Deep Learning Online Test

The deep learning pre-employment test evaluates a candidate's understanding of core deep learning concepts like activation functions, backpropagation, RNNs & CNNs, learning rate, dropout, batch normalization, data processing pipelines, multi-layer perceptrons and data normalization. This test also focuses on their ability to apply deep learning algorithms to use cases like computer vision, image recognition, object detection, text classification etc.

Get started for free

Preview questions

Screen candidates with a 30 mins test

Test duration: 30 mins

Difficulty level: Moderate

Availability: Ready to use

Questions:

8 Machine Learning MCQs
8 Deep Learning MCQs

Covered skills:

Neural Networks

Data Normalization

Cost Functions and Activation Functions

Backpropagation

Neural Networks

Convolutional Neural Networks

Recurrent Neural Networks

Generative Adversarial Networks

Natural Language Processing

Computer Vision

Transfer Learning

Autoencoders

Optimization Algorithms

Get started for free

Preview questions

Use Adaface tests trusted by recruitment teams globally

Adaface is used by 1500+ businesses in 80 countries.

Adaface skill assessments measure on-the-job skills of candidates, providing employers with an accurate tool for screening potential hires.

Use the Deep Learning Test to shortlist qualified candidates

The Deep Learning Online Test helps recruiters and hiring managers identify qualified candidates from a pool of resumes, and helps in taking objective hiring decisions. It reduces the administrative overhead of interviewing too many candidates and saves time by filtering out unqualified candidates at the first step of the hiring process.

The test screens for the following skills that hiring managers look for in candidates:

Understanding and implementing neural networks
Applying data normalization techniques
Selecting appropriate cost functions and activation functions
Implementing backpropagation algorithm
Designing and evaluating convolutional neural networks
Developing recurrent neural networks
Creating generative adversarial networks
Applying natural language processing techniques
Implementing computer vision algorithms
Understanding and implementing transfer learning
Developing autoencoders
Optimizing deep learning models using optimization algorithms

Get started for free

Preview questions

Screen candidates with the highest quality questions

We have a very high focus on the quality of questions that test for on-the-job skills. Every question is non-googleable and we have a very high bar for the level of subject matter experts we onboard to create these questions. We have crawlers to check if any of the questions are leaked online. If/ when a question gets leaked, we get an alert. We change the question for you & let you know.

How we design questions

These are just a small sample from our library of 15,000+ questions. The actual questions on this Deep Learning Test will be non-googleable.

🧐 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: 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
Easy Gradient descent optimization Gradient Descent	Solve
You are working on a regression problem using a simple neural network. You want to optimize the model's weights using gradient descent with different learning rate schedules. Consider the following pseudo code for training the neural network: Which of the following learning rate schedules would most likely result in the fastest convergence without overshooting the optimal weights? A: Constant learning rate of 0.01 B: Exponential decay with initial learning rate of 0.1 and decay rate of 0.99 C: Exponential decay with initial learning rate of 0.01 and decay rate of 0.99 D: Step decay with initial learning rate of 0.1 and decay rate of 0.5 every 100 epochs E: Step decay with initial learning rate of 0.01 and decay rate of 0.5 every 100 epochs F: Constant learning rate of 0.1
Medium Less complex decision tree model Model Complexity Overfitting	Solve
You are given a dataset to solve a classification problem using a decision tree algorithm. You are concerned about overfitting and decide to implement pruning to control the model's complexity. Consider the following pseudo code for creating the decision tree model: Which of the following combinations of parameters would result in a less complex decision tree model, reducing the risk of overfitting? A: max_depth=5, min_samples_split=2, min_samples_leaf=1 B: max_depth=None, min_samples_split=5, min_samples_leaf=5 C: max_depth=3, min_samples_split=2, min_samples_leaf=1 D: max_depth=None, min_samples_split=2, min_samples_leaf=1 E: max_depth=3, min_samples_split=10, min_samples_leaf=10 F; max_depth=5, min_samples_split=5, min_samples_leaf=5
Easy n-gram generator	Solve
Our newest machine learning developer want to write a function to calculate the n-gram of any text. An N-gram means a sequence of N words. So for example, "black cats" is a 2-gram, "saw black cats" is a 3-gram etc. The 2-gram of the sentence "the big bad wolf fell down" would be [["the", "big"], ["big", "bad"], ["bad", "wolf"], ["wolf", "fell"], ["fell", "down"]]. Can you help them select the correct function for the same?
Easy Recommendation System Selection Recommender Systems Collaborative Filtering Content-Based Filtering	Solve
You are tasked with building a recommendation system for a newly launched e-commerce website. Given that the website is new, there is not much user interaction data available. Also, the items in the catalog have rich descriptions. Based on these requirements, which type of recommendation system approach would be the most suitable for this task?
Easy Sensitivity and Specificity Confusion Matrix Model Evaluation	Solve
You have trained a supervised learning model to classify customer reviews as either "positive" or "negative" based on a dataset with 10,000 samples and 35 features, including the review text, reviewer's name, and rating. The dataset is split into a 7,000-sample training set and a 3,000-sample test set. After training the model, you evaluate its performance using a confusion matrix on the test set, which shows the following results: Based on the confusion matrix, what are the sensitivity and specificity of the model?

