Which of the following techniques could allow Google’s Gmail to identify spam or irrelevant emails in the inbox?ClassificationRegression Traditional ProgrammingClustering

Question 2 (1 point) AI programs are programs that can Question 2 options: learn the same way humans learn sense, reason, act, and adapt always do what humans cannot do magically solve problems Question 3 (1 point) Which of the following techniques could allow Google's Gmail to identify spam or irrelevant emails in the inbox? Question 3 options: Regression Classification Traditional Programming Clustering Question 4 (1 point) Which of the following describes the AI/Machine Learning Process in the right sequence? Question 4 options: Deployment->Discovery->Learning->Problem Statement Learning->Discovery->Problem Statement->Deployment Problem Statement->Discovery->Learning->Deployment Discovery->Problem Statement->Deployment->Learning Question 5 (1 point) Which of the following is NOT an appropriate application of AI? Question 5 options: Collecting data from an online form Converting 'Singlish' speech to text Predictive Maintenance on HDB Lifts Diagnosis of chronic wounds Question 6 (1 point) Which of the following does NOT describe Supervised Learning in Artificial Intelligence (AI)? Question 6 options: When the computer algorithm iteratively makes predictions on a set of training data and is corrected by a teacher Finding the average of a large dataset of numbers Training a computer algorithm to recognize different models and make of cars with classified car images Training a computer algorithm to recognize cats with millions of classified animal pictures Question 7 (1 point) Which THREE (3) of the following are benefits that can be attributed to AI? Question 7 options: Prediction of the likelihood of survival from surgical procedures based on past surgical data gathered Devices (e.g. toys) that can hear and respond to human commands and/or conversations Automated design and development of computer programmes from scratch Watching movies to provide recommendations Question 8 (1 point) Which of the following is the field within AI used to aid computers in understanding and responding to human's natural language? Question 8 options: Natural Language Processing Text Classification Sentiment Analysis Question Answering Question 9 (1 point) What is the field or sub-field of study in AI that allows an AI application to automatically identify and tag the names of individuals to pictures they have taken? wefie Question 9 options: Supervised Learning Photo Sharing Augmented Reality Computer Vision Question 10 (1 point) Which of the following is the subset of mainstream AI that deals with the science of making computers or machines visually enabled? Question 10 options: Robotics Computer Vision Chatbots Natural Language Processing Question 11 (1 point) A technology company developed a language translation mobile application that allows a user to point his/her mobile phone camera at any text and the app can detect the language of the text and translate to another language of choice. See below. Google Translation Which field of AI has the company used to develop this mobile app? Question 11 options: Robotics Natural Language Processing Chatbots Reinforcement Learning Question 12 (1 point) Which of the following steps should be applied first during Natural Language Processing? Question 12 options: Word vector embedding Simplify the sentence Remove all the redundant words Remove all the digit characters Question 13 (1 point) Which of the following AI application is capable of monitoring patients with mobility issues to avoid fatal falls? Question 13 options: Speech to text conversion Pose estimation Face recognition Face Analysis Question 14 (1 point) Your boss provides you with several thousands of images of dogs and cats. She wants you to build a machine learning algorithm to identify which of the images are dogs and which are cats. Which of the following AI approaches is best suited? Question 14 options: Classification Regression Reinforcement Learning Question 15 (1 point) You are given a home loan dataset and asked to come up with a way to help companies determine the risk level (between 0.0 to 1.0) of potential borrowers. Which of the following AI approaches is best suited? Question 15 options: Classification Reinforcement Learning Supervised Learning Regression Question 16 (1 point) You are given a list of music subscription data for individuals. Your boss asks you to find a way to determine the renewal subscription rate in the future. Which of the following AI approaches is best suited? Question 16 options: Classification Linear Learning Anomaly Prevention Regression Question 17 (1 point) AI Engineers build AI models that can work well with Question 17 options: bad data messy data unbiased data missing data Question 18 (1 point) Decision made by AI should be Explainable, Transparent and Question 18 options: Meaningful Fair Effective Biased Question 19 (1 point) Which of the following AI applications is assessed to have the least severity and probability of harm that can arise from an AI-based decision? Question 19 options: An AI system to approve or reject bank loan application A medical diagnostic system used by doctor A facial recognition system used on mobile device An AI recommendation system used by online clothing store Question 20 (1 point) Which of the following datasets is less likely to cause data privacy infringement issue when it is used to train AI system? Question 20 options: Customer bank account data Images of animals from opensource repository Images of the human faces from Facebook Data scrapped from LinkedIn Profiles

Which of the following is used in Spam filtering in e-mails?

In which scenario would you use clustering?Answer areaTo classify emails as spam or not spamTo group customers based on purchasing behaviorTo predict the price of a houseTo detect fraud in financial transactions

Which of the following is/are correct way(s) to deal with spam? (i) Reply the spammer's email directly to complain. (ii) Forward the spam to every address on the email address book. (iii) Give up using email from now on, and communicate with traditional methods. (iv) Set up filter rules in email applications to filter out unwanted spam emails.

You are tasked with evaluating a simple binary classification model using a confusion matrix. The dataset involves predicting whether a given email is spam or not. To better understand the model's performance, you plan to extract specific metrics from the confusion matrix, specifically True Positives (TP) and False Positives (FP). Below is your initial code setup:from sklearn.metrics import confusion_matrixfrom sklearn.model_selection import train_test_splitfrom sklearn.ensemble import RandomForestClassifierfrom sklearn.datasets import make_classification# Generate synthetic binary classification dataX, y = make_classification(n_samples=1000, n_features=20, n_classes=2, random_state=42)# Split the dataX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)# Train a Random Forest classifierclassifier = RandomForestClassifier(random_state=42)classifier.fit(X_train, y_train)# Predict the test set resultsy_pred = classifier.predict(X_test)# Generate the confusion matrixcm = confusion_matrix(y_test, y_pred)# [Your code here] - Extract and print True Positives and False PositivesWhich snippet of code correctly extracts and prints the True Positives (TP) and False Positives (FP) from the confusion matrix?Which snippet of code correctly completes the setup to create a pipeline including PolynomialFeatures and LogisticRegression, fits it on the training data, and makes predictions?print("TP:", cm[2, 2])print("FP:", cm[1, 2])tp = cm[1, 1]fp = cm[0, 1]print("True Positives:", tp)print("False Positives:", fp)print("TP:", cm[1][1])print("FP:", cm[2][1])print("True Positives:", cm[2][2])print("False Positives:", cm[1][2])