Here you will get Introduction to Machine Learning in Production Coursera Quiz Answers
In the first course of Machine Learning Engineering for Production Specialization, you will identify the various components and design an ML production system end-to-end: project scoping, data needs, modeling strategies, and deployment constraints and requirements; and learn how to establish a model baseline, address concept drift, and prototype the process for developing, deploying, and continuously improving a productionized ML application
SKILLS YOU WILL GAIN
- Human-level Performance (HLP)
- Concept Drift
- Model baseline
- Project Scoping and Design
- ML Deployment Challenges
All Quiz Answers For Week 1
Quiz 1 >>The Machine Learning Project Lifecycle
Q1. Which of these are stages of the machine learning project lifecycle? Check all that apply.
Q2. Which of these is not an advantage of a typical edge deployment compared to a typical cloud deployment?
- Less network bandwidth needed
- Lower latency
- Can function even if network connection is down
- More computational power available
Q3. In the speech recognition example, what is the problem with some labelers transcribing audio as “Um, today’s weather” and others transcribing “Umm…, today’s weather”?
- We should not be transcribing “Umm.” The correct transcription, which serves the user’s needs better, is just “Today’s weather.
- The first is grammatically incorrect and we should use the second transcription.
- Either transcription is okay, but the inconsistency is problematic.
- The second is grammatically incorrect and we should use the first transcription.
Q4. After a system is deployed, monitoring and maintaining the system will help us handle cases of concept drift or data drift.
Q5. Which statement is a more accurate description of the full cycle of a machine learning project?
- It is a linear process, in which we move step-by-step from scoping to deployment. (That’s why we call it a cycle. Bicycles are only good at going forward, not backward.)
- It is an iterative process, where during a later stage we might go back to an earlier stage. (That’s why we call it a cycle–it’s a circular process.)
Quiz 2 >>Deployment
Q1. You’ve built a new system for making loan approval decisions. For now, its output is not used in any decision making process, and a human loan officer is solely responsible for deciding what loans to approve. But the system’s output is logged for analysis. What is this type of deployment called?
- Shadow mode deployment
- Red green deployment
- Canary deployment
- Blue green deployment
Q2. On a new social media platform, you’re rolling out a new anti-spam system to flag and hide spammy posts. Your team decides to roll out the anti-spam filter via a canary deployment, and roll it out to 1% of users initially. Which of these would you advocate?
- Monitor that 1% of users’ reaction, and if it goes well, flip the switch to send all traffic (100%) to the system.
- Use a plan to ramp up to more users at a fixed rate: 1% in the first week, 2% in second week, 4% in third, and so on, so that the rollout can be well planned and managed.
- Monitor that 1% of users’ reaction, and either gradually ramp up (if it’s going well) or rollback (if not)
- After a successful canary deployment, begin to implement a shadow mode deployment.
Q3. You’re building a healthcare screening system, where you input a patient’s symptoms, and for the easy cases (such as an obvious case of the common cold) the system will give a recommendation directly, and for the harder cases it will pass the case on to a team of in-house doctors who will form their own diagnosis independently. What degree of automation are you implementing in this example for patient care?
- Human only
- Full Automation
- Partial Automation
- Shadow mode
Q4. You have built and deployed an anti-spam system that inputs an email and outputs either 0 or 1 based on whether the email is spam. Which of these will result in either concept drift or data drift?
- Spammers trying to change the wording used in emails to get around your spam filter.
- Cloud computational costs going down, resulting in a lower cost to process each email received.
- Updating a monitoring dashboard to keep track of new metrics.
- None of these will result in either concept drift or data drift.
Q5. Which of these statements is a more accurate description of deployment?
- It is an iterative process, where you should expect to make multiple adjustments (such as metrics monitored using dashboards or percentage of traffic served) to work towards optimizing the system.
- Because deployment is a high stakes event, it’s critical to design the right system, so that immediately after launch it will immediately work reliably and scale effectively.
