No student devices needed. Know more
30 questions
1. What is Machine Learning? (Choose 3 Answers)
Artificial Intelligence
Machine Learning
Data Statistics
Deep Learning
Deep Learning is a subfield of Machine Learning
TRUE
FALSE
Artificial Intelligence is superset of ________________ & _____________________
Machine Learning & Neural Networks
Machine Learning & Deep Learning
Deep Learning & Neural Networks
Which of the following statements are incorrect. (choose 3 option)
Reinforcement Learning is also an unsupervised learning
Having human in the loop is not necessary especially when the data are getting bigger because it will cost more and AI helps to be more cost-effective
Supervised learning is a complex method compared to unsupervised learning
Regression has continuous output variable that makes it a part of unsupervised learning
All of the above
Which of the statements are true
AI can recognize handwriting really well
AI can recognize words spoken in accents
AI can visually describe an image
AI can perform multiple robotic tasks at once
The steps: definition, value, stakeholders, priority & investment corresponds to which of the following stages of AI approach
Data
Business Case
Deploy & Measure
Active Learning & Tuning
What is the correct steps would you work to gauge the effectiveness of a machine learning model?
I – You make decision and apply necessary changes from the obtained metrics.
II – You use measures such as the F1 score, the accuracy, and the confusion matrix.
III – You implement a choice selection of performance metrics.
IV – You would split the dataset into training and test sets, or perhaps use cross-validation techniques to further segment the dataset into composite sets of training and test sets within the data.
I, II, III, IV
IV, III, II, I
I, III, II, IV
IV, II, III, I
Job: find a stock photo for collateral which is likely to drive conversion and sales
1) Gather examples of photos with high conversion
2) Gather examples of photos with low conversion
3) Identify visual criteria which are consistent with high converting photos
4) Log on to stock photo database
5) Generate appropriate search query
6) Enter search query
7) Apply filter to narrow results
8) Identify images with corresponding aesthetic qualities
9) Evaluate pricing options
10) Purchase image
Which sequential steps could use ML computer vision technology to accomplish the task?
1 - 3
2 - 5
5 - 8
7 - 10
Which methodology is recommended for Machine Learning project
Waterfall
Kanban
Scrum
Which of the following is NOT a requirement for building a dataset?
Dataset should be as complete as possible.
Dataset must contain enough information to represent all real-world cases.
Dataset must be already annotated with labels of interest.
What does garbage in, garbage out (GIGO) refer to?
Erroneous inputs will lead inevitably to false and misleading outputs.
Erroneous inputs will be rejected from being used in the model.
Erroneous inputs and outputs will be auto-corrected by the model.
What is the difference between Precision, and Recall?
Precision refers to how many relevant items are selected; Recall refers to among the selected items, how many are relevant.
Precision refers to sensitivity of the model; Recall refers to specificity of the model.
Precision refers to among the selected items, how many are relevant; Recall refers to how many relevant items are selected.
Which of the following is false?
To handle missing data, we can remove observations with missing data, or imputing the missing values based on other observations.
Outliers in data should always be removed.
We can label missing data as missing (categorical variable) or 0 (for numerical variable).
Which of the following are true?
Appen’s data annotation platform supports all kinds of raw data (text, video, audio, images).
Job templates are useful for building jobs in projects, as most of the steps in the job has been completed.
All of the above.
Which of the following about CML is false?
CML supports Python, R and Julia.
CML is derived from HTML.
CML was customised by Figure Eight to be used for creating HTML templates.
Assume that you want to make a face-mask detector for the grocery store, which detects a person not wearing a face mask in the store. What is the best data would you need to train this model?
100 images of people shopping in department store
5-hour CCTV video of the grocery store recorded when people didn’t wear face masks
10-hour CCTV video of the grocery store recorded when everyone wore face masks
5-hour CCTV video of the grocery store recorded when people didn’t wear face masks and 5-hour CCTV video of the grocery store recorded when everyone wore face masks
Which of the following bias is introduced by humans while generating the training data?
A. Model Bias
Annotation Bias
Data Bias
None of the above
Which of the following are business outcomes? Select all that apply?
Model accuracy
Generate Revenue
Improve Customer Experience
Model execution time
Choose the correct statement among the following :
Mockup is a wireframe, but with visual design (static)
Mock up is a prototype, but with interaction (dynamic)
Prototype is a mockup, but with interactions (dynamic)
Wireframe is structure and functional requirements (static)
What best describes Supervised Learning?
Supervised learning is a type of machine learning where inferences are drawn from datasets containing input data without labelled responses
Supervised learning is the process by which multiple models, such as classifiers, are strategically generated and combined to solve a particular problem
Supervised learning is a type of machine learning where a function is inferred from labelled training data
Supervised learning is defined as a Machine Learning method that is concerned with how software agents should take actions in an environment
Please explain the goal of A/B Testing. Choose all correct answers
A/B Testing is a statistical hypothesis testing meant for a randomized experiment with two variables, A and B.
A/B Testing is utilized to optimize the recall value of the model
A/B Testing is used to draw a conclusion whether a model is accurate or not
A/B Testing is a methodology to determine which given 2 models result the most efficient outcome
Choose all algorithm that is considered as supervised learning
Support Vector Machines
K-means clustering
Apriori Association
Neural Networks
Linear Regression
Suppose you are working on weather prediction, and you would like to predict whether or not it will be raining at 5pm tomorrow. You want to use a learning algorithm for this. Would you treat this as?
Association
Regression
Clustering
Classification
What do you understand by the Selection Bias?
Selection bias occurs when the person performing the data analysis wants to prove a predetermined assumption
Selection bias happens when there are extreme discrepancy among the data value
Selection bias is typically associated with research that doesn’t have a random selection of participants.
Selection bias is the moment when the model gives an over simplistic or overcomplicated picture of reality.
What are the differences between over-fitting and under-fitting? Choose all correct answers
A statistical model describes random error or noise instead of the underlying relationship is called over-fitting.
A statistical model describes random error or noise instead of the underlying relationship is called under-fitting.
Overfitting occurs when a statistical model or machine learning algorithm cannot capture the underlying trend of the data
Underfitting occurs when a statistical model or machine learning algorithm cannot capture the underlying trend of the data
What are Activation Functions in a Neural Network? Choose all correct answers
It finds the root mean square error of all inputted signal
It rescales the span of the input into range 0 to 1
It performs complex computations in the hidden layers and then transfers the result to the output layer.
It converts the linear input signals of a node into non-linear output to facilitate the learning of high order polynomials
What do you know about the convolutional term in convolutional neural network (CNN)? Choose all correct answers
It refers to a mathematical operation that produces a high dimensional tensor
It refers to the mathematical function that slides a filter over the input
The term convolution refers to the mathematical combination of three functions to produce the fourth function
It breaks down the input feature into smaller parts
What do Shared Weights mean in CNN? Choose the best answer
It calculates the feature´s weights and compares with other algorithms in order to find the best parameters.
Forcing the neurons of one layer to share weights, the forward pass becomes the equivalent of convolving a filter over the tensor to produce a new tensor.
Sharing weights among the features, make it easier and faster to CNN predict the correct image.
It means that CNN uses the weights of each feature in order to find the best model to make a prediction, sharing the results and returning the average.
What is the desired output of the CNN layer?
Kernel
Classifier
Decomposed input
Feature map
What type of cost function is used in a convolutional neural network?
It depends on the task.
Maximum Likelihood
RMSE
Categorical cross-entropy
Explore all questions with a free account