	🧐 Question	🔧 Skill
	Medium Changed decision boundary	2 mins Deep Learning	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	3 mins Deep Learning	Solve
You are fine-tuning a Convolutional Neural Network (CNN) for image classification. The network architecture is as follows: 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	3 mins Deep Learning	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
	Easy Gradient descent optimization Gradient Descent	2 mins Machine Learning	Solve
You are working on a regression problem using a simple neural network. You want to optimize the model's weights using gradient descent with different learning rate schedules. Consider the following pseudo code for training the neural network: Which of the following learning rate schedules would most likely result in the fastest convergence without overshooting the optimal weights? A: Constant learning rate of 0.01 B: Exponential decay with initial learning rate of 0.1 and decay rate of 0.99 C: Exponential decay with initial learning rate of 0.01 and decay rate of 0.99 D: Step decay with initial learning rate of 0.1 and decay rate of 0.5 every 100 epochs E: Step decay with initial learning rate of 0.01 and decay rate of 0.5 every 100 epochs F: Constant learning rate of 0.1
	Medium Less complex decision tree model Model Complexity Overfitting	2 mins Machine Learning	Solve
You are given a dataset to solve a classification problem using a decision tree algorithm. You are concerned about overfitting and decide to implement pruning to control the model's complexity. Consider the following pseudo code for creating the decision tree model: Which of the following combinations of parameters would result in a less complex decision tree model, reducing the risk of overfitting? A: max_depth=5, min_samples_split=2, min_samples_leaf=1 B: max_depth=None, min_samples_split=5, min_samples_leaf=5 C: max_depth=3, min_samples_split=2, min_samples_leaf=1 D: max_depth=None, min_samples_split=2, min_samples_leaf=1 E: max_depth=3, min_samples_split=10, min_samples_leaf=10 F; max_depth=5, min_samples_split=5, min_samples_leaf=5
	Easy n-gram generator	2 mins Machine Learning	Solve
Our newest machine learning developer want to write a function to calculate the n-gram of any text. An N-gram means a sequence of N words. So for example, "black cats" is a 2-gram, "saw black cats" is a 3-gram etc. The 2-gram of the sentence "the big bad wolf fell down" would be [["the", "big"], ["big", "bad"], ["bad", "wolf"], ["wolf", "fell"], ["fell", "down"]]. Can you help them select the correct function for the same?
	Easy Recommendation System Selection Recommender Systems Collaborative Filtering Content-Based Filtering	2 mins Machine Learning	Solve
You are tasked with building a recommendation system for a newly launched e-commerce website. Given that the website is new, there is not much user interaction data available. Also, the items in the catalog have rich descriptions. Based on these requirements, which type of recommendation system approach would be the most suitable for this task?
	Easy Sensitivity and Specificity Confusion Matrix Model Evaluation	2 mins Machine Learning	Solve
You have trained a supervised learning model to classify customer reviews as either "positive" or "negative" based on a dataset with 10,000 samples and 35 features, including the review text, reviewer's name, and rating. The dataset is split into a 7,000-sample training set and a 3,000-sample test set. After training the model, you evaluate its performance using a confusion matrix on the test set, which shows the following results: Based on the confusion matrix, what are the sensitivity and specificity of the model?