All Quiz Answers For Week 2
Quiz 1 >>Selecting and Training a Model
Q1. Which of these is a more accurate description of a data-centric approach to ML development?
- Holding the training data fixed, work to improve your neural network’s architecture to do well on the problem.
- Holding the neural network architecture fixed, work to improve the data to do well on the problem.
Q2. Say you have an algorithm that diagnoses illnesses from medical X-rays, and achieves high average test set accuracy. What can you now say with high confidence about this algorithm? Check all that apply.
- It does well even on rare classes of diseases.
- Its diagnoses are roughly equally accurate on all genders and ethnicities, so we are confident it is not biased against any gender or ethnicity.
- The system can be safely deployed in a healthcare setting.
- None of the above.
Q3. Which of these statements about establishing a baseline are accurate? Check all that apply.
- Human level performance (HLP) is generally more effective for establishing a baseline on unstructured data problems (such as images and audio) than structured data problems
- Open-source software should not be used to establish a baseline, since the performance of a good open source implementation might be too good and thus too hard to beat.
- For unstructured data problems, using human-level performance as the baseline can give an estimate of the irreducible error/Bayes error and what performance is reasonable to achieve.
- It can be established based on an older ML system
Q4. On a speech recognition problem, say you run the sanity-check test of trying to overfit a single training example. You pick a clearly articulated clip of someone saying “Today’s weather”, and the algorithm fails to fit even this single audio clip, and outputs “______”. What should you do?
- Train the algorithm on a larger dataset to help it to fit the data better.
- Use data augmentation on this one audio clip to make sure the algorithm hears a variety of examples of “today’s weather” to fit this phrase better.
- Debug the code/algorithm/hyperparameters to make it pass this sanity-check test first, before moving to larger datasets.
- Create a training set of this example repeated 100 times to force the algorithm to learn to fit this example well.
Quiz 2 >>Modeling challenges
Q1. You are working on a binary classification ML algorithm that detects whether a patient has a specific disease. In your dataset, 98% of the training examples (patients) don’t have the disease, so the dataset is very skewed. Accuracy on both positive and negative classes is important. You read a research paper claiming to have developed a system that achieves 95% on ____ metric. What metric would give you the most confidence they’ve built a useful and non-trivial system? (Select one)
- F1 score
Q2. On the previous problem above with 98% negative examples, if your algorithm is print(“1”) (i.e., it says everyone has the disease). Which of these statements is true?
- The algorithm achieves 100% recall.
- The algorithm achieves 100% precision.
- The algorithm achieves 0% precision.
- The algorithm achieves 0% recall.
Q3. True or False? During error analysis, each example should only be assigned one tag. For example, in a speech recognition application you may have the tags: “car noise”, “people noise” and “low bandwidth”. If you encounter an example with both car noise and low bandwidth audio, you should use your judgement to assign just one of these two tags rather than apply both tags.
Q4. You are building a visual inspection system. Error analysis finds:
|Type of defect||Accuracy||HLP||% of data|
Based on this, what is the more promising type of defect to work on?
- Discoloration, because the algorithm’s accuracy is lower and thus there’s more room for improvement.
- Discoloration, because HLP is lower which suggests this is therefore the harder problem that thus needs more attention.
- Scratch defects, because the gap to HLP is higher and thus there’s more room for improvement.
- Work on both classes equally because they are each 50% of the data.
Q5. You’re considering applying data augmentation to a phone visual inspection problem. Which of the following statements are true about data augmentation? (Select all that apply)
- Data augmentation should try to generate more examples in the parts of the input space where the algorithm is already doing well and there’s no need for improvement.
- Data augmentation should distort the input sufficiently to make sure they are hard to classify by humans as well.
- GANs can be used for data augmentation.
- Data augmentation should try to generate more examples in the parts of the input space where you’d like to see improvement in the algorithm’s performance.
All Quiz Answers For week 3
Quiz >>Data Stage of the ML Production Lifecycl
Q1. Which of these statements do you agree with regarding structured vs. unstructured data problems?
