1_Basics | AI - Anony231/LLMSecuirty GitHub Wiki
LLM stands for Large Language Model, which is a type of artificial intelligence program designed to understand and generate human-like text, among other tasks. These models are trained on massive amounts of text data and can be used for various applications like natural language processing, machine translation, content generation, and chatbots.
What is Generative AI?
It is a kind of Artificial Intelligence technology that can produce various types of content including text, audio, video and synthetic data. This creates new content based on what it has learned from existing content.
What is AI?
AI is a discipline like how physics is discipline of science, AI is a branch of Computer Science that deals with creation of Intelligent Agents or systems that can reason, learn, and act autonomously.
AI has to do with theory and methods to build machines that think and act like humans.
What is Machine Learning?
This is subfield of AI. It is a program or system that trains a model from input data. The trained model can make useful predictions from new(never-before-seen) data drawn from the same one used to train the model.
This mean that Machine Learning gives the computer the ability to learn without explicit programming.
How does the Machine Learning models look?
- Supervised (Labeled Data)
- Unsupervised (Unlabeled Data)
What is Deep learning?
It is a type of Machine Learning that uses artificial neural networks, allowing them to process more complex patterns than machine learning. Artificial Neural networks are inspired by the human brain. Like our brain, they are made of many interconnected nodes, or neurons, that can learn to perform tasks by processing data and predictions.
Deep learning models have many layers of neurons, which allow them to learn more complex patterns than traditional machine learning models. Neural networks can use both labeled and unlabeled data. This is called semi-supervised learning. In this, a neural network is trained on a small amount of labeled data and a large amount of unlabeled data.
The labeled data helps the neural network to learn basic concepts of the tasks, while the unlabeled data helps the neural network to generalize to new examples.
Gen AI
Gen AI is a subset of Deep Learning, which means it uses Artificial Neural Networks that can process both labeled and unlabeled data using Supervised, Unsupervised, and semi supervised data. LLMs are also a subset of Deep Learning.
Deep learning models or Machine Learning models can be divided into two types.
- Generative
- Discriminative
Discriminative: It is a type of model that is used to classify or predict labels for data points. These are typically trained on a dataset of labeled data points, and they learn the relationship between the features of the data points and the labels. Once the discriminative model is trained, it can be used to predict the label for a new data points.
Generative: It generates new data instances based on a learned probability distribution of existing data. This creates new content.
Prompt: A prompt is a short piece of text that is given to a LLM as input, and it can be used to control the output of a model in variety of ways. Prompt design is a process of creating a prompt that will generate the desired output from an LLM.