Basics Flashcards
Labeled data
dataset where each instance or example is accompanied by a label or target variable that represents the desired output or classification.
Unlabeled data
dataset where the instances or examples do not have any associated labels or target variables. The data consists only of input features, without any corresponding output or classification.
Structured data
data that is organized and formatted in a predefined manner, typically in the form of tables or databases with rows and columns. This type of data is suitable for traditional machine learning algorithms that require well-defined features and labels. The following are types of structured data.
Unstructured data
data that lacks a predefined structure or format, such as text, images, audio, and video.
Batch inferencing
when the computer takes a large amount of data, such as images or text, and analyzes it all at once to provide a set of results.
Real-time inferencing
when the computer has to make decisions quickly, in response to new information as it comes in. This is important for applications where immediate decision-making is critical, such as in chatbots or self-driving cars.
Computer vision
a field of artificial intelligence that makes it possible for computers to interpret and understand digital images and videos.
Natural language processing (NLP
when a computer uses algorithms and information about linguistics to better understand language.
foundation model lifecycle
comprehensive process that involves several stages, each playing a crucial role in developing and deploying effective and reliable foundation models
Multimodal models
multimodal models can process and generate multiple modes of data simultaneously.
Generative adversarial networks (GANs)
a type of generative model that involves two neural networks competing against each other in a zero-sum game framework.
Generator
generates new synthetic data (for example, images, text, or audio) by taking random noise as input and transforming it into data that resembles the training data distribution.
Discriminator
This network takes real data from the training set and synthetic data generated by the generator as input. Its goal is to distinguish between the real and generated data.
Variational autoencoders (VAEs)
generative model that combines ideas from autoencoders (a type of neural network) and variational inference (a technique from Bayesian statistics). In a VAE, the model consists of two parts:
Encoder
This neural network takes the input data (for example, an image) and maps it to a lower-dimensional latent space, which captures the essential features of the data.
Decoder
This neural network takes the latent representation from the encoder and generates a reconstruction of the original input data.
Retrieval-augmented generation (RAG)
technique that supplies domain-relevant data as context to produce responses based on that data.
Perceptron
Basic machine learning model designed so that computers could learn from a diverse range of data
Neural Network
neural networks are composed of billions of artificial neurons or nerve cells that process and transmit information
supervised learning
A process by which data is associated with tags (labeled data) allowing computer algorithms to learn the underlying patterns and relationships in the data based on those tags.
unsupervised learning
A process by which data without tags (unlabeled data) is analyzed by machines to engage in a form of implied learning. With repetition and improved training techniques, machines behave more human-like, and with greater accuracy over time.
Machine Learning
Machine learning is a sub-field of AI that teaches computers how to learn new things without being programmed to do them
Generative AI
A type of artificial intelligence that is capable of generating new content on its own, by analyzing and understanding existing data.
deep learning
A sub-discipline of machine learning that imitates how humans learn or obtain certain types of knowledge.
Artificial Intelligence
is a branch of computer science focused on the theory and development of computer systems that perform tasks normally required by humans
Reinforcement learning
a method in which the training model learns from its environment by being rewarded for correct moves and punished for incorrect moves
