dogs. You set it loose on this large set of examples and the computer analyzes these examples and looks for patterns. It then uses these patterns to make predictions about any new examples it has never seen before.
For example, if you give a machine learning model enough pictures of cats and dogs, it will eventually be able to tell the difference between the two without being explicitly told what the differences are.
There are many different types of AI, each with its own strengths and weaknesses. Some AI is better at recognizing pictures or speech, while others are better at playing games or making predictions.
AI is used in many different applications, from self-driving cars to speech recognition to predicting the weather. It’s an exciting field that is constantly evolving and improving, and it has the potential to change the world in many positive ways.
I asked ChaptGPT itself why it has such an extensive knowledge and what ‘rules’ it was fed and it provided the following:
“As an AI language model, I was created and trained using a set of algorithms and rules that enable me to understand and respond to human language. These rules include natural language processing (NLP), machine learning, and deep learning techniques.
NLP helps me understand the structure and meaning of human language. It enables me to recognize the different parts of speech, such as nouns, verbs, and adjectives, and to understand the relationships between them. NLP also helps me understand idiomatic expressions, metaphors, and other aspects of language that can be tricky to interpret.
Machine learning enables me to learn from the vast amounts of data that I have been trained on. This data includes books, articles, websites, and other sources of information that have been carefully curated and labeled to help me learn. Using machine learning, I can recognize patterns in this data and use them to make predictions and generate responses.
Finally, deep learning allows me to process large amounts of data quickly and efficiently. It enables me to identify and learn from subtle patterns in language, such as the nuances of tone and context. With deep learning, I can continuously improve my understanding and use of language, making me better able to communicate with humans in a natural and intuitive way.
Overall, the rules and algorithms that underpin my operation are designed to help me understand, interpret, and respond to human language in a way that is both accurate and natural.”
Don’t fear AI – use it where it adds value and look forward to just where this exciting technology is heading.
