Oracle 1z0-1122-23 Oracle Cloud Infrastructure 2023 AI Foundations Associate Exam Practice Test

 Prompt engineering is the art of designing natural language instructions or queries that can elicit the desired response from a large language model. Prompt engineering does not modify the model parameters or architecture, but rather relies on the model’s existing knowledge and capabilities. Prompt engineering can be used to perform various tasks such as text generation, sentiment analysis, and code completion, by providing the model with the appropriate context, format, and constraints67. Prompt engineering is also known as zero-shot learning or query-based learning. References: [2211.01910] Large Language Models Are Human-Level Prompt Engineers](https://arxiv.org/abs/2211.01910),  A developer’s guide to prompt engineering and LLMs - The GitHub Blog

Supervised learning is a type of machine learning that uses labeled data sets to train algorithms that can classify data or predict outcomes. Labeled data sets are data sets that have both input features and output labels for each instance. For example, a labeled data set for image classification would have images as input features and the corresponding categories (such as dog, cat, bird, etc.) as output labels. Supervised learning algorithms learn the relationship between the input features and the output labels from the training data set and then use that relationship to make predictions on new or unseen data. Supervised learning can be divided into two subtypes: classification and regression. Classification is the task of assigning discrete categories to data instances, such as spam or not spam for emails. Regression is the task of predicting continuous values for data instances, such as house prices or stock prices. References: : Oracle Cloud Infrastructure AI - Machine Learning Concepts, What is Supervised Learning? | IBM

The attention mechanism in the Transformer architecture is a technique that allows the model to focus on the most relevant parts of the input and output sequences. It computes a weighted sum of the input or output embeddings, where the weights indicate how much each word contributes to the representation of the current word. The attention mechanism helps the model capture the long-range dependencies and the semantic relationships between words in a sequence12. References: The Transformer Attention Mechanism - MachineLearningMastery.com, Attention Mechanism in the Transformers Model - Baeldung

Large language models (LLMs) are a class of deep learning models that can recognize and generate natural language, among other tasks. LLMs are trained on huge sets of text data, learning grammar, semantics, and context. LLMs use the Transformer architecture, which relies on self-attention to process and understand the input and output sequences. LLMs can perform various natural language processing and understanding tasks based on the input provided, such as text summarization, question answering, text generation, and more34. Traditional machine learning models, on the other hand, are usually trained with specific statistical algorithms that deliver pre-defined outcomes. They often require labeled data and feature engineering, and they are not as flexible and adaptable as LLMs5. References: What are LLMs, and how are they used in generative AI?, An Introduction to LLMOps: Operationalizing and Managing Large Language Models using Azure ML, An Introduction to Large Language Models (LLMs): How It Got … - Labellerr

Oracle Cloud Infrastructure Document Understanding service is a cloud-based AI service for automating data extraction from documents. It can process various types of documents, such as invoices, receipts, contracts, forms, etc., and extract key information fields from them using optical character recognition (OCR) and natural language understanding (NLU) techniques. It can also provide confidence scores for each extracted field and enable human verification if needed. By using this service, businesses can reduce manual efforts, improve accuracy, and accelerate workflows that involve document processing. Some of the use cases for Oracle Cloud Infrastructure Document Understanding service are:

• Invoice Processing: Extract invoice details, such as invoice number, date, amount, vendor name, etc., and validate them against purchase orders or contracts.
• Contract Analysis: Extract contract terms, such as parties, duration, clauses, obligations, etc., and compare them with standard templates or policies.
• Form Processing: Extract form fields, such as name, address, phone number, email, etc., and populate them into databases or applications. References: : [Document Understanding Overview - Oracle], [AI Document Understanding at Scale | Oracle]

Unsupervised learning is a type of machine learning that is used to understand relationships within data and is not focused on making predictions or classifications. Unsupervised learning algorithms work with unlabeled data, which means the data does not have predefined categories or outcomes. The goal of unsupervised learning is to discover hidden patterns, structures, or features in the data that can provide valuable insights or reduce complexity. Some of the common techniques and applications of unsupervised learning are:

• Clustering: Grouping similar data points together based on their attributes or distances. For example, clustering can be used to segment customers based on their preferences, behavior, or demographics.
• Dimensionality reduction: Reducing the number of variables or features in a dataset while preserving the essential information. For example, dimensionality reduction can be used to compress images, remove noise, or visualize high-dimensional data in lower dimensions.
• Anomaly detection: Identifying outliers or abnormal data points that deviate from the normal distribution or behavior of the data. For example, anomaly detection can be used to detect fraud, network intrusion, or system failure.
• Association rule mining: Finding rules that describe how variables or items are related or co-occur in a dataset. For example, association rule mining can be used to discover frequent itemsets in market basket analysis or recommend products based on purchase history. References: : Unsupervised learning - Wikipedia, What is Unsupervised Learning? | IBM

Machine learning is a branch of artificial intelligence that enables computers to learn from data and experience without being explicitly programmed. Machine learning algorithms can adapt to new data and situations and improve their performance over time2. References: Artificial Intelligence (AI) | Oracle

Large language models are trained on massive amounts of data to capture the complexity and diversity of natural language. Larger model sizes mean more parameters, which enable the model to learn more patterns and nuances from the data. Larger models also tend to generalize better to new tasks and domains. However, larger models also require more computational resources, data quality, and data size to train and deploy. Therefore, large language models handle the trade-off by prioritizing larger model sizes to achieve better performance, while using various techniques to optimize the training and inference efficiency4. References: Artificial Intelligence (AI) | Oracle

Computer Vision is an AI domain that is associated with tasks such as recognizing faces in images and classifying objects. Computer vision is a field of artificial intelligence that enables computers and systems to derive meaningful information from digital images, videos, and other visual inputs, and to take actions or make recommendations based on that information. Computer vision works by applying machine learning and deep learning models to visual data, such as pixels, colors, shapes, textures, etc., and extracting features and patterns that can be used for various purposes. Some of the common techniques and applications of computer vision are:

• Face recognition: Identifying or verifying the identity of a person based on their facial features.
• Object detection: Locating and labeling objects of interest in an image or a video.
• Object recognition: Classifying objects into predefined categories, such as animals, vehicles, fruits, etc.
• Scene understanding: Analyzing the context and semantics of a visual scene, such as the location, time, weather, activity, etc.
• Image segmentation: Partitioning an image into multiple regions that share similar characteristics, such as color, texture, shape, etc.
• Image enhancement: Improving the quality or appearance of an image by applying filters, transformations, or corrections.
• Image generation: Creating realistic or stylized images from scratch or based on some input data, such as sketches, captions, or attributes. References: : What is Computer Vision? | IBM, Computer vision - Wikipedia