Machine Learning
51 bites tagged Machine Learning — interview questions with model answers, and 60-second explainers.
NLP pipeline to theme and tag research transcripts
Chunk and embed transcripts, cluster or LLM-tag for themes, run sentiment with aspect awareness, and keep a human in the loop. designing an NLP pipeline plus honest limits.
Vector embeddings and vector databases
An embedding is a learned dense vector capturing semantic meaning, and vector DBs use ANN indexes like HNSW for fast similarity search that relational B-trees cannot provide. grasp of embeddings and ANN search.
RL components and how Q-learning works
Agent acts on the environment, observes state and reward, seeking to maximize cumulative discounted reward; Q-learning iteratively updates Q(s,a) toward reward plus discounted best… foundational RL vocabulary and the Q-learning update.
Interpreting a black-box gradient boosting model
Global tools like permutation importance or aggregated SHAP rank overall feature influence; local tools like per-instance SHAP or LIME explain one prediction; SHAP unifies both via additive… model interpretability methods.
Random Forest versus Gradient Boosting
Random Forest trains deep trees in parallel and averages to cut variance; boosting builds shallow trees sequentially, each correcting prior errors to cut bias, often higher accuracy but… understanding bagging versus boosting.
Eigenvalues, eigenvectors, and their role in PCA
An eigenvector keeps direction under a matrix, its eigenvalue scales it; PCA finds eigenvectors of the covariance matrix as principal axes. linear algebra intuition behind dimensionality reduction.
How gradient descent and the learning rate work
Gradient descent steps downhill along the negative gradient to minimize cost; the learning rate sets step size; too high diverges or oscillates, too low converges painfully slowly. optimization fundamentals.
Generative Adversarial Network (GAN)
A GAN trains two networks in competition: a generator that fabricates fake samples and a discriminator that judges real versus fake. Their adversarial game pushes the generator toward realistic outputs, enabling image synthesis and data generation without…
Automatically moderate user-generated ad copy
A layered pipeline of fast keyword/regex filters plus an ML text classifier, with human review for borderline cases. moderation design and tradeoffs. a keyword blocklist alone, which misses context and is easily evaded.
Precision vs recall in object detection.
Precision is fraction of detections that are correct, recall is fraction of true objects found; prioritize recall for safety-critical detection, precision when false alarms are costly. precision and recall trade-offs.
Design petabyte-scale distributed training
Object storage with columnar formats, distributed preprocessing, a data-parallel framework with efficient sharded loading, and managed orchestration. end-to-end big-data ML architecture.
How would you speed up slow single-GPU training?
Vertical scaling to bigger or multi-GPU instances, then data-parallel or model-parallel distributed training across nodes. knowledge of scaling training.
How would you build CI/CD for an ML model?
Data and model versioning, automated training plus evaluation gates, model registry, deployment with monitoring and retraining triggers. MLOps maturity beyond app deployment.
Deploying a real-time inference endpoint
Package the model artifact and inference code in a container, choose instance type and autoscaling, configure the endpoint with health checks, and plan safe rollout like canary plus monitoring. model serving operations.
Feeding large object-store data into training
Stream data instead of copying it all to disk, use streaming/pipe modes, shard and prefetch in parallel, and pack many small images into larger files. ML data loading efficiency. downloading the whole 1TB to local disk first.
Pre-built AI service vs custom model
Choose a managed service for speed, no ML expertise, and common tasks; build custom for domain-specific needs, control, or cost at scale. buy-versus-build judgment for ML. always building custom when a managed API suffices.
Run a Core ML image model with Vision
Add the .mlmodel so Xcode generates a class, wrap it in a VNCoreMLModel, run a VNCoreMLRequest via a VNImageRequestHandler, read results off the main queue. Wiring Core ML into Vision for image inference.
Build a SaaS churn prediction model
Define churn and the prediction window, engineer usage-trend and tenure features, try logistic regression then gradient-boosted trees, and evaluate on class-imbalanced metrics. end-to-end supervised modeling with a clear label.
Explain a model registry's purpose and what to store per version
Tests if you treat the registry as a governance bridge between training and production, not just storage. Strong answers cite versioned artifacts, lineage, metrics, dependencies, and approval gates. Red flag: calling it a file dump or experiment tracker.
Design a centralized model registry for a large enterprise
Tests ML artifact governance at scale. Strong answers cover immutable versioned artifacts with dependency manifests, a framework-agnostic API, and pluggable deployment targets. Red flag: treating models as opaque files without environment reproducibility.
Describe a Model Registry and how it differs from versioned storage
It tests governance and lifecycle metadata beyond file storage. A strong answer covers lineage, stage transitions, approval gates, and artifact metadata, contrasting with buckets that only store file versions.
Why systematically track ML experiments and what should you log?
This tests reproducibility mindset over bookkeeping. A strong answer names three motivations—reproducibility, selection, debugging—and three logs: hyperparameters, metrics, and code versions.
Design a defense-in-depth strategy against adversarial evasion on a deployed image classifier
Proactive: adversarial training, preprocessing, ensembles. Your ability to layer training-time and inference-time defenses for adversarial robustness.
How would you design a reproducible ML training pipeline?
Tests if you can version ML's three moving parts: code, data, and environment. Good answers cover Git for code, DVC or lakehouse versioning for data, and Docker plus locked dependencies for environments.
Get Machine Learning bites daily.
Five a day, five minutes, offline. With quizzes so it sticks.
Open testing — you’ll join as an early tester.