Search test library by skills or roles
⌘ K

Adaface Sample Deep Learning Questions

Here are some sample Deep Learning questions from our premium questions library (10273 non-googleable questions).

Skills

Others

Embedded Systems Agile/Scrum Cyber Security SAP ABAP SAP HANA SAP Fiori SAP GRC SAP QM SAP SuccessFactors Salesforce Developer Salesforce Administrator Boomi Dynamics 365 SCM Dynamics 365 Finance Dynamics 365 Customer Service Dynamics 365 Sales Dynamics 365 Customer Voice Dynamics 365 Commerce Dynamics AX Spark Adobe InDesign Oracle Hyperion Planning Customer Support ITIL Blue Prism SAS SCCM SSAS SSIS SSRS Citrix Google AdWords Weblogic Talend UML Human Resource Management Talent Acquisition Power Apps RPA CISCO CISCO DCIM French Apache NiFi Apache Pig TIBCO Spotfire TIBCO Business Studio TIBCO Administration TIBCO ActiveMatrix BPM TIBCO Hawk TIBCO Apache Tomcat Oracle Hyperion Financial Management Oracle Fusion Oracle AIA Oracle APEX Oracle BPM Oracle Apps Oracle Financial Apps Oracle OAF Oracle SOA SAP Hybris SAP BusinessObjects SAP BI SAP PowerDesigner SAP PowerBuilder SAP Leonardo SAP MDM SAP MDG SAP BW SAP SRM SAP UI5 SAP MM SAP HCM SAP BTP (SCP) SAP PI SAP PP SAP Basis SAP SD SAP WM SAP PS SAP BODS SAP DBM SAP Litmos SAP FI Loadrunner WPF WebFOCUS Ranorex Informatica Data Quality GDPR RabbitMQ Gradle Grunt EJB SnapLogic SharePoint Progress (OpenEdge) Informatica B2B Data Exchange Informatica MDM Joomla Ionic Liferay Sqoop Computer Literacy Communication Skills Technical Support Ecommerce Analytics Software Support Growth Marketing Marketing Analysis Digital Marketing Product Marketing SEO Outreach Market Research Jira German Italian Spanish Grammar & Vocabulary Listening Comprehension Reading Comprehension Sentence Structure
🧐 Question

Medium

Changed decision boundary
Solve
We have trained a model on a linearly separable training set to classify the data points into 2 sets (binary classification). Our intern recently labelled some new data points which are all correctly classified by the model. All of the new data points lie far away from the decision boundary. We added these new data points and re-trained our model- our decision boundary changed. Which of these models do you think we could be working with?
            The 2 data sources use SQL Server and have a 3-character CompanyCode column. Both data sources contain an ORDER BY clause to sort the data by CompanyCode in ascending order. 
            
            Teylor wants to make sure that the Merge Join transformation works without additional transformations. What would you recommend?
A: Perceptron
            B: SVM
            C: Logistic regression
            D: Guassion discriminant analysis

Medium

CNN Architecture Tuning
Convolutional Neural Networks
Hyperparameter Optimization
Solve
You are fine-tuning a Convolutional Neural Network (CNN) for image classification. The network architecture is as follows:
 image
The model is trained using the following parameters:
            
            - Batch size: 64
            - Learning rate: 0.001
            - Optimizer: Adam
            - Loss function: Categorical cross-entropy
            
            After several training epochs, you observe that the training accuracy is high, but the validation accuracy plateaus and is significantly lower. This suggests possible overfitting. Which of the following adjustments would most effectively mitigate this issue without overly compromising the model's performance?
A: Increase the batch size to 128
            B: Add dropout layers with a dropout rate of 0.5 after each MaxPooling2D layer
            C: Replace Adam optimizer with SGD (Stochastic Gradient Descent)
            D: Decrease the number of filters in each Conv2D layer by half
            E: Increase the learning rate to 0.01
            F: Reduce the size of the Dense layer to 64 units

Medium

CNN for Imbalanced Image Dataset
Convolutional Neural Networks
Imbalanced Datasets
Solve
You are fine-tuning a Convolutional Neural Network (CNN) for an image classification task where the dataset is highly imbalanced. The majority class comprises 70% of the data. The initial model setup and subsequent experiments yield the following observations:
            
            **Initial Setup:**
            
            - CNN architecture: 6 convolutional layers with increasing filter sizes, followed by 2 fully connected layers.
            - Activation function: ReLU
            - No class-weighting or data augmentation.
            - Results: High overall accuracy, but poor precision and recall for minority classes.
            
            **Experiment 1:**
            
            - Changes: Implement class-weighting to penalize mistakes on minority classes more heavily.
            - Results: Improved precision and recall for minority classes, but overall accuracy slightly decreased.
            
            **Experiment 2:**
            
            - Changes: Add dropout layers with a rate of 0.5 after each convolutional layer.
            - Results: Overall accuracy decreased, and no significant change in precision and recall for minority classes.
            
            Given these outcomes, what is the most effective strategy to further improve the model's performance specifically for the minority classes without compromising the overall accuracy?
A: Increase the dropout rate to 0.7
            B: Further fine-tune class-weighting parameters
            C: Increase the number of filters in the convolutional layers
            D: Add batch normalization layers after each convolutional layer
            E: Use a different activation function like LeakyReLU
            F: Implement more aggressive data augmentation on the minority class
🧐 Question🔧 Skill

Medium

Changed decision boundary

2 mins

Deep Learning
Solve

Medium

CNN Architecture Tuning
Convolutional Neural Networks
Hyperparameter Optimization

3 mins

Deep Learning
Solve

Medium

CNN for Imbalanced Image Dataset
Convolutional Neural Networks
Imbalanced Datasets

3 mins

Deep Learning
Solve
🧐 Question🔧 Skill💪 Difficulty⌛ Time
Changed decision boundary
Deep Learning
Medium2 mins
Solve
CNN Architecture Tuning
Convolutional Neural Networks
Hyperparameter Optimization
Deep Learning
Medium3 mins
Solve
CNN for Imbalanced Image Dataset
Convolutional Neural Networks
Imbalanced Datasets
Deep Learning
Medium3 mins
Solve

Trusted by recruitment teams in enterprises globally

Amazon Morgan Stanley Vodafone United Nations HCL PayPal Bosch WeWork Optimum Solutions Deloitte Microsoft NCS Doubtnut Sokrati J&T Express Capegemini

We evaluated several of their competitors and found Adaface to be the most compelling. Great library of questions that are designed to test for fit rather than memorization of algorithms.


Swayam Narain, CTO, Affable

hashtag image heart icon Swayam
customers across world
Join 1200+ companies in 75+ countries.
Try the most candidate friendly skills assessment tool today.
g2 badges
Ready to streamline your recruitment efforts with Adaface?
Ready to streamline your recruitment efforts with Adaface?
logo
40 min tests.
No trick questions.
Accurate shortlisting.
ada
Ada
● Online
Previous
Score: NA
Next
✖️