Covariance Matrices<\/figcaption><\/figure>\nAll the others are embeddings:
Q 4. You are a junior Data Scientist and are working on a deep neural network model with Tensorflow to optimize the level of customer satisfaction for after-sales services with the goal of creating greater client loyalty.<\/strong>You are struggling with your model (learning rates, hidden layers and nodes selection) for optimizing processing and to let it converge in the fastest way.<\/strong>Which is your problem, in ML language?<\/strong><\/p>\nA. Cross-Validation
Correct Answer: C<\/strong>\nTraining data<\/strong> also called examples or records. It is the main input for model configuration and, in supervised learning, presents labels, that is the correct answers based on past experience. Input data is used to build the model but will not be part of the model.<\/li>\nParameters<\/strong> are Instead the variables to be found to solve the riddle. They are part of the final model and they make the difference among similar models of the same type.<\/li>\nHyperparameters<\/strong> are configuration variables that influence the training process itself: Learning rate, hidden layers number, number of epochs, regularization, batch size are all examples of hyperparameters.A is wrong<\/strong> because Cross Validation is related to the input data organization for training, test, and validationB is wrong<\/strong> because Regularization is related to feature management and overfittingD is wrong<\/strong> because drift management is when data distribution changes and you have to adjust the model<\/li>\n<\/ul>\n<\/span>Architect ML solutions<\/span><\/h3>\nQ 5. You work in a major banking institution. The Management has decided to rapidly launch a bank loan service, as the Government has created a series of “first home” facilities for the younger population.<\/strong>The goal is to carry out the automatic management of the required documents (certificates, origin documents, legal information) so that the practice can be built and verified automatically using the data and documents provided by customers and can be managed in a short time and with the minimum contribution of the scarce specialized personnel.<\/strong>Which of these GCP services can you use?<\/strong><\/p>\nA. Dialogflow
Correct answers: B<\/strong>Document AI<\/strong> is the perfect solution because it is a complete service for the automatic understanding of documents and their management.Dialogflow<\/figcaption><\/figure>\n\nA is wrong <\/b>because <\/span>Dialogflow <\/b>is for speech Dialogs, not written documents.<\/span><\/li>\nC is wrong <\/b>because <\/span>NLP <\/b>is integrated into Document AI.<\/span><\/li>\nD is wrong<\/b> because functions like <\/span>AutoML <\/b>are integrated into Document AI, too.<\/span><\/li>\n<\/ul>\nQ 6. You work for a large retail company. You are preparing a marketing model. The model will have to make predictions based on the historical and analytical data of the e-commerce site (analytics-360). In particular, customer loyalty and remarketing possibilities should be studied. You work on historical tabular data. You want to quickly create an optimal model, both from the point of view of the algorithm used and the tuning and life cycle of the model.<\/strong>What are the two best services you can use?<\/strong><\/p>\nA. AutoML Tables
Correct answers: A and C<\/strong>\nLinear<\/li>\n Feedforward deep neural network<\/li>\n Gradient Boosted Decision Tree<\/li>\n AdaNet<\/li>\n Ensembles of various model architectures Normalization<\/li>\n Encoding and embeddings for categorical features.<\/li>\n Timestamp columns management (important in our case)Vertex AI<\/figcaption><\/figure>\n\nB is wrong<\/strong> because AutoML Tables has additional automated feature engineering and is integrated into Vertex AI.<\/li>\nD is wrong<\/strong> because GKE doesn\u2019t supply all the ML features of Vertex AI. It is an advanced K8s managed environment.<\/li>\n<\/ul>\nQ 7. Your company operates an innovative auction site for furniture from all times. You have to create a series of ML models that allow you, starting from the photos, to establish the period, style and type of the piece of furniture depicted.<\/strong>Furthermore, the model must be able to determine whether the furniture is interesting and require it to be subject to a more detailed estimate. You want Google Cloud to help you reach this ambitious goal faster.<\/strong>Which of the following services do you think is the most suitable?<\/strong>A. AutoML Vision Edge
Correct Answer: D<\/strong>Vision AI<\/strong> uses pre-trained models trained by Google. This is powerful, but not enough.AutoML Vision<\/strong> lets you train models to classify your images with your own characteristics and labels. So, you can tailor your work as you want.A is wrong<\/strong> because AutoML Vision Edge<\/strong> is for local devices.C is wrong<\/strong> because Video AI<\/strong> manages videos, not pictures. It can extract metadata from any streaming video, get insights in a far shorter time, and let trigger events.<\/p>\nML model Deployed<\/figcaption><\/figure>\nQ 8. You are using an AI Platform, and you are working with a series of demanding training jobs. So, you want to use TPUs instead of CPUs. You are not using Docker images or custom containers.<\/strong>What is the simplest configuration to indicate if you do not have particular needs to customize in the YAML configuration file?<\/strong><\/p>\nA. Use scale-tier to BASIC_TPU
