Practice AI/ML questions
Browse by topic, filter by difficulty, and track your progress across deep learning, LLMs, MLOps, and more.
- Total
- 365
- Topics
- 10
- Solved
- 0
- Saved
- 0
Browse by topic
365 questions
- 01
Linear Regression Using Gradient Descent
Machine Learningeasy - 02
Implement Gradient Descent Variants with MSE Loss
Machine Learningmedium - 03
Implement Adam Optimization Algorithm
Machine Learningmedium - 04
Implement Lasso Regression using ISTA
Machine Learningmedium - 05
Single Neuron
Machine Learningeasy - 06
Sigmoid Activation Function Understanding
Machine Learningeasy - 07
Softmax Activation Function Implementation
Machine Learningeasy - 08
Implementation of Log Softmax Function
Machine Learningeasy - 09
Implement ReLU Activation Function
Machine Learningeasy - 10
Simple Convolutional 2D Layer
Machine Learningmedium - 11
Implementing a Simple RNN
Machine Learningmedium - 12
Poisson Distribution Probability Calculator
Machine Learningeasy - 13
Binomial Distribution Probability
Machine Learningmedium - 14
Normal Distribution PDF Calculator
Machine Learningmedium - 15
Descriptive Statistics Calculator
Machine Learningeasy - 16
Calculate Covariance Matrix
Machine Learningeasy - 17
Generate a Confusion Matrix for Binary Classification
Machine Learningeasy - 18
Calculate Accuracy Score
Machine Learningeasy - 19
Implement Precision Metric
Machine Learningeasy - 20
Implement Recall Metric in Binary Classification
Machine Learningeasy - 21
Implement F-Score Calculation for Binary Classification
Machine Learningeasy - 22
Calculate R-squared for Regression Analysis
Machine Learningeasy - 23
Calculate Mean Absolute Error (MAE)
Machine Learningeasy - 24
Calculate Root Mean Square Error (RMSE)
Machine Learningeasy - 25
Implement K-Fold Cross-Validation
Machine Learningmedium - 26
Calculate Performance Metrics for a Classification Model
Machine Learningmedium - 27
KL Divergence Between Two Normal Distributions
Machine Learningeasy - 28
Principal Component Analysis (PCA) Implementation
Machine Learningmedium - 29
K-Means Clustering
Machine Learningmedium - 30
Linear Regression Using Normal Equation
Machine Learningeasy - 31
Binary Classification with Logistic Regression
Machine Learningeasy - 32
Calculate Jaccard Index for Binary Classification
Machine Learningeasy - 33
Pegasos Kernel SVM Implementation
Machine Learninghard - 34
Implement AdaBoost Fit Method
Machine Learninghard - 35
Matrix-Vector Dot Product
Machine Learningeasy - 36
Transpose of a Matrix
Machine Learningeasy - 37
Dot Product Calculator
Machine Learningeasy - 38
Scalar Multiplication of a Matrix
Machine Learningeasy - 39
Calculate Cosine Similarity Between Vectors
Machine Learningeasy - 40
Calculate Mean by Row or Column
Machine Learningeasy - 41
Calculate Eigenvalues of a Matrix
Machine Learningmedium - 42
Calculate 2x2 Matrix Inverse
Machine Learningeasy - 43
Matrix times Matrix
Machine Learningmedium - 44
Implement Self-Attention Mechanism
Deep Learningmedium - 45
The Pattern Weaver's Code
Deep Learningmedium - 46
Positional Encoding Calculator
Deep Learninghard - 47
Implement Multi-Head Attention
Deep Learninghard - 48
GPT-2 Text Generation
Deep Learninghard - 49
Linear Regression Using Gradient Descent
Deep Learningeasy - 50
Implement Gradient Descent Variants with MSE Loss
Deep Learningmedium - 51
Implement Adam Optimization Algorithm
Deep Learningmedium - 52
Implement Lasso Regression using ISTA
Deep Learningmedium - 53
