Interview Master 360
A Comprehensive Guide to Mastering Technical Interviews
Practical Programming Problems⚓︎
Developers : Programming, Data Structures and Algorithms(PDSA)⚓︎
Coding Pattern for the Interview Practice
Machine Learning Engineers, Data Scientists and AI Engineers⚓︎
1. Easy⚓︎
Areas : Linear Algebra, Statistics, Optimization, Machine Learning, Deep Learning etc
| ID | Title | Difficulty | Category | Status |
|---|---|---|---|---|
| 1 | Matrix-Vector Dot Product | easy | Linear Algebra | Done |
| 2 | Transpose of a Matrix | easy | Linear Algebra | Done |
| 3 | Reshape Matrix | easy | Linear Algebra | Done |
| 4 | Calculate Mean by Row or Column | easy | Linear Algebra | Done |
| 5 | Scalar Multiplication of a Matrix | easy | Linear Algebra | Done |
| 6 | Calculate Covariance Matrix | easy | Statistics | |
| 7 | Linear Regression Using Normal Equation | easy | Machine Learning | |
| 8 | Linear Regression Using Gradient Descent | easy | Machine Learning | |
| 9 | Feature Scaling Implementation | easy | Machine Learning | |
| 10 | Sigmoid Activation Function Understanding | easy | Deep Learning | |
| 11 | Softmax Activation Function Implementation | easy | Deep Learning | |
| 12 | Single Neuron | easy | Deep Learning | |
| 13 | Transformation Matrix from Basis B to C | easy | Linear Algebra | |
| 14 | Random Shuffle of Dataset | easy | Machine Learning | |
| 15 | Batch Iterator for Dataset | easy | Machine Learning | |
| 16 | One-Hot Encoding of Nominal Values | easy | Machine Learning | |
| 35 | Convert Vector to Diagonal Matrix | easy | Linear Algebra | |
| 36 | Calculate Accuracy Score | easy | Machine Learning | |
| 39 | Implementation of Log Softmax Function | easy | Deep Learning | |
| 42 | Implement ReLU Activation Function | easy | Deep Learning | |
| 43 | Implement Ridge Regression Loss Function | easy | Machine Learning | |
| 44 | Leaky ReLU Activation Function | easy | Deep Learning | |
| 45 | Linear Kernel Function | easy | Machine Learning | |
| 46 | Implement Precision Metric | easy | Machine Learning | |
| 52 | Implement Recall Metric in Binary Classification | easy | Machine Learning | |
| 56 | KL Divergence Between Two Normal Distributions | easy | Deep Learning | |
| 61 | Implement F-Score Calculation for Binary Classification | easy | Machine Learning | |
| 64 | Implement Gini Impurity Calculation for a Set of Classes | easy | Machine Learning | |
| 65 | Implement Compressed Row Sparse Matrix (CSR) Format Conversion | easy | Linear Algebra | |
| 66 | Implement Orthogonal Projection of a Vector onto a Line | easy | Linearr Algebra | |
| 67 | Implement Compressed Column Sparse Matrix Format (CSC) | easy | Linear Algebra | |
| 69 | Calculate R-squared for Regression Analysis | easy | Machine Learning | |
| 70 | Calculate Image Brightness | easy | Computer Vision | |
| 71 | Calculate Root Mean Square Error (RMSE) | easy | Machine Learning | |
| 72 | Calculate Jaccard Index for Binary Classification | easy | Machine Learning | |
| 73 | Calculate Dice Score for Classification | easy | Machine Learning | |
| 75 | Generate a Confusion Matrix for Binary Classification | easy | Machine Learning | |
| 76 | Calculate Cosine Similarity Between Vectors | easy | Linear Algebra | |
| 78 | Descriptive Statistics Calculator | easy | Statistics | |
| 81 | Poisson Distribution Probability Calculator | easy | Probability | |
| 82 | Grayscale Image Contrast Calculator | easy | Computer Vision | |
| 83 | Dot Product Calculator | easy | Linear Algebra | |
| 84 | Phi Transformation for Polynomial Features | easy | Linear Algebra | |
| 86 | Detect Overfitting or Underfitting | easy | Machine Learning | |
| 93 | Calculate Mean Absolute Error (MAE) | easy | Machine Learning | |
| 95 | Calculate the Phi Coefficient | easy | Statistics | |
| 96 | Implement the Hard Sigmoid Activation Function | easy | Deep Learning | |
| 97 | Implement the ELU Activation Function | easy | Deep Learning | |
| 98 | Implement the PReLU Activation Function | easy | Deep Learning | |
| 99 | Implement the Softplus Activation Function | easy | Deep Learning | |
| 100 | Implement the Softsign Activation Function | easy | Deep Learning | |
| 102 | Implement the Swish Activation Function | easy | Deep Learning | |