Correct Answer: A<\/strong>B, C and D are wrong<\/strong> because it is not the easiest way. Moreover, workerType, parameterServerType, evaluatorType, workerCount, parameterServerCount, and evaluatorCount for jobs use custom containers and for TensorFlow jobs.TensorFlow<\/figcaption><\/figure>\nQ 9. You work for an industrial company that wants to improve its quality system. It has developed its own deep neural network model with Tensorflow to identify the semi-finished products to be discarded with images taken from the production lines in the various production phases.<\/strong>You need to monitor the performance of your models and let them go faster.<\/strong>Which is the best solution that you can adopt?<\/strong><\/p>\nA. TFProfiler
Correct Answer: A<\/strong>Tensorflow 2<\/figcaption><\/figure>\n\nB is wrong<\/strong> because the TF function is a transformation tool used to make graphs out of your programs. It helps to create performant and portable models but is not a tool for optimization.<\/li>\nC is wrong<\/strong> because TF tracing lets you record TensorFlow Python operations in a graph.<\/li>\nD is wrong<\/strong> because TF debugging is for Debugger V2 and creates a log of debug information.<\/li>\nE is wrong<\/strong> because Checkpoints catch the value of all parameters in a serialized SavedModel format.<\/li>\n<\/ul>\nQ 10. Your team needs to create a model for managing security in restricted areas of a campus.<\/strong>Everything that happens in these areas is filmed and, instead of having a physical surveillance service, the videos must be managed by a model capable of intercepting unauthorized people and vehicles, especially at particular times.<\/strong>What are the GCP services that allow you to achieve all this with minimal effort?<\/strong>A. AI Infrastructure
Correct Answer: C<\/strong>In particular, AutoML Video Intelligence Object Tracking allows you to identify and locate particular entities of interest to you with your specific tags.<\/span><\/p>\nAutoML Video Intelligence Object Tracking<\/figcaption><\/figure>\n\nA is wrong <\/b>because AI Infrastructure allows you to manage hardware configurations for ML systems and in particular the processors used to accelerate machine learning workloads.<\/span><\/li>\nB is wrong<\/b> because Cloud Video Intelligence AI is a pre-configured and ready-to-use service, therefore not configurable for specific needs<\/span><\/li>\nD is wrong <\/b>because Vision A is for images and not video.<\/span><\/li>\n<\/ul>\nQ 11. With your team you have to decide the strategy for implementing an online forecasting model in production.<\/strong>This template needs to work with both a web interface as well as DialogFlow and Google Assistant and a lot of requests are expected.<\/strong>You are concerned that the final system is not efficient and scalable enough, and you are looking for the simplest and most managed GCP solution.<\/strong>Which of these can be the solution?<\/strong><\/p>\nA. AI Platform Prediction
Correct Answer: A<\/strong>machine learning models<\/figcaption><\/figure>\n\nB and C are wrong <\/b>because they are not managed services<\/span><\/li>\nD is wrong <\/b>because Kubeflow is not a managed service, it is used into AI Platforma and let you to deploy ML systems to various environments<\/span><\/li>\n<\/ul>\n<\/span>Design data preparation and processing systems<\/span><\/h3>\nQ 12. You work for a digital publishing website with an excellent technical and cultural level, where you have both famous authors and unknown experts who express ideas and insights.<\/strong>You, therefore, have an extremely demanding audience with strong interests that can be of various types.<\/strong>Users have a small set of articles that they can read for free every month. Then they need to sign up for a paid subscription.<\/strong>You have been asked to prepare an ML training model that processes user readings and article preferences. You need to predict trends and topics that users will prefer.<\/strong>But when you train your DNN with Tensorflow, your input data does not fit into RAM memory.<\/strong>What can you do in the simplest way?<\/strong><\/p>\nA. Use tf.data.Dataset
Correct Answer: A<\/strong>tf.data.Dataset<\/figcaption><\/figure>\n\nB is wrong <\/b>because it is far more complex, even if it is feasible.<\/span><\/li>\nC and D are wrong<\/b> because they work in real memory, so they don\u2019t solve the problem at all.<\/span><\/li>\n<\/ul>\nQ 13. You are working on a deep neural network model with Tensorflow. Your model is complex, and you work with very large datasets full of numbers.<\/strong>You want to increase performances. But you cannot use further resources.<\/strong>You are afraid that you are not going to deliver your project in time.<\/strong>Your mentor said to you that normalization could be a solution.<\/strong>Which of the following choices do you think is not for data normalization?<\/strong><\/p>\nA. Scaling to a range
Correct Answer: C<\/strong>z-test<\/strong> is not correct because it is a statistic that is used to prove if a sample mean belongs to a specific population. For example, it is used in medical trials to prove whether a new drug is effective or not.Scaling to a range<\/strong> converts numbers into a standard range ( 0 to 1 or -1 to 1).Feature Clipping<\/strong> caps all numbers outside a certain range.Log Scaling<\/strong> uses the logarithms instead of your values to change the shape. This is possible because the log function preserves monotonicity.Z-score<\/strong> is a variation of scaling: the resulting number is divided by the standard deviations. It is aimed at obtaining distributions with mean = 0 and std = 1.<\/p>\nNormalization Techniques<\/figcaption><\/figure>\n<\/span>Develop ML models<\/span><\/h3>\nQ 14. You need to develop and train a model capable of analyzing snapshots taken from a moving vehicle and detecting if obstacles arise. Your work environment is an AI Platform (currently Vertex AI).<\/strong>Which technique or algorithm do you think is best to use?<\/strong><\/p>\nA. TabNet algorithm with TensorFlow
Correct Answer: D<\/strong>TensorFlow Object Detection API<\/figcaption><\/figure>\n