- It is generally easier for humans to label data and to apply data augmentation on unstructured data than structured data.
- It is generally easier for humans to label data and to apply data augmentation on structured data than unstructured data.
- It is generally easier for humans to label data on unstructured data, and easier to apply data augmentation on structured data.
- It is generally easier for humans to label data on structured data, and easier to apply data augmentation on unstructured data.
Q2. Take speech recognition. Some labelers transcribe with “…” (as in, “Um… today’s weather”) whereas others do so with commas “,”. Human-level performance (HLP) is measured according to how well one transcriber agrees with another. You work with the team and get everyone to consistently use commas “,”. What effect will this have on HLP?
- HLP will decrease.
- HLP will increase.
- HLP will stay the same.
Q3. Take a phone visual inspection problem. Suppose even a human inspector looking at an image cannot tell if there is a scratch. If however the same inspector were to look at the phone directly (rather than an image of the phone) then they can clearly tell if there is a scratch. Your goal is to build a system that gives accurate inspection decisions for the factory (not publish a paper). What would you do?
- Try to improve the consistency of the labels, y.
- Get a big dataset of many training examples, since this is a challenging problem that will require a big dataset to do well on.
- Carefully measure HLP on this problem (which will be low) to make sure the algorithm can match HLP.
- Try to improve their imaging (camera/lighting) system to improve the quality or clarity of the input images, x.
Q4. You are building a system to detect cats. You ask labelers to please “use bounding boxes to indicate the position of cats.” Different labelers label as follows:
What is the most likely cause of this?
- Labelers have not had enough coffee.
- Ambiguous labeling instructions.
- Lazy labelers.
- That this should have been posed as a segmentation rather than a detection task.
Q5. You are building a visual inspection system. HLP is measured according to how well one inspector agrees with another. Error analysis finds:
|Type of defect||Accuracy||HLP||% of data|
You decide that it might be worth checking for label consistency on both scratch and discoloration defects. If you had to pick one to start with, which would you pick?
- It is more promising to check (and potentially improve) label consistency on scratch defects than discoloration defects, since HLP is higher on scratch defects and thus it’s more reasonable to expect high consistency.
- It is more promising to check (and potentially improve) label consistency on discoloration defects than scratch defects. Since HLP is lower on discoloration, it’s possible that there might be ambiguous labelling instructions that is affecting HLP.
Q6. To implement the data iteration loop effectively, the key is to take all the time that’s needed to construct the right dataset first, so that all development can be done on that dataset without needing to spend time to update the data.
Q7. You have a data pipeline for product recommendations that (i) cleans data by removing duplicate entries and spam, (ii) makes predictions. An engineering team improves the system used for step (i). If the trained model for step (ii) remains the same, what can we confidently conclude about the performance of the overall system?
- It will definitely improve since the data is now more clean.
- It’s not possible to say – it may perform better or worse.
- It will get worse because stage (ii) is now experiencing data/concept drift.
- It will get worse because changing an earlier stage in a data pipeline always results in worse performance of the later stages.
Q8. What is the primary goal of building a PoC (proof of concept) system?
- To build a robust deployment system.
- To collect sufficient data to build a robusts system for deployment.
- To select the most appropriate ML architecture for a task.
- To check feasibility and help decide if an application is workable and worth deploying.
Q9. MLOps tools can store meta-data to keep track of data provenance and lineage. What do the terms data provenance and lineage mean?
- Data provenance refers to where the data comes from, and data lineage the sequence of processing steps applied to it.
- Data provenance refers the input x, and data lineage refers to the output y.
- Data provenance refers to the sequence of processing steps applied to a dataset, and data lineage refers to where the data comes from.
- Data provenance refers data pipeline, and data lineage refers to the age of the data (i.e., how recently was it collected).
Q10. You are working on phone visual inspection, where the task is to use an input image, x, to classify defects, y. You have stored meta-data for your entire ML system, such as which factory each image came from. Which of the following are reasonable uses of meta-data?
