ML/AI Essentials: From Core Concepts to Practical Use Cases

In Natural Language Processing (NLP), what is the task of Named Entity Recognition (NER)?

• Translating text from one language to another

• Identifying and classifying named entities in text into categories like people, organizations, and locations, etc

• Summarizing long documents

• Generating random sentences

What is a common use of computer vision technology? 

• Editing documents

• Analyzing visual data from cameras or images

• Compiling software code

• Managing network traffic

What is the purpose of Optical Character Recognition (OCR)?

• To translate spoken language into text

• To convert different types of documents, such as scanned paper documents or PDFs, into editable and searchable data

• To enhance the resolution of digital images

• To manage and organize digital files

Which of the following is a common application of machine learning?

• Weather forecasting

• Creating web pages

• Word processing

• Spreadsheet calculations

What is the difference between supervised and unsupervised learning?

• Supervised learning does not require data, while unsupervised learning does

• Supervised learning requires labeled data, while unsupervised learning does not

• Supervised learning is used for clustering, while unsupervised learning is used for regression

• Both are the same

Which of the following is an example of a classification problem?

• Predicting the temperature for tomorrow

• Determining if an email is spam or not

• Estimating the price of a house

• Calculating the sum of two numbers

Why is it important to split data into training and test sets in machine learning?

• To ensure the model can generalize well to new, unseen data

• To reduce the size of the dataset

• To make data processing faster

• To avoid data redundancy

What does the term 'overfitting' mean in machine learning?

• A model that performs well on new data but poorly on training data

• A model that is too simple for the data

• A model that performs well on training data but poorly on new data

• A model that cannot be trained

When building a machine learning model, what is the primary purpose of hyperparameter tuning? 

• To improve the model's performance by optimizing settings that are not learned from the data

• To increase the size of the dataset

• To decrease the computational cost of training

• To ensure the model overfits the training data

In a confusion matrix, what does the term 'False Positive' (FP) refer to?

• An instance where the model incorrectly predicts a positive class

• An instance where the model correctly predicts a positive class

• An instance where the model incorrectly predicts a negative class

• An instance where the model correctly predicts a negative class