12. Adversarial search is a type of search used in AI for which of the following tasks? a) Pattern recognition b) Speech recognition c) Decision making in competitive environments d) Natural language processing

Question 1Which of these terms best describes the type of AI used in today’s email spam filters, speech recognition, and other specific applications?1 pointArtificial General Intelligence (AGI)Artificial Narrow Intelligence (ANI)2.Question 2What do you call the commonly used AI technology for learning input (A) to output (B) mappings?1 pointUnsupervised learningReinforcement learningSupervised learningArtificial General Intelligence3.Question 3You want to use supervised learning to build a speech recognition system. The figure above suggests that in order for a neural network (deep learning) to achieve the best performance, you would ideally use: (Select all that apply)1 pointA large dataset (of audio files and the corresponding text transcript)A small dataset (of audio files and the corresponding text transcript)A large neural networkA small neural network4.Question 4The only way to acquire data for a supervised learning algorithm is to manually label it. I.e., given the input A, to ask a human to provide B.1 pointTrueFalse5.Question 5Which of these statements regarding data acquisition do you agree with?1 pointIt doesn’t matter how data is acquired. The more data, the better.Only structured data is valuable; AI cannot process unstructured data.It doesn’t help to give data to an AI team, because they can always produce whatever they need by themselves.Some types of data are more valuable than others; working with an AI team can help you figure out what data to acquire.6.Question 6You run a company that manufactures scooters. Which of the following are examples of unstructured data? (Select all that apply.)1 pointThe maximum speed of each of your scootersThe number of scooters sold per week over the past yearPictures of your scootersAudio files of the engine sound of your scooters7.Question 7Suppose you run a website that sells cat food. Which of these might be a good result from a data science project? (Select all that apply.)1 pointA slide deck presenting a plan on how to modify pricing in order to improve sales.A large dataset of images labeled as “Cat” and “Not Cat”A neural network that closely mimics how cats’ brains work.Insights into how to market cat food more effectively, depending on the breed of cat.8.Question 8Based on the terminology defined in Lesson 4 “The terminology of AI”, which of the following statements do you agree with? (Select all that apply.)1 pointThe terms “machine learning” and “data science” are used almost interchangeably.Deep learning is a type of machine learning. (I.e., all deep learning algorithms are machine learning algorithms.)AI is a type of deep learning. (I.e., All AI algorithms are deep learning algorithms.)The terms “deep learning” and “neural network” are used almost interchangeably.9.Question 9Which of these do AI companies do well?1 pointStrategic data acquisitionInvest in unified data warehousesSpot automation opportunitiesAll of the above10.Question 10Say you want to input a picture of a person’s face (A), and output whether or not they are smiling (B). Because this is a task that most humans can do in less than 1 second, supervised learning can probably learn this A-to-B mapping.1 pointTrueFalse

Which of these are examples of adversarial attacks on an AI system? (Select all that apply)1 pointSubtly modifying an audio clip to make a speech recognition system think someone said “Yes, authorized” when they actually said “No, reject.”Using AI to synthesize a fake video of a politician saying something they never actually said.Adding a sticker to a stop sign to make an AI system fail to detect it. Subtly changing an image to make an AI system mistakenly recognize a dog as a cat.

Machine learning is a subset of which of the following.(1 Point)Artificial intelligenceDeep learningData learningNone of the above

Out of the following, which is not an application of AI?a)Handwriting recognitionb)None of the mentionedc)Tasks involving decision makingd)Speech recognitione)Intelligent robots

Question 1Which of these terms best describes the type of AI used in today’s email spam filters, speech recognition, and other specific applications?1 pointArtificial Narrow Intelligence (ANI)Artificial General Intelligence (AGI)