Softmax Activation Function Implementation
Deep Learningeasy - 54
Implementation of Log Softmax Function
Deep Learningeasy - 55
Sigmoid Activation Function Understanding
Deep Learningeasy - 56
Implement ReLU Activation Function
Deep Learningeasy - 57
Leaky ReLU Activation Function
Deep Learningeasy - 58
Implement the PReLU Activation Function
Deep Learningeasy - 59
Single Neuron
Deep Learningeasy - 60
Implementing a Simple RNN
Deep Learningmedium - 61
Implement Long Short-Term Memory (LSTM) Network
Deep Learningmedium - 62
Simple Convolutional 2D Layer
Deep Learningmedium - 63
Poisson Distribution Probability Calculator
Deep Learningeasy - 64
Binomial Distribution Probability
Deep Learningmedium - 65
Normal Distribution PDF Calculator
Deep Learningmedium - 66
Descriptive Statistics Calculator
Deep Learningeasy - 67
Calculate Covariance Matrix
Deep Learningeasy - 68
Single Neuron with Backpropagation
Deep Learningmedium - 69
Implementing Basic Autograd Operations
Deep Learningmedium - 70
Implement a Simple RNN with Backpropagation Through Time (BPTT)
Deep Learninghard - 71
Matrix-Vector Dot Product
Deep Learningeasy - 72
Transpose of a Matrix
Deep Learningeasy - 73
Dot Product Calculator
Deep Learningeasy - 74
Scalar Multiplication of a Matrix
Deep Learningeasy - 75
Calculate Cosine Similarity Between Vectors
Deep Learningeasy - 76
Calculate Mean by Row or Column
Deep Learningeasy - 77
Calculate Eigenvalues of a Matrix
Deep Learningmedium - 78
Calculate 2x2 Matrix Inverse
Deep Learningeasy - 79
Matrix times Matrix
Deep Learningmedium - 80
Dropout Layer
Data Science Interview Prepmedium - 81
Min-Max Scaling of Feature Values
Data Science Interview Prepeasy - 82
Softmax Activation Function Implementation
Data Science Interview Prepeasy - 83
Single Neuron
Data Science Interview Prepeasy - 84
Implement ReLU Activation Function
Data Science Interview Prepeasy - 85
Calculate F1 Score from Predicted and True Labels
Data Science Interview Prepeasy - 86
Calculate Accuracy Score
Data Science Interview Prepeasy - 87
Calculate Root Mean Square Error (RMSE)
Data Science Interview Prepeasy - 88
Calculate Mean Absolute Error (MAE)
Data Science Interview Prepeasy - 89
Implement Precision Metric
Data Science Interview Prepeasy - 90
Detect Overfitting or Underfitting
Data Science Interview Prepeasy - 91
ExponentialLR Learning Rate Scheduler
Data Science Interview Prepeasy - 92
Linear Regression Using Gradient Descent
Data Science Interview Prepeasy - 93
K-Means Clustering
Data Science Interview Prepmedium - 94
Implement Early Stopping Based on Validation Loss
Data Science Interview Prepeasy - 95
Find the Best Gini-Based Split for a Binary Decision Tree
Data Science Interview Prepmedium - 96
Implement K-Nearest Neighbors
Data Science Interview Prepmedium - 97
One-Hot Encoding of Nominal Values
Data Science Interview Prepeasy - 98
Implement K-Fold Cross-Validation
Data Science Interview Prepmedium - 99
Calculate Mean by Row or Column
Data Science Interview Prepeasy - 100
Feature Scaling Implementation
Data Science Interview Prepeasy - 101
Implement Gradient Descent Variants with MSE Loss
MLE Interview Prepmedium - 102
Compute Multi-class Cross-Entropy Loss
MLE Interview Prepeasy - 103
Implement Ridge Regression Loss Function
MLE Interview Prepeasy - 104
Implement Lasso Regression using ISTA
MLE Interview Prepmedium - 105
Implement Self-Attention Mechanism
MLE Interview Prepmedium - 106
Implement Multi-Head Attention
MLE Interview Prephard - 107