	🧐 Question	🔧 Skill	💪 Difficulty	⌛ Time
	Changed decision boundary	Deep Learning	Medium	2 mins	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
	CNN Architecture Tuning Convolutional Neural Networks Hyperparameter Optimization	Deep Learning	Medium	3 mins	Solve
You are fine-tuning a Convolutional Neural Network (CNN) for image classification. The network architecture is as follows: 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
	CNN for Imbalanced Image Dataset Convolutional Neural Networks Imbalanced Datasets	Deep Learning	Medium	3 mins	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
	Gradient descent optimization Gradient Descent	Machine Learning	Easy	2 mins	Solve
You are working on a regression problem using a simple neural network. You want to optimize the model's weights using gradient descent with different learning rate schedules. Consider the following pseudo code for training the neural network: Which of the following learning rate schedules would most likely result in the fastest convergence without overshooting the optimal weights? A: Constant learning rate of 0.01 B: Exponential decay with initial learning rate of 0.1 and decay rate of 0.99 C: Exponential decay with initial learning rate of 0.01 and decay rate of 0.99 D: Step decay with initial learning rate of 0.1 and decay rate of 0.5 every 100 epochs E: Step decay with initial learning rate of 0.01 and decay rate of 0.5 every 100 epochs F: Constant learning rate of 0.1
	Less complex decision tree model Model Complexity Overfitting	Machine Learning	Medium	2 mins	Solve
You are given a dataset to solve a classification problem using a decision tree algorithm. You are concerned about overfitting and decide to implement pruning to control the model's complexity. Consider the following pseudo code for creating the decision tree model: Which of the following combinations of parameters would result in a less complex decision tree model, reducing the risk of overfitting? A: max_depth=5, min_samples_split=2, min_samples_leaf=1 B: max_depth=None, min_samples_split=5, min_samples_leaf=5 C: max_depth=3, min_samples_split=2, min_samples_leaf=1 D: max_depth=None, min_samples_split=2, min_samples_leaf=1 E: max_depth=3, min_samples_split=10, min_samples_leaf=10 F; max_depth=5, min_samples_split=5, min_samples_leaf=5
	n-gram generator	Machine Learning	Easy	2 mins	Solve
Our newest machine learning developer want to write a function to calculate the n-gram of any text. An N-gram means a sequence of N words. So for example, "black cats" is a 2-gram, "saw black cats" is a 3-gram etc. The 2-gram of the sentence "the big bad wolf fell down" would be [["the", "big"], ["big", "bad"], ["bad", "wolf"], ["wolf", "fell"], ["fell", "down"]]. Can you help them select the correct function for the same?
	Recommendation System Selection Recommender Systems Collaborative Filtering Content-Based Filtering	Machine Learning	Easy	2 mins	Solve
You are tasked with building a recommendation system for a newly launched e-commerce website. Given that the website is new, there is not much user interaction data available. Also, the items in the catalog have rich descriptions. Based on these requirements, which type of recommendation system approach would be the most suitable for this task?
	Sensitivity and Specificity Confusion Matrix Model Evaluation	Machine Learning	Easy	2 mins	Solve
You have trained a supervised learning model to classify customer reviews as either "positive" or "negative" based on a dataset with 10,000 samples and 35 features, including the review text, reviewer's name, and rating. The dataset is split into a 7,000-sample training set and a 3,000-sample test set. After training the model, you evaluate its performance using a confusion matrix on the test set, which shows the following results: Based on the confusion matrix, what are the sensitivity and specificity of the model?

Test candidates on core Deep Learning Hiring Test topics

Neural Networks: Neural networks are a computational model inspired by biological neural networks. They are composed of layers of interconnected nodes, or artificial neurons, that process and transmit information using weighted inputs. They are measured in this test to assess the understanding of fundamental concepts in deep learning.

Data Normalization: Data normalization is a technique used to standardize the range of data values. It involves transforming the data to have a consistent scale, typically between 0 and 1. This skill is measured in this test to evaluate the ability to preprocess data effectively, which is crucial for training accurate neural networks.

Cost Functions and Activation Functions: Cost functions are used to measure the difference between predicted and actual values in a neural network, guiding the learning process. Activation functions introduce non-linearity to the output of each neuron in a neural network, enabling complex computations. This skill is measured in this test to assess the knowledge of selecting appropriate cost and activation functions for different tasks.