| 103 | Implement the SELU Activation Function | easy | Deep Learning | |
| 104 | Binary Classification with Logistic Regression | easy | Machine Learning | |
| 108 | Measure Disorder in Apple Colors | easy | Machine Learning | |
| 112 | Min-Max Normalization of Feature Values | easy | Data Preprocessing | |
| 113 | Implement a Simple Residual Block with Shortcut Connection | easy | Deep Learning | |
| 114 | Implement Global Average Pooling | easy | Deep Learning | |
| 115 | Implement Batch Normalization for BCHW Input | easy | Deep Learning | |
| 116 | Derivative of a Polynomial | easy | calculus | |
| 118 | Compute the Cross Product of Two 3D Vectors | easy | Linear Algebra | |
| 120 | Bhattacharyya Distance Between Two Distributions | easy | Statistics | |
| 121 | Vector Element-wise Sum | easy | Linear Algebra | |
| 123 | Calculate Computational Efficiency of MoE | easy | Deep Learning | |
| 128 | Dynamic Tanh: Normalization-Free Transformer Activation | easy | Deep Learning | |
| 129 | Calculate Unigram Probability from Corpus | easy | NLP | |
| 134 | Compute Multi-class Cross-Entropy Loss | easy | Deep Learning | |
| 135 | Implement Early Stopping Based on Validation Loss | easy | Machine Learning | |
| 141 | Shift and Scale Array to Target Range | easy | Machine Learning | |
| 145 | Adagrad Optimizer | easy | Deep Learning | |
| 146 | Momentum Optimizer | easy | Deep Learning | |
| 147 | GeLU Activation Function | easy | Deep Learning | |
| 148 | Adamax Optimizer | easy | Deep Learning | |
| 153 | StepLR Learning Rate Scheduler | easy | Machine Learning | |
| 154 | ExponentialLR Learning Rate Scheduler | easy | Machine Learning | |
| 156 | Implement SwiGLU activation function | easy | Deep Learning | |
| 162 | Upper Confidence Bound (UCB) Action Selection | easy | Reinforcement Learning | |
| 165 | Compute Discounted Return | easy | Reinforcement Learning | |
| 167 | Calculate the Discounted Return for a Given Trajectory | easy | Reinforcement Learning | |
| 168 | Calculate Conditional Probability from Data | easy | Probability |
2. Medium⚓︎
| ID | Title | Difficulty | Category | Status |
|---|---|---|---|---|
| 177NEW | Implement MuonClip (qk-clip) for Stabilizing Attention | medium | Deep Learning | |
| 6 | Calculate Eigenvalues of a Matrix | medium | Linear Algebra | |
| 7 | Matrix Transformation | medium | Linear Algebra | |
| 8 | Calculate 2x2 Matrix Inverse | medium | Linear Algebra | |
| 9 | Matrix times Matrix | medium | Linear Algebra | |
| 11 | Solve Linear Equations using Jacobi Method | medium | Linear Algebra | |
| 17 | K-Means Clustering | medium | Machine Learning | |
| 18 | Implement K-Fold Cross-Validation | medium | Machine Learning | |
| 19 | Principal Component Analysis (PCA) Implementation | medium | Machine Learning | |
| 25 | Single Neuron with Backpropagation | medium | Deep Learning | |
| 26 | Implementing Basic Autograd Operations | medium | Deep Learning | |
| 31 | Divide Dataset Based on Feature Threshold | medium | Machine Learning | |
| 32 | Generate Sorted Polynomial Features | medium | Machine Learning | |
| 33 | Generate Random Subsets of a Dataset | medium | Machine Learning | |
| 37 | Calculate Correlation Matrix | medium | Linear Algebra | |
| 41 | Simple Convolutional 2D Layer | medium | Deep Learning | |
| 47 | Implement Gradient Descent Variants with MSE Loss | medium | Machine Learning | |
| 48 | Implement Reduced Row Echelon Form (RREF) Function | medium | Linear Algebra | |
| 49 | Implement Adam Optimization Algorithm | medium | Deep Learning | |
| 50 | Implement Lasso Regression using Gradient Descent | medium | Machine Learning | |
| 51 | Optimal String Alignment Distance | medium | NLP | |
| 53 | Implement Self-Attention Mechanism | medium | Deep Learning | |
| 54 | Implementing a Simple RNN | medium | Deep Learning | |
| 55 | 2D Translation Matrix Implementation | medium | Linear Algebra | |
| 57 | Gauss-Seidel Method for Solving Linear Systems | medium | Linear Algebra | |
| 58 | Gaussian Elimination for Solving Linear Systems | medium | Linear Algebra | |
| 59 | Implement Long Short-Term Memory (LSTM) Network | medium | Deep Learning | |