Positional Encoding Calculator
MLE Interview Prephard - 108
Single Neuron with Backpropagation
MLE Interview Prepmedium - 109
Implementing a Custom Dense Layer in Python
MLE Interview Prephard - 110
Implement Batch Normalization for BCHW Input
MLE Interview Prepmedium - 111
Dropout Layer
MLE Interview Prepmedium - 112
Implement ReLU Activation Function
MLE Interview Prepeasy - 113
Softmax Activation Function Implementation
MLE Interview Prepeasy - 114
Implement K-Fold Cross-Validation
MLE Interview Prepmedium - 115
Generate a Confusion Matrix for Binary Classification
MLE Interview Prepeasy - 116
Implement Precision Metric
MLE Interview Prepeasy - 117
Implement Recall Metric in Binary Classification
MLE Interview Prepeasy - 118
Implement F-Score Calculation for Binary Classification
MLE Interview Prepeasy - 119
Calculate AUC (Area Under ROC Curve)
MLE Interview Prepmedium - 120
Implement Adam Optimization Algorithm
MLE Interview Prepmedium - 121
Momentum Optimizer
MLE Interview Prepeasy - 122
Gradient Clipping by Global Norm
MLE Interview Prepmedium - 123
Implement Stratified Train-Test Split
MLE Interview Prepmedium - 124
Implement Grid Search
MLE Interview Prepmedium - 125
Implement Early Stopping Based on Validation Loss
MLE Interview Prepeasy - 126
Feature Drift Detection using Population Stability Index
MLE Interview Prepmedium - 127
A/B Test Statistical Analysis for Model Comparison
MLE Interview Prephard - 128
Calculate P50/P95/P99 Latency Percentiles
MLE Interview Prepeasy - 129
Implement INT8 Quantization
MLE Interview Prepmedium - 130
Implement Prediction Distribution Monitoring
MLE Interview Prepmedium - 131
Calculate Statistical Power for Experiment Design
MLE Interview Prepmedium - 132
Implement Request Batching for Inference
MLE Interview Prepmedium - 133
Simple Convolutional 2D Layer
MLE Interview Prepmedium - 134
Implement Global Average Pooling
MLE Interview Prepeasy - 135
Implement Long Short-Term Memory (LSTM) Network
MLE Interview Prepmedium - 136
Implement GRU Cell
MLE Interview Prepmedium - 137
Linear Regression Using Gradient Descent
MLE Interview Prepeasy - 138
Train Logistic Regression with Gradient Descent
MLE Interview Prephard - 139
K-Means Clustering
MLE Interview Prepmedium - 140
Principal Component Analysis (PCA) Implementation
MLE Interview Prepmedium - 141
Decision Tree Learning
MLE Interview Prephard - 142
Calculate Image Brightness
Computer Visioneasy - 143
Grayscale Image Contrast Calculator
Computer Visioneasy - 144
Optical Flow EPE with Masks (OmniWorld-style metric)
Computer Visionmedium - 145
PCA Color Augmentation
Computer Visionhard - 146
Convert RGB Image to Grayscale
Computer Visioneasy - 147
Flip an Image Horizontally or Vertically
Computer Visioneasy - 148
Apply Zero Padding to an Image
Computer Visioneasy - 149
Bilinear Image Resizing
Computer Visionmedium - 150
Sobel Edge Detection
Computer Visionmedium - 151
Non-Maximum Suppression for Object Detection
Computer Visionhard - 152
MMLU Log-Probability Scoring
LLMmedium - 153
Rubric-Based LLM Judge Evaluation
LLMmedium - 154
Boxed Answer Extraction for Math Benchmarks
LLMmedium - 155
Math Answer Verification with Equivalence Checking
LLMmedium - 156
Pairwise Preference Judge for LLM Comparison
LLMmedium - 157
Code Execution Verifier for Programming Benchmarks
LLMmedium - 158
Direct Preference Optimization (DPO) Loss
LLMmedium - 159
Top-p (Nucleus) Sampling
LLMmedium - 160
What are Large Language Models (LLMs)?
