Skip to main content

Concept Interview Questions

Review this list of 152 Concept interview questions and answers verified by hiring managers and candidates.
  • OpenAI logoAsked at OpenAI 

    "Reinforcement Learning is a type of machine learning where an agent learns to make decisions by trying out different actions and receiving rewards or penalties in return. The goal is to learn, over time, which actions yield the highest rewards. There are three core components in RL: The agent — the learner or decision-maker (e.g., an algorithm or robot), The environment — everything the agent interacts with, Actions and rewards — the agent takes actions, and the environmen"

    Constantin P. - "Reinforcement Learning is a type of machine learning where an agent learns to make decisions by trying out different actions and receiving rewards or penalties in return. The goal is to learn, over time, which actions yield the highest rewards. There are three core components in RL: The agent — the learner or decision-maker (e.g., an algorithm or robot), The environment — everything the agent interacts with, Actions and rewards — the agent takes actions, and the environmen"See full answer

    Machine Learning Engineer
    Concept
    +1 more
  • Anthropic logoAsked at Anthropic 
    Machine Learning Engineer
    Concept
    +2 more
  • Apple logoAsked at Apple 

    "Hey Grandma, you've had a lot of experience with infants, haven't you? When they were babies, you taught them how to chew in their first six months. This initial phase is like giving them data. Once they learned how to chew, they could handle any food you gave them. Next, you refined their learning by teaching them that they should only chew on food. This is like refining the data so they understand what is relevant. Then, a few months later, they started crawling and walking, learning by observ"

    Hari priya K. - "Hey Grandma, you've had a lot of experience with infants, haven't you? When they were babies, you taught them how to chew in their first six months. This initial phase is like giving them data. Once they learned how to chew, they could handle any food you gave them. Next, you refined their learning by teaching them that they should only chew on food. This is like refining the data so they understand what is relevant. Then, a few months later, they started crawling and walking, learning by observ"See full answer

    Machine Learning Engineer
    Concept
  • Google logoAsked at Google 

    "Clarification questions What is the purpose of connecting the DB? Do we expect high-volumes of traffic to hit the DB Do we have scalability or reliability concerns? Format Code -> DB Code -> Cache -> DB API -> Cache -> DB - APIs are built for a purpose and have a specified protocol (GET, POST, DELETE) to speak to the DB. APIs can also use a contract to retrieve information from a DB much faster than code. Load balanced APIs -> Cache -> DB **Aut"

    Aaron W. - "Clarification questions What is the purpose of connecting the DB? Do we expect high-volumes of traffic to hit the DB Do we have scalability or reliability concerns? Format Code -> DB Code -> Cache -> DB API -> Cache -> DB - APIs are built for a purpose and have a specified protocol (GET, POST, DELETE) to speak to the DB. APIs can also use a contract to retrieve information from a DB much faster than code. Load balanced APIs -> Cache -> DB **Aut"See full answer

    Product Manager
    Concept
    +5 more
  • "I did not give the proper ans so gettting rejected"

    Praveen K. - "I did not give the proper ans so gettting rejected"See full answer

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

  • Software Engineer
    Concept
  • Google logoAsked at Google 

    "Grandma! You know how we can look at a picture and know what's in it—like seeing a cat or a dog? Computers can learn to do that too! It's just they use special tricks and math to see and understand pictures or videos. It helps them figure out what's in the pictures, almost like how we do! Almost like giving it eyes to see the world in its own way!"

    Praveen D. - "Grandma! You know how we can look at a picture and know what's in it—like seeing a cat or a dog? Computers can learn to do that too! It's just they use special tricks and math to see and understand pictures or videos. It helps them figure out what's in the pictures, almost like how we do! Almost like giving it eyes to see the world in its own way!"See full answer

    Machine Learning Engineer
    Concept
  • +1

    "https://www.freecodecamp.org/news/what-happens-when-you-hit-url-in-your-browser/"

    Kanika - "https://www.freecodecamp.org/news/what-happens-when-you-hit-url-in-your-browser/"See full answer

    Product Manager
    Concept
    +2 more
  • Machine Learning Engineer
    Concept
    +1 more
  • Nvidia logoAsked at Nvidia 