| 60 | Implement TF-IDF (Term Frequency-Inverse Document Frequency) | medium | NLP | |
| 68 | Find the Image of a Matrix Using Row Echelon Form | medium | Linear Algebra | |
| 74 | Create Composite Hypervector for a Dataset Row | medium | Linear Algebra | |
| 77 | Calculate Performance Metrics for a Classification Model | medium | Machine Learning | |
| 79 | Binomial Distribution Probability | medium | Probability | |
| 48 | Implement Reduced Row Echelon Form (RREF) Function | medium | Linear Algebra | |
| 49 | Implement Adam Optimization Algorithm | medium | Deep Learning | |
| 50 | Implement Lasso Regression using Gradient Descent | medium | Machine Learning | |
| 51 | Optimal String Alignment Distance | medium | NLP | |
| 53 | Implement Self-Attention Mechanism | medium | Deep Learning | |
| 54 | Implementing a Simple RNN | medium | Deep Learning | |
| 55 | 2D Translation Matrix Implementation | medium | Linear Algebra | |
| 57 | Gauss-Seidel Method for Solving Linear Systems | medium | Linear Algebra | |
| 58 | Gaussian Elimination for Solving Linear Systems | medium | Linear Algebra | |
| 59 | Implement Long Short-Term Memory (LSTM) Network | medium | Deep Learning | |
| 60 | Implement TF-IDF (Term Frequency-Inverse Document Frequency) | medium | NLP | |
| 68 | Find the Image of a Matrix Using Row Echelon Form | medium | Linear Algebra | |
| 74 | Create Composite Hypervector for a Dataset Row | medium | Linear Algebra | |
| 77 | Calculate Performance Metrics for a Classification Model | medium | Machine Learning | |
| 79 | Binomial Distribution Probability | medium | Probability | |
| 132 | Simulate Markov Chain Transitions | medium | Probability | |
| 133 | Implement Q-Learning Algorithm for MDPs | medium | Reinforcement Learning | |
| 136 | Calculate KL Divergence Between Two Multivariate Gaussian Distributions | medium | Probability | |
| 138 | Find the Best Gini-Based Split for a Binary Decision Tree | medium | Machine Learning | |
| 139 | Elastic Net Regression via Gradient Descent | medium | Machine Learning | |
| 140 | Bernoulli Naive Bayes Classifier | medium | Machine Learning | |
| 142 | Gridworld Policy Evaluation | medium | Reinforcement Learning | |
| 143 | Instance Normalization (IN) Implementation | medium | Deep Learning | |
| 144 | Apriori Frequent Itemset Mining | medium | Machine Learning | |
| 149 | Adadelta Optimizer | medium | Deep Learning | |
| 151 | Dropout Layer | medium | Deep Learning | |
| 152 | Implementing ROUGE Score | medium | Machine Learning | |
| 155 | CosineAnnealingLR Learning Rate Scheduler | medium | Machine Learning | |
| 157 | Implement the Bellman Equation for Value Iteration | medium | Reinforcement Learning | |
| 158 | Epsilon-Greedy Action Selection for n-Armed Bandit | medium | Reinforcement Learning | |
| 159 | Incremental Mean for Online Reward Estimation | medium | Reinforcement Learning | |
| 160 | Mixed Precision Training | medium | Machine Learning | |
| 161 | Exponential Weighted Average of Rewards | medium | Reinforcement Learning | |
| 163 | Gradient Bandit Action Selection | medium | Reinforcement Learning | |
| 166 | Evaluate Expected Value in a Markov Decision Process | medium | Reinforcement Learning | |
| 169 | Implement AdamW Optimizer Step | medium | Optimization | |
| 170 | Muon Optimizer Step with Matrix Preconditioning | medium | Optimization | |
| 171 | Minimax Algorithm for Tic-Tac-Toe | medium | Game Theory | |
| 172 | Muon Optimizer Update with Newton-Schulz Iteration | medium | Deep Learning | |
| 173 | Implement K-Nearest Neighbors | medium | Machine Learning | |
| 175 | Implement the SARSA Algorithm on policy | medium | Reinforcement Learning | |
| 176 | Chi-square Probability Distribution | medium | Probability |
3. Hard⚓︎
| ID | Title | Difficulty | Category | Status |
|---|---|---|---|---|
| 12 | Singular Value Decomposition (SVD) | hard | Linear Algebra | |
| 13 | Determinant of a 4x4 Matrix using Laplace's Expansion (hard) | hard | Linear Algebra | |
| 20 | Decision Tree Learning | hard | Machine Learning | |
| 21 | Pegasos Kernel SVM Implementation | hard | Machine Learning | |
| 28 | SVD of a 2x2 Matrix using eigen values & vectors | hard | Linear Algebra | |
| 38 | Implement AdaBoost Fit Method | hard | Machine