LLMeasy - 161
Tokenization
LLMeasy - 162
Hallucination in LLMs
LLMeasy - 163
Temperature Parameter
LLMeasy - 164
Prompt Engineering
LLMeasy - 165
Fine-Tuning
LLMeasy - 166
Generative vs Discriminative AI
LLMeasy - 167
Pre-training
LLMeasy - 168
Zero-Shot Prompting
LLMeasy - 169
Context Window
LLMeasy - 170
Transformer Architecture
LLMmedium - 171
Self-Attention Mechanism
LLMmedium - 172
Encoder vs Decoder
LLMmedium - 173
Retrieval-Augmented Generation (RAG)
LLMmedium - 174
Vector Databases
LLMmedium - 175
Embeddings
LLMmedium - 176
RLHF
LLMmedium - 177
Top-K vs Top-P Sampling
LLMmedium - 178
Cross-Entropy Loss
LLMmedium - 179
LoRA (Low-Rank Adaptation)
LLMmedium - 180
Perplexity
LLMmedium - 181
Few-Shot Prompting
LLMmedium - 182
Greedy vs Beam Search
LLMmedium - 183
Semantic Search
LLMmedium - 184
Softmax Function
LLMmedium - 185
Masked Language Modeling
LLMmedium - 186
Instruction Tuning
LLMmedium - 187
Gradient Descent in LLMs
LLMmedium - 188
Overfitting vs Underfitting
LLMmedium - 189
Transfer Learning
LLMmedium - 190
FlashAttention
LLMhard - 191
Rotary Position Embeddings (RoPE)
LLMhard - 192
KV Cache
LLMhard - 193
Mixture of Experts (MoE)
LLMhard - 194
Direct Preference Optimization (DPO)
LLMhard - 195
Quantization (GPTQ / AWQ)
LLMhard - 196
Speculative Decoding
LLMhard - 197
PagedAttention
LLMhard - 198
Tensor Parallelism vs Pipeline Parallelism
LLMhard - 199
Grouped-Query Attention (GQA)
LLMhard - 200
Contrastive Decoding
LLMhard - 201
Catastrophic Forgetting
LLMhard - 202
ALiBi Positional Encoding
LLMhard - 203
Chinchilla Scaling Laws
LLMhard - 204
Self-Supervised Learning Frameworks
LLMhard - 205
The Softmax Bottleneck
LLMhard - 206
Constitutional AI
LLMhard - 207
Length Extrapolation Limitation
LLMhard - 208
Byte-Pair Encoding (BPE)
LLMhard - 209
Catastrophic Forgetting in RLHF
LLMhard - 210
Build a Simple ETL Pipeline (MLOps)
MLOpsmedium - 211
Calculate Model Inference Statistics for Monitoring
MLOpseasy - 212
Calculate Batch Prediction Health Metrics
MLOpseasy - 213
Calculate SLA Compliance Metrics for Model Service
MLOpseasy - 214
Analyze Canary Deployment Health for Model Rollout
MLOpsmedium - 215
Data Quality Scoring for ML Pipelines
MLOpsmedium - 216
Feature Drift Detection using Population Stability Index
MLOpsmedium - 217
A/B Test Statistical Analysis for Model Comparison
MLOpshard - 218
ML Pipeline DAG Scheduler with Critical Path Analysis
MLOpshard - 219
Implement Prediction Distribution Monitoring
MLOpsmedium - 220
Implement Request Batching for Inference
MLOpsmedium - 221
Implement Volume Bars Sampling
Reinforcement Learningmedium - 222
Implement Dollar Bars Sampling
Reinforcement Learningmedium - 223
Diffusion Reconstruction Loss
Reinforcement Learningmedium - 224
Forward Diffusion Process
Reinforcement Learningmedium - 225
Forward & Backward Diffusion Process
Reinforcement Learningmedium - 226
Implement the GRPO Objective Function
Reinforcement Learninghard - 227
Policy Gradient with REINFORCE
Reinforcement Learninghard - 228
Implement Q-Learning Algorithm for MDPs
Reinforcement Learningmedium - 229
Gridworld Policy Evaluation
Reinforcement Learningmedium - 230
Implement the Bellman Equation for Value Iteration
Reinforcement Learningmedium - 231
Epsilon-Greedy Action Selection for n-Armed Bandit
Reinforcement Learningmedium - 232
Incremental Mean for Online Reward Estimation
Reinforcement Learningeasy - 233
Exponential Weighted Average of Rewards
Reinforcement Learningeasy - 234
Upper Confidence Bound (UCB) Action Selection
Reinforcement Learningeasy - 235
Gradient Bandit Action Selection
Reinforcement Learningmedium - 236