Backpropagation: Backpropagation is a key algorithm for training neural networks. It calculates the gradients of the network's parameters with respect to the loss, allowing for the adjustment of weights in previous layers. This skill is measured in this test to gauge the understanding of how gradients propagate backward through a neural network for efficient learning.

Convolutional Neural Networks: Convolutional neural networks (CNNs) are deep learning models specifically designed for processing structured grid data, such as images. They are built on the idea of convolution, where filters scan and extract local patterns from input data. This skill is measured in this test to evaluate the knowledge of CNN architecture and its application in computer vision tasks.

Recurrent Neural Networks: Recurrent neural networks (RNNs) are neural networks that process variable-length sequential data, such as text or time-series. They have feedback connections that allow information to persist throughout the network. This skill is measured in this test to assess understanding of RNNs and their ability to model sequential patterns.

Generative Adversarial Networks: Generative adversarial networks (GANs) consist of two neural networks: a generator and a discriminator. They are trained together in a competitive process, where the generator aims to produce synthetic data that is indistinguishable from real data. This skill is measured in this test to evaluate knowledge of GAN architecture and its application in generating realistic data.

Natural Language Processing: Natural language processing (NLP) involves the interaction between computers and human language. It encompasses tasks such as speech recognition, text classification, and machine translation. This skill is measured in this test to assess the understanding of NLP techniques and their application in various language-related tasks.

Computer Vision: Computer vision is a branch of artificial intelligence that deals with interpreting visual information from images or videos. It involves tasks like object detection, image recognition, and image segmentation. This skill is measured in this test to evaluate the knowledge of computer vision algorithms and their application in solving visual perception problems.

Transfer Learning: Transfer learning refers to leveraging pre-trained models on one task to improve performance on another task. By utilizing knowledge gained from previous tasks, transfer learning can significantly reduce the amount of training data and time required. This skill is measured in this test to assess the understanding of transferring learned features from one domain to another.

Autoencoders: Autoencoders are neural networks designed to reconstruct the input data from a compressed representation, called the latent space. They are often used for unsupervised learning and dimensionality reduction. This skill is measured in this test to evaluate the knowledge of autoencoders and their application in tasks like data compression and anomaly detection.

Optimization Algorithms: Optimization algorithms play a crucial role in training neural networks by iteratively adjusting the model's parameters to minimize the training loss. Examples include stochastic gradient descent (SGD), Adam, and RMSprop. This skill is measured in this test to assess the familiarity with different optimization algorithms and their impact on network convergence and performance.

Get started for free

Preview questions

Make informed decisions with actionable reports and benchmarks

View sample scorecard

Screen candidates in 3 easy steps

Pick a test from over 500+ tests

The Adaface test library features 500+ tests to enable you to test candidates on all popular skills- everything from programming languages, software frameworks, devops, logical reasoning, abstract reasoning, critical thinking, fluid intelligence, content marketing, talent acquisition, customer service, accounting, product management, sales and more.

Invite your candidates with 2-clicks

Make informed hiring decisions

Get started for free

Preview questions

Try the most advanced candidate assessment platform

ChatGPT Protection

Non-googleable Questions

Web Proctoring

IP Proctoring

Webcam Proctoring

MCQ Questions

Coding Questions

Typing Questions

Personality Questions

Custom Questions

Ready-to-use Tests

Custom Tests

Custom Branding

Bulk Invites

Public Links

ATS Integrations

Multiple Question Sets

Custom API integrations

Role-based Access

Priority Support

GDPR Compliance

Pick a plan based on your hiring needs

The most advanced candidate screening platform.
14-day free trial. No credit card required.

From

$15

per month (paid annually)

View pricing plans

With Adaface, we were able to optimise our initial screening process by upwards of 75%, freeing up precious time for both hiring managers and our talent acquisition team alike!

Brandon Lee, Head of People, Love, Bonito

It's very easy to share assessments with candidates and for candidates to use. We get good feedback from candidates about completing the tests. Adaface are very responsive and friendly to deal with.

Kirsty Wood, Human Resources, WillyWeather

We were able to close 106 positions in a record time of 45 days! Adaface enables us to conduct aptitude and psychometric assessments seamlessly. My hiring managers have never been happier with the quality of candidates shortlisted.

Amit Kataria, CHRO, Hanu

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