An AI Glossary – Written by ChatGPT 3.5

(With plain English subtitles … written by Human 1.0!)

1. Artificial Intelligence (AI): The simulation of human intelligence processes by machines, especially computer systems. These processes include learning (the acquisition of information and rules for using the information), reasoning (using rules to reach approximate or definite conclusions), and self-correction. (An electronic approximation of the human brain typically focused on a domain like text search, self-driving, finance, medicine and so on.)

2. Machine Learning (ML): A subset of AI that focuses on the development of algorithms that allow computers to learn from and make predictions or decisions based on data. (Computers using machine learning learn from data and make decisions or predictions without being explicitly programmed for every task.) 

3. Deep Learning: A subset of machine learning that uses neural networks with many layers (deep neural networks) to model and extract patterns from complex datasets. (One might argue that this is a superset of machine learning since it is more complex.)

4. Neural Network: A computer system modeled after the human brain’s network of neurons, used to recognize patterns. (Accomplished via input layers – like human senses, hidden layers – like human thought, and output layers – human decisions/conclusions/actions.) 

5. Supervised Learning: A type of machine learning where the model is trained on labeled data, and its goal is to learn a mapping from input data to output labels. (Think teacher and student. The teacher – an algorithm – provides data and labels for the student – or model – to process.  “This is a 7” or “this is a car” or “212 degrees Farenheight is the boiling point of water at sea level.”  Supervised learning is used in applications suich as image processing, natural language processing, predictive modeling, and production control.)

6. Unsupervised Learning: A type of machine learning where the model is trained on unlabeled data and must find patterns and relationships without guidance. (In the early days of data mining aka Big Data, humans needed to identify clusters and anomalies.  AI can now perform these tasks.)

7. Reinforcement Learning: A type of machine learning where an agent learns to make decisions by taking actions in an environment to maximize some notion of cumulative reward. (A simple example is Hulu using your likes and dislikes to recommend future viewing.  Complex examples would be financial portfolio management based on risk profiles and investment performance or personalized healthcare recommendations based on patient data and clinical outcomes from similarly diagnosed populations.)

8. Natural Language Processing (NLP): The ability of computers to understand, interpret, and generate human language. (Google Translate, Grammarly sentiment and grammar checks, spam or inflamatory content detection, text generation – such as this document, and question answering such as Siri, Alexa, and Google Assistant are examples.)

9. Computer Vision: The field of AI and computer science that focuses on enabling computers to interpret visual information from the real world, including images and videos. (Think Tesla self-driving capabilities – perhaps after the autobraking, Autopilot, and other recalls!)

10. Algorithm: A set of rules or instructions designed to perform a specific task or solve a particular problem. (There are hundreds, if not thousands, of algorithms both common and specific to particular disciplines.)

11. Feature: A measurable property or characteristic of input data used by machine learning algorithms to make predictions or decisions. (An AI feature such as Natural Language Understanding is different from a product feature such as a user interface.  Stated another way, an AI feature describes what something is vs. a product feature which describes what something does.)

12. Model: A mathematical representation of a real-world process or system used for analysis, prediction, or control. (In simple terms, an AI model describes a prototypical end result.  More specifically, it encapsulates the learned knowledge and patterns from data and the expected outcomes.)

13. GPT: Generative Pre-Trained Transformer. A series of AI language models developed by OpenAI. They utilize a transformer architecture, which is highly effective for understanding and generating human-like text. These models are first pre-trained on a vast corpus of text data to learn general language patterns and then fine-tuned for specific tasks through supervised learning. GPTs are capable of a wide range of language tasks, including answering questions, writing text, and more, making them versatile tools in natural language processing. (Translation: They have been pre-trained by feeding them billions of pieces of data from the Internet and other publicly available sources.  They have been taught how to interpret and transform that data to generate responses to questions like “explain transformer architecture to a non-technical person” which resulted in the following:) 

Imagine you’re at a busy party, trying to follow a conversation. Instead of listening to each word in order, you focus on the key words that give you the gist of the discussion. This is similar to how the transformer architecture works in handling language.

Transformers can look at an entire sentence at once, rather than one word at a time. They pay attention to important words, no matter where they are in the sentence, to understand and generate language. This makes them very good at picking up on nuances and context, much like how you tune into the most relevant parts of a conversation in a noisy room. This ability helps them understand and produce text effectively, making them useful for tasks like translating languages or answering questions.

One can even ask for the same question to be answered in olde English:
Imagine, if thee wilt, that thou art at a grand feast in a bustling hall, where many a conversation unfurls around thee. Thou dost not merely harken to thy nearest neighbour, but thine ears catch snippets of discourse from yon and hither, piecing together tales and tidings from all corners of the room.

Or French:
Imaginez que vous êtes à une réception où de nombreuses conversations ont lieu simultanément. Plutôt que d’écouter une seule personne à la fois, vous avez la capacité d’écouter tout le monde en même temps, saisissant l’essence de chaque conversation, peu importe où elle se déroule dans la pièce.

Or Cantonese, or Russian, or … There are not a fixed number of languages because GPTs are language models, not translators.  The quality of the translation will be directly affected by the amount of training material – and human training – that were available in any particular language.  ChatGPT 4.0 completely froze when the same answer was requested in Esperanto, for instance!