Gambler's Problem: Value Iteration
Reinforcement Learninghard - 237
Compute Discounted Return
Reinforcement Learningeasy - 238
Evaluate Expected Value in a Markov Decision Process
Reinforcement Learningmedium - 239
Calculate the Discounted Return for a Given Trajectory
Reinforcement Learningeasy - 240
Monte Carlo Tree Search
Reinforcement Learninghard - 241
GSPO: Group Sequence Policy Optimization
Reinforcement Learninghard - 242
Dr. GRPO: Complete Objective Function
Reinforcement Learningmedium - 243
Group Relative Advantage for GRPO
Reinforcement Learningeasy - 244
KL Divergence Estimator for GRPO
Reinforcement Learningeasy - 245
Pass@k and Majority Voting Evaluation Metrics
Reinforcement Learningeasy - 246
Budget-Constrained RL Loss
Reinforcement Learningmedium - 247
Compute Temporal Difference Error
Reinforcement Learningeasy - 248
First-Visit Monte Carlo Prediction
Reinforcement Learningmedium - 249
n-Step TD Prediction
Reinforcement Learningmedium - 250
TD(llama) with Eligibility Traces
Reinforcement Learninghard - 251
Fine-Tune Model Weights with RLHF Policy Gradient
Reinforcement Learningmedium - 252
RAFT: Iterative Reward-Ranked Fine-Tuning Loop
Reinforcement Learningmedium - 253
Byte Pair Encoding (BPE) Tokenizer
NLPmedium - 254
Optimal String Alignment Distance
NLPeasy - 255
Implement TF-IDF (Term Frequency-Inverse Document Frequency)
NLPmedium - 256
GPT-2 Text Generation
NLPhard - 257
BM25 Ranking
NLPmedium - 258
Evaluate Translation Quality with METEOR Score
NLPmedium - 259
Compute Pointwise Mutual Information
NLPmedium - 260
Calculate Unigram Probability from Corpus
NLPeasy - 261
Calculate Perplexity for Language Models
NLPeasy - 262
BLEU Score for Text Generation
NLPmedium - 263
Bradley-Terry Model for Pairwise Rankings
NLPmedium - 264
Exact Match Score with Normalization
NLPeasy - 265
MMLU Letter-Matching Evaluation
NLPmedium - 266
ReAct Pattern Implementation
Agentseasy - 267
Function Call Parser
Agentseasy - 268
Sliding Window Memory Buffer
Agentseasy - 269
Basic Agent Loop with Termination
Agentseasy - 270
Sequential Prompt Chain
Agentseasy - 271
Keyword-Based Tool Selector
Agentseasy - 272
Tool Execution with Try-Catch
Agentseasy - 273
Observation-Action Cycle Logger
Agentseasy - 274
Token Budget Tracker
Agentseasy - 275
Simple Self-Critique Wrapper
Agentseasy - 276
Idempotency Key Generator
Agentseasy - 277
Tool Input Validator
Agentseasy - 278
Agent State Machine
Agentseasy - 279
Simple Input Guardrail
Agentseasy - 280
Deterministic vs Non-Deterministic Classifier
Agentseasy - 281
Simple Knowledge Graph Memory
Agentsmedium - 282
Factuality Checker for Agent Outputs
Agentsmedium - 283
Tool Misuse Detector
Agentsmedium - 284
Blackboard Knowledge System
Agentsmedium - 285
Parallel Agent Executor
Agentsmedium - 286
Conversation Memory Compressor
Agentsmedium - 287
Agent Message Bus
Agentsmedium - 288
Circuit Breaker for Tool Calls
Agentsmedium - 289
Agent Evaluation Framework
Agentsmedium - 290
Tool Execution Sandbox
Agentsmedium - 291
Loop Detection and Prevention
Agentsmedium - 292
LRU-K Memory Eviction
Agentsmedium - 293
Reward Hacking Detector
Agentsmedium - 294
Hierarchical Task Decomposer
Agentsmedium - 295
Coordinator Agent Implementation
Agentsmedium - 296
Role-Based Agent System
Agentsmedium - 297
Multi-Layer Guardrail System
Agentsmedium - 298
Agent Observability Logger
Agentsmedium - 299
Agent Failure Recovery System
Agentsmedium - 300
Safety Constraint Validator
Agentsmedium - 301
Design Production-Ready Agent System
Agentshard - 302
Distributed Multi-Agent Coordinator
Agentshard - 303
Agent Latency Optimizer
Agentshard - 304
