Skip to main content

Concept Interview Questions

Review this list of 159 Concept interview questions and answers verified by hiring managers and candidates.
  • Add answer
    Video answer for 'Explain training and testing data.'
    Concept
    Machine Learning
  • Canva logoAsked at Canva 
    3 answers

    "inheritance means its acquire all properties from parent class to child class.composition means its acquire some properties as our request is called composition"

    Niteesh V. - "inheritance means its acquire all properties from parent class to child class.composition means its acquire some properties as our request is called composition"See full answer

    Software Engineer
    Concept
  • Google logoAsked at Google 
    3 answers

    "25 min"

    Yasin E. - "25 min"See full answer

    Concept
    Behavioral
    +1 more
  • Concept
    Machine Learning
  • +1

    "a process can include many threads. good for concurrent and parallel task execution"

    Erjan G. - "a process can include many threads. good for concurrent and parallel task execution"See full answer

    Data Engineer
    Concept
  • 🧠 Want an expert answer to a question? Saving questions lets us know what content to make next.

  • Snap logoAsked at Snap 
    Add answer
    Machine Learning Engineer
    Concept
    +1 more
  • Yahoo logoAsked at Yahoo 
    1 answer

    "Open Oriented programming is a way to organize code around objects rather then functions."

    Yasir M. - "Open Oriented programming is a way to organize code around objects rather then functions."See full answer

    Software Engineer
    Concept
  • Add answer
    Video answer for 'Explain gradient descent.'
    Concept
    Machine Learning
  • Pinterest logoAsked at Pinterest 
    1 answer

    "The difference between convex and nonconvex functions lies in their mathematical properties and the implications for optimization problems. Convex Functions:A convex function has a shape where any line segment connecting two points on its graph lies entirely above or on the graph. This property ensures that any local minimum is also a global minimum, making optimization straightforward and reliable. Convex functions are critical in machine learning and optimization tasks because of th"

    Alan T. - "The difference between convex and nonconvex functions lies in their mathematical properties and the implications for optimization problems. Convex Functions:A convex function has a shape where any line segment connecting two points on its graph lies entirely above or on the graph. This property ensures that any local minimum is also a global minimum, making optimization straightforward and reliable. Convex functions are critical in machine learning and optimization tasks because of th"See full answer

    Machine Learning Engineer
    Concept
  • Infosys logoAsked at Infosys 
    1 answer

    "In Java, GC is the process of automatically identifying and reclaming memory occupied by objects that are no longer reachable.. the process involves the 3 steps Mark phase -- identify the objects that are still in use. i.e reachable sweep Phase -- removes the unreachable objects compact phase -- rearragnes objects to prevent fragmentation 4 types of Garbage collection Serial GC -- single threaded simple and compacting -- best for small applications Parrallel GC -- throughput GC"

    Sue G. - "In Java, GC is the process of automatically identifying and reclaming memory occupied by objects that are no longer reachable.. the process involves the 3 steps Mark phase -- identify the objects that are still in use. i.e reachable sweep Phase -- removes the unreachable objects compact phase -- rearragnes objects to prevent fragmentation 4 types of Garbage collection Serial GC -- single threaded simple and compacting -- best for small applications Parrallel GC -- throughput GC"See full answer

    Software Engineer
    Concept
  • Hubspot logoAsked at Hubspot 
    Add answer
    Machine Learning Engineer
    Concept
    +1 more
  • Pinterest logoAsked at Pinterest 
    1 answer

    "For a dataset with one million data points, a Deep Neural Network (DNN) is almost always the superior choice over a K-Nearest Neighbors (KNN) algorithm. The primary reasons for this preference involve computational efficiency, scalability, and the ability to handle high-dimensional data. 1. Computational Complexity (Inference Time) KNN: It is a "lazy learner." It doesn't actually "learn" a model; instead, it stores the entire dataset. To make a single prediction, it must calcul"

    Woosung J. - "For a dataset with one million data points, a Deep Neural Network (DNN) is almost always the superior choice over a K-Nearest Neighbors (KNN) algorithm. The primary reasons for this preference involve computational efficiency, scalability, and the ability to handle high-dimensional data. 1. Computational Complexity (Inference Time) KNN: It is a "lazy learner." It doesn't actually "learn" a model; instead, it stores the entire dataset. To make a single prediction, it must calcul"See full answer

    Machine Learning Engineer
    Concept
  • Amazon logoAsked at Amazon 
    Add answer
    Machine Learning Engineer
    Concept
  • Netflix logoAsked at Netflix 
    1 answer

