Q1. What is the bias-variance tradeoff?
Bias is error from overly simple assumptions; a high-bias model underfits and misses patterns in both training and test data. Variance is error from sensitivity to the tr...
Technical Question Bank · Peer-Reviewed
Job Interview Questions and Answers Directory
Search and filter frequently asked interview questions across technical, programming, and behavioral domains. Tailor your interview preparation by difficulty for freshers or experienced developers (18 available).
Active:
Tag: learning ×
Q2. What is the difference between supervised and unsupervised learning?
Supervised learning uses labelled examples, learning a mapping from inputs to known outputs. Tasks include classification (predict a category, such as spam or not) and re...
Q3. How do you handle class imbalance in a classification problem?
Class imbalance means one class is far rarer, so accuracy becomes misleading and models favor the majority. Strategies: - Resampling: oversample the minority (SMOTE synth...
Q4. What is overfitting and how do you prevent it?
Overfitting is when a model learns noise and idiosyncrasies of the training set instead of the underlying pattern. It performs well on training data but poorly on new dat...
Q5. Describe a time you failed or a project did not go as planned.
Choose a failure that is real but not catastrophic, and focus on learning and corrective action. Situation: "I estimated a feature at two weeks; it took six." Task: "I ow...
Q6. How do you measure whether learning outcomes were achieved?
I decide what evidence would prove the objective was met, then collect it in more than one way. Direct measures include a task, quiz or performance rubric aligned to the ...
Q7. Explain precision and recall and when to prefer each.
Precision is the fraction of predicted positives that are truly positive: TP / (TP + FP). Recall, or sensitivity, is the fraction of actual positives that were found: TP ...
Q8. What is cross-validation and why use it?
Cross-validation repeatedly splits data into training and validation folds to estimate how well a model generalizes. In k-fold, the data is split into k parts; the model ...
Q9. Tell me about a time you had to learn something quickly.
Show a learning system, not just a story. Example: "We inherited a Go service with no tests and I had never written Go. I gave myself three days: I read the standard libr...
Q10. How would you redesign a course for online delivery?
I start from the learning outcomes and the constraints, not from the technology. First I map which outcomes can be achieved online and which need synchronous or practical...