- As an alternative to having to comment your code.
- To suggest tags or to generate insights during error analysis.
- As another input provided to human labelers (in addition to the image x) to boost HLP.
- Keeping track of data provenance and lineage.
I hope this article would be helpful for you to find all the coursera Quiz Answers.
If this article helped you learn something new for free, let others know about this,
Want to learn more? Check out another course.
<<<Check out another Coursera Quiz Answers >>>
Interpersonal Communication For Engineering Leaders Coursera Quiz Answers
Industrial Biotechnology Coursera Quiz Answers
Functional Programming Principles In Scala Coursera Quiz Answers
Exploratory Data Analysis Coursera Quiz Answers
Get More Solutions :
Linkedinn Assessments Solutions
Use “Ctrl+F” To Find Any Questions Answer. & For Mobile User, You Just Need To Click On Three dots In Your Browser & You Will Get A “Find” Option There. Use These Option to Get Any Random Questions Answer.How many hours is machine learning coursera? ›
Coursera's Machine Learning by Stanford University Course
There are 11 weeks of content, and it takes about 61 hours to complete this course. Coursera's ML by Stanford University course covers skills like: Convolutional neural networks.
The Machine Learning Engineering for Production (MLOps) Specialization covers how to conceptualize, build, and maintain integrated systems that continuously operate in production. In striking contrast with standard machine learning modeling, production systems need to handle relentless evolving data.Why is machine learning exciting? ›
Machine Learning is so exciting because of its general applications. With a good grip in ML, we can solve many problems, faster, more efficiently, than we were able to solve a few years back.What happens if I fail a Coursera quiz? ›
If you do not obtain the required passing grade on a quiz, you have two options: Option 1: You can immediately retake the quiz without review. Option 2: You can click “review chapter info” to go over course material again and then give the quiz another go.How many times can I attempt coursera quiz? ›
You can take the same quiz as many times as you want to.
You can start and finish one of these popular courses in under a day - for free! Check out the list below.Can I complete Coursera course in 7 days? ›
Yes you can finish your course well before time.Can I finish Coursera course in one month? ›
With all courses in subscription-based Specializations running at least monthly, you can complete a Specialization in as little as a month (if, for example, you're already familiar with some of the material), or over several months (if the topic is completely new to you).What are the 3 parts of machine learning? ›
- Representation: what the model looks like; how knowledge is represented.
- Evaluation: how good models are differentiated; how programs are evaluated.
- Optimization: the process for finding good models; how programs are generated.
- Data Collection. → The quantity & quality of your data dictate how accurate our model is. ...
- Data Preparation. → Wrangle data and prepare it for training. ...
- Choose a Model. ...
- Train the Model. ...
- Evaluate the Model. ...
- Parameter Tuning. ...
- Make Predictions.