    "Clarifying When we say cloud gaming, we refer to a video gaming experience using cloud computing, right? Assumption: Yes. Understanding of cloud computing first. I'll use some analogies: Imagine you are looking to do heavy computing but don't have a powerful CPU and GPU. CPU and GPU are like your big calculators. You can buy a powerful CPU and GPU, but problems: It costs a lot to buy. It costs a lot to run. You don't need it 24-7. You are not a un"

    Darpan D. - "Clarifying When we say cloud gaming, we refer to a video gaming experience using cloud computing, right? Assumption: Yes. Understanding of cloud computing first. I'll use some analogies: Imagine you are looking to do heavy computing but don't have a powerful CPU and GPU. CPU and GPU are like your big calculators. You can buy a powerful CPU and GPU, but problems: It costs a lot to buy. It costs a lot to run. You don't need it 24-7. You are not a un"See full answer

    Product Manager
    Concept
    +3 more
  • Machine Learning Engineer
    Concept
    +1 more
  • Snap logoAsked at Snap 
    Machine Learning Engineer
    Concept
  • Lyft logoAsked at Lyft 

    "Potential ad creators: Brands Drivers Travel services. Goal: To create a revenue stream. Acquire new users? To potentially develop new products? For now, lets focus on generating revenue as the goal. Potential ad products: Ads from brands you can watch while you are riding. Most riders dont look at the app while riding but we can provide them incentives like 5% off next ride if they watch ads the whole ride and pay it via ad revenue. Drivers can pay Lyft to be matched more w"

    M N. - "Potential ad creators: Brands Drivers Travel services. Goal: To create a revenue stream. Acquire new users? To potentially develop new products? For now, lets focus on generating revenue as the goal. Potential ad products: Ads from brands you can watch while you are riding. Most riders dont look at the app while riding but we can provide them incentives like 5% off next ride if they watch ads the whole ride and pay it via ad revenue. Drivers can pay Lyft to be matched more w"See full answer

    Concept
    Product Design
  • Apple logoAsked at Apple 
    Machine Learning Engineer
    Concept
  • "No discussion around better initialization of weights like Xavier etc.?"

    Vips M. - "No discussion around better initialization of weights like Xavier etc.?"See full answer

    Concept
    Machine Learning
  • Microsoft logoAsked at Microsoft 

    "BERT is a bidirectional encoder representation transformer. It takes a sequence of tokens and produces vector embeddings for each token. The BERT Model was trained on the task of next sentence prediction task and masked language modeling. The key difference between word2vec and BERT is that, word2vec produces semantic embeddings for each word, where as BERT produces contextual word embeddings based on the relationships between surrounding words. Example - Vector Embedding of lets say word "i"

    Sanmitra I. - "BERT is a bidirectional encoder representation transformer. It takes a sequence of tokens and produces vector embeddings for each token. The BERT Model was trained on the task of next sentence prediction task and masked language modeling. The key difference between word2vec and BERT is that, word2vec produces semantic embeddings for each word, where as BERT produces contextual word embeddings based on the relationships between surrounding words. Example - Vector Embedding of lets say word "i"See full answer

    Machine Learning Engineer
    Concept
  • Meta (Facebook) logoAsked at Meta (Facebook) 

    "Clarification Am I the PM for overall Xbox or certain part of the Xbox team? Interview (I): let's assume you own the overall Xbox product Are there particular user segments that the MSFT Gaming division is trying to focus on as their strategy? I: nothing in particular, why don't you tell me where we should focus? What are some challenges that Xbox have been facing? (ie revenue from xbox hardware purchase? xbox live subscription purchase? engagement?) I: nothing in pa"

    Mark - "Clarification Am I the PM for overall Xbox or certain part of the Xbox team? Interview (I): let's assume you own the overall Xbox product Are there particular user segments that the MSFT Gaming division is trying to focus on as their strategy? I: nothing in particular, why don't you tell me where we should focus? What are some challenges that Xbox have been facing? (ie revenue from xbox hardware purchase? xbox live subscription purchase? engagement?) I: nothing in pa"See full answer

    Concept
    Analytical
    +1 more
  • Amazon logoAsked at Amazon 
    Machine Learning Engineer
    Concept
    +1 more
Showing 41-60 of 152