Agent Cost Optimizer
Agentshard - 305
Scalable Multi-Agent Orchestrator
Agentshard - 306
Advanced Failure Recovery with Checkpointing
Agentshard - 307
End-to-End Observability Pipeline
Agentshard - 308
Tree of Thoughts Implementation
Agentshard - 309
Hierarchical Memory System
Agentshard - 310
Hierarchical Task Network Planner
Agentshard - 311
Tool Composition and Chaining Engine
Agentshard - 312
Constitutional AI Safety Layer
Agentshard - 313
Agent Self-Improvement System
Agentshard - 314
Multi-Agent Consensus Protocol
Agentshard - 315
Advanced RAG with Query Rewriting and Fusion
Agentshard - 316
Define and Implement a Basic AI Agent Class
Agentseasy - 317
Implement Agent Lifecycle States
Agentseasy - 318
Build a Prompt Chain Pipeline
Agentseasy - 319
Implement Short-Term vs Long-Term Memory
Agentseasy - 320
Implement the ReAct Pattern
Agentseasy - 321
Agent Self-Reflection and Self-Critique
Agentseasy - 322
Basic Tool Registration and Calling
Agentseasy - 323
Implement Termination Conditions for Agent Loops
Agentseasy - 324
Observation-Thought-Action Cycle Implementation
Agentseasy - 325
Implement Basic Guardrails for Agent Output
Agentseasy - 326
Vector Database Integration for Agent Memory
Agentseasy - 327
Implement Tool Retry Mechanism
Agentseasy - 328
Agent Token Budget Controller
Agentseasy - 329
Implement Role-Based Multi-Agent System
Agentseasy - 330
Implement Basic Hallucination Detection
Agentseasy - 331
Implement a Full ReAct Agent with Dynamic Tool Selection
Agentsmedium - 332
Planner-Executor Agent Architecture
Agentsmedium - 333
Implement RAG Inside an Agent
Agentsmedium - 334
Implement Agent Communication Protocol
Agentsmedium - 335
Task Decomposition with Dependency Resolution
Agentsmedium - 336
Implement Episodic Memory with Retrieval
Agentsmedium - 337
Implement Tool Idempotency and Validation
Agentsmedium - 338
Debate Agent Implementation
Agentsmedium - 339
Implement Agent Sandboxing and Safety Constraints
Agentsmedium - 340
Memory Compression and Summarization
Agentsmedium - 341
Implement Coordinator Agent Pattern
Agentsmedium - 342
Knowledge Graph Integration for Agent Reasoning
Agentsmedium - 343
Implement Agent Evaluation Framework
Agentsmedium - 344
Implement Parallel Agent Execution
Agentsmedium - 345
Implement Hierarchical Agent System
Agentsmedium - 346
Blackboard Architecture for Multi-Agent Coordination
Agentsmedium - 347
Design a Production-Ready AI Agent System
Agentshard - 348
Design a Distributed Multi-Agent System with Fault Tolerance
Agentshard - 349
Implement Agent Observability and Distributed Tracing
Agentshard - 350
Latency Optimization for Multi-Step Agent Pipelines
Agentshard - 351
Implement Agent Cost Optimization System
Agentshard - 352
Implement Failure Recovery and Checkpoint System
Agentshard - 353
Design an Agent with Full Conflict Resolution
Agentshard - 354
Implement Tool Misuse Detection System
Agentshard - 355
Implement Agent Alignment and Value Alignment Checker
Agentshard - 356
Implement Scalable Multi-Agent Message Router
Agentshard - 357
Implement Semantic Memory Eviction with Relevance Scoring
Agentshard - 358
Deterministic vs Non-Deterministic Tool Usage
Agentsmedium - 359
Tool Execution Loop with Configurable Error Policies
Agentsmedium - 360
Tree of Thoughts Planning Agent
Agentsmedium - 361
Generator-Critic Self-Play Loop
Agentsmedium - 362
Full Agent Observability Pipeline with Cost Tracking and Alerts
Agentshard - 363
Auto-Scaling Agent Worker Pool
Agentshard - 364
Cross-Session Agent Memory and User Profiling
Agentshard - 365
Adaptive Instruction Priority and Conflict Resolution
Agentshard