The number one problem facing Machine Learning is the lack of good data. While enhancing algorithms often consumes most of the time of developers in AI, data quality is essential for the algorithms to function as intended.Why is Python so good for machine learning? ›
Due to its easier understandability by humans, it is easier to make models for machine learning. Furthermore, many coders say that Python is more intuitive than other programming languages. It is suitable for a collaborative implementation as and when multiple developers are involved.Why does Netflix use machine learning? ›
Not only was Netflix able to offer consumers easy-to-access and affordable content, they generated billions of data in the process. This newfound data allowed Netflix to utilize machine learning (ML) to offer a hyper-personalized experience for all users.Do employers take Coursera seriously? ›
Coursera certificates are different and are respected by employers and universities. This is because Coursera offers the highest quality when it comes to courses. Coursera courses are led by the top universities and companies that you could think of. This makes Coursera certificates and degrees legitimate and valuable.What happens if you get behind on Coursera? ›
There are no penalties for missing deadlines. If you fall behind in an on demand course, you can adjust the suggested deadlines, or turn them off. If you fall behind in a session-based course, you may need to transfer to the next session, but your record of completed assignments will transfer with you.Are Coursera deadlines strict? ›
Most Coursera courses have personalized deadlines that begin when you enroll in a course. There is no grade penalty for a missed deadline, so you can work at your own pace if you cannot or do not want to meet the suggested deadlines.Can I complete Coursera course in one week? ›
All Coursera courses have a suggested time commitment usually of between 4 and 10 weeks, committing a few hours of study a week. However, in most cases, you are not obliged to follow the recommended schedule and can study the courses at your own pace.Can I skip practice quizzes in Coursera? ›
Yes, you can skip over optional assignments in any course. If the assignment is not listed on your Grades page, it means the assignment is not graded. But, it is better to do all assignments, quizzes, etc.How fast can you finish Coursera? ›
|Specializations||Master a Skill||1-3 months|
|Professional Certificates||Get job ready for a career||4-7 months|
|Coursera Plus||Certified access to 90%+ of catalog||various|
|MasterTrack Certificates||Earn credit towards a degree||4-7 months|
Nothing. As long as you finish everything before the course ends, you can do the work at any time with no penalty.Can Coursera get you a job? ›
Coursera does not provide or guarantee job placement. So, take specializations and certificate programs that help you hone the skills you intend to showcase to employees. No, you can't get a job by simply taking a single Coursera course but you may be able to get a job by completing a professional certificate program.Which is the easiest courses in Coursera? ›
- AI For Everyone. DeepLearning.AI. ...
- What is Data Science? ...
- Hacking Exercise For Health. ...
- Python for Data Science, AI & Development. ...
- Stanford Introduction to Food and Health. ...
- First Step Korean. ...
- Fundamentals of Graphic Design. ...
- Design Thinking for Innovation.
Most employers are familiar with Coursera and the quality of education it provides. In fact, many employers see Coursera certificates as a valuable addition to a job seeker's skillset. Coursera certificates show that you're motivated to learn and that you're willing to invest in your own development.Are Coursera certificates worth anything? ›
A straightforward answer to this, Yes. The Coursera certificate adds value to your resume and will help you if you are looking for a promotion or job change. Coursera offers great courses from top educators and top universities that can help you get a job if you are an individual.Can I get certificate from Coursera without completing the course? ›
In order to get a Course Certificate, you must: Complete Name Verification. (Some courses in Degree or MasterTrack programs require ID Verification, which includes submitting a photo and verified ID) Pass all required assignments in the course, or meet the course passing threshold for a cumulative graded course.Can I take 2 Coursera courses at once? ›
Once subscribed, you can take as many courses and earn as many certificates as you would like for a single, all-inclusive price.Can I add Coursera certificate in my resume? ›
Add Coursera professional certificates to your resume
Offered by such world-class partners as Google, IBM, and Meta, Coursera's flexible, online professional certificates can help you get job-ready for such in-demand careers as project manager or data analyst.
Coursera provides accredited certificates that are recognised by employers. Coursera doesn't create its own learning material. However, it works alongside educational institutions, government agencies and top universities to facilitate its online courses.What are the 5 types of machine learning? ›
There are primarily three types of machine learning: Supervised, Unsupervised, and Reinforcement Learning. Let's explore and understand the different types of machine learning one by one.
There are two main types of machine learning models: machine learning classification (where the response belongs to a set of classes) and machine learning regression (where the response is continuous).What are the 2 types of machine learning techniques? ›
Machine learning uses two types of techniques: supervised learning, which trains a model on known input and output data so that it can predict future outputs, and unsupervised learning, which finds hidden patterns or intrinsic structures in input data.What are the three common machine learning problems? ›
Learning Problems. First, we will take a closer look at three main types of learning problems in machine learning: supervised, unsupervised, and reinforcement learning.What is the most important part of machine learning? ›
Training is the most important part of Machine Learning. Choose your features and hyper parameters carefully. Machines don't take decisions, people do. Data cleaning is the most important part of Machine Learning.What are the 3 types of machine learning algorithms? ›
Within machine learning, there are many kinds of algorithms. These can be divided into three main categories: supervised learning, unsupervised learning and reinforcement learning.What is the most important first step in a machine learning project? ›
The first step to successfully making a machine learning project is to understand the problem, solve it, and produce an outcome that meets your needs. Before starting your project, you must understand the problem, data, and context.What are the four types of machine learning algorithms? ›
- Supervised Learning.
- Unsupervised Learning.
- Semi-Supervised Learning.
- Reinforced Learning.
- Data Issues. #1 - Not Looking at the Data. #2 - Not Looking for Data Leakage.
- Modeling Issues. #3 - Developing to the Test Set. #4 - Not Looking at the Model. ...
- Process Issues. #6 - Not Qualifying the Use Case. #7 - Not Understanding the User.
- Ethical concerns. There are, of course, many advantages to trusting algorithms. ...
- Deterministic problems. ...
- Lack of Data. ...
- Lack of interpretability. ...
- Lack of reproducibility. ...
- With all its limitations, is ML worth using?
Python is easy to learn and easy to put in practice when compared to C++ which becomes harder as we advance through its features. Another advantage of Python is its libraries that allow us to write any functionality especially data analysis and machine learning. So popularity-wise Python scores over C++.
There's no wrong choice when it comes to learning Python or R. Both are in-demand skills and will allow you to perform just about any data analytics task you'll encounter. Which one is better for you will ultimately come down to your background, interests, and career goals.Is AI or Python better? ›
While machine learning and artificial intelligence are based on complex algorithms and workflows, Python, with its easy-to-write code, allows developers to focus on solving ML problems rather than technical nuances of the language. That's why many programmers consider Python to be more intuitive than other languages.Is machine learning GPU or CPU? ›
While CPUs can process many general tasks in a fast, sequential manner, GPUs use parallel computing to break down massively complex problems into multiple smaller simultaneous calculations. This makes them ideal for handling the massively distributed computational processes required for machine learning.How many algorithms does Netflix use? ›
This software is a key player in Netflix's success. The NRE is composed of multiple algorithms that filter content based on a user's profile. The system filters over 3,000+ titles using 1,300 recommendation clusters all based on an individual user's preferences.What coding is used for Netflix? ›
Python and Java, the preferred programming languages of Netflix.Can I skip practice quizzes in coursera? ›
Yes, you can skip over optional assignments in any course. If the assignment is not listed on your Grades page, it means the assignment is not graded. But, it is better to do all assignments, quizzes, etc.How do I pass an assignment on Coursera? ›
- Open the course you want to submit an assignment for.
- Click the Grades tab.
- Choose the assignment you want to submit work for.
- Read the instructions, then click My submission to submit your assignment.
- To save a draft of your assignment, click Save draft.
If students failed in peer review assignment they can re-submit the assignment to be graded again and If you have already completed peer reviews for other people's assignments, you won't need to do them again. And after passing the peer grade assignment you will get certificate of completion.Can you fail an assignment but pass the module? ›
Grades will vary from university and courses, but most of the time you don't have to re-sit an assignment to end up passing the module or even the year. Such as, if your averaged course mark is 40 or above, you can pass the module overall regardless of the failed piece of work.Can you fail an assignment and still pass the module? ›
If you've failed one piece of coursework or an exam, it may not be necessary to re-submit that element. If your marks for other module elements are high enough that your averaged course mark is 40 or above, you will pass the module overall regardless of the one failure.
Well, the answer is no. Google Classroom uses Google Forms to prepare quizzes and assessments, and the latter has no such functionality to track cheating. If schools or teachers wish to use a third party along with this platform, there are chances to track the cheating patterns.Is it possible to get answers from Google Forms? ›
Open your form in Google Forms > Click Responses > Click Question to view the answers by question. You can use the previous and next icons to navigate between questions or select a specific question from the dropdown list.