101 Flashcards
Generative AI
A type of artificial intelligence that can produce various types of content, including text, images, audio/video, and synthetic data.
Basic AI
The theory and methods to build machines that think like humans.
Machine learning
A sub-field of AI. It’s a program that trains a model with data input. The trained model can make useful predictions drawn from the data used to train the model.
Supervised ML
Has labeled data that comes with a tag (name, type, or number). The model learns from past examples to predict future values.
Unsupervised ML
Unlabeled data (no tags). All about discovery, looking at raw data and seeing if it falls into groups.
Deep learning
A subset of Machine learning. Uses artificial neural networks to process complex patterns
Neural Networks
Like our brain, they are made of of interconnected nodes/neurons that can learn to perform tasks by processing data and making predictions.
Algorithm
A set of step by step instructions a program uses to solve a problem or accomplish a certain task. They can involve complex math, logical operations, etc.
Hallucinations
Words or phrases generated by the model that are often nonsensical or grammatically incorrect.
Large Language Models (LLMs)
(image) A subset of Deep Learning. Large, general purpose models that can be pre-trained and then fine-tuned for a specific purpose. [e.g. question answering, document summarization, and text generation] ChatGPT and Bard are LLMs
Parameters
The knowledge the machine learned from the model training. [Predicting text]
PaLM (Pathways Language Model)
Google released PaLM, a 540 billion-parameter model that achieves a state-of-the-art performance across multiple language tasks.
Prompt Design
Prompt design is the process of creating a prompt that is tailored to the specific task that the system is being asked to perform.
For example, if the system is being asked to translate a text from English to French, the prompt should be written in English and should specify that the translation should be in French.
Prompt Engineering
Prompt engineering is the process of creating a prompt that is designed to improve performance. This may involve using domain-specific knowledge, providing examples of the desired output, or using keywords that are known to be effective for the specific system
Tuning
Tuning a model enables you to customize the model response based on examples of the task that you want the model to perform. It is essentially the process of adapting a model to a new domain or set of custom use cases by training the model on new data.