    "TF-IDF CONCEPT EXPLANATION AND INTUITION BUILDING: TF-IDF is a measure that reflects the importance of a word in the document relative to a collection of documents. Its full form is Term Frequency - Inverse Document Frequency. The term TF indicates how often a term occurs in a particular document. It is the ratio of count of a particular term in a document to the number of terms in that particular document. So, the intuition is that if a term occurs frequently in a single documen"

    Satyam C. - "TF-IDF CONCEPT EXPLANATION AND INTUITION BUILDING: TF-IDF is a measure that reflects the importance of a word in the document relative to a collection of documents. Its full form is Term Frequency - Inverse Document Frequency. The term TF indicates how often a term occurs in a particular document. It is the ratio of count of a particular term in a document to the number of terms in that particular document. So, the intuition is that if a term occurs frequently in a single documen"See full answer

    Machine Learning Engineer
    Concept
  • "ArrayList allows constant time access (O(1)) to elements using their index because it uses a dynamic array internally, whereas LinkedList requires traversal from the head node, resulting in linear time complexity (O(n))."

    Aziz V. - "ArrayList allows constant time access (O(1)) to elements using their index because it uses a dynamic array internally, whereas LinkedList requires traversal from the head node, resulting in linear time complexity (O(n))."See full answer

    Software Engineer
    Concept
    +1 more
  • Google logoAsked at Google 
    2 answers

    "Idempotence refers to the property that the same request multiple times produces the same result on the server side. No matter how many times I repeat the request, the server state does not change after the first request. This concept is important to ensure consistency, especially in systems where requests may be repeated due to network failures or other problems. Let's take a look at different HTTP methods for a clearer understanding. GET: By definition, GET requests must be powerless. Execut"

    T I. - "Idempotence refers to the property that the same request multiple times produces the same result on the server side. No matter how many times I repeat the request, the server state does not change after the first request. This concept is important to ensure consistency, especially in systems where requests may be repeated due to network failures or other problems. Let's take a look at different HTTP methods for a clearer understanding. GET: By definition, GET requests must be powerless. Execut"See full answer

    Solutions Architect
    Concept
    +2 more
  • Nvidia logoAsked at Nvidia 
    Add answer
    Software Engineer
    Concept
    +1 more
  • 1 answer

    "The algorithm calculates certain metrics like entropy & Gini Impurity. The goal of the decision tree algorithm is to find the most optimal value for these metrics, lowest values for Gini Impurity & Entropy. Once it converges on the minima, it creates a split & grows the branches."

    Saurabh J. - "The algorithm calculates certain metrics like entropy & Gini Impurity. The goal of the decision tree algorithm is to find the most optimal value for these metrics, lowest values for Gini Impurity & Entropy. Once it converges on the minima, it creates a split & grows the branches."See full answer

    Data Scientist
    Concept
    +1 more
  • Amazon logoAsked at Amazon 
    1 answer

    "Effective loss functions for computer vision models vary depending on the specific task, some commonly used loss functions for different tasks: Classification Cross-Entropy Loss:Used for multi-class classification tasks. Measures the difference between the predicted probability distribution and the true distribution. Binary Cross-Entropy Loss:Used for binary classification tasks. Evaluates the performance of a model by comparing predicted probabilities to the true binary labe"

    Shibin P. - "Effective loss functions for computer vision models vary depending on the specific task, some commonly used loss functions for different tasks: Classification Cross-Entropy Loss:Used for multi-class classification tasks. Measures the difference between the predicted probability distribution and the true distribution. Binary Cross-Entropy Loss:Used for binary classification tasks. Evaluates the performance of a model by comparing predicted probabilities to the true binary labe"See full answer

    Machine Learning Engineer
    Concept
  • Discord logoAsked at Discord 
    1 answer

    "This is a Measure Success question with a slight twist. The twist here is we need to consider a hypothetical product rather that one already built. This changes our formula slightly - specifically we may not be able to apply a UX flow to drive analysis since we're unsure of the implementation. Instead, we'll look at core behaviors that are indicative of success. Here's the modified formula: Ask clarifying questions State the goal of the feature **Apply a UX flow to drive a"

    Exponent - "This is a Measure Success question with a slight twist. The twist here is we need to consider a hypothetical product rather that one already built. This changes our formula slightly - specifically we may not be able to apply a UX flow to drive analysis since we're unsure of the implementation. Instead, we'll look at core behaviors that are indicative of success. Here's the modified formula: Ask clarifying questions State the goal of the feature **Apply a UX flow to drive a"See full answer

    Product Manager
    Concept
Showing 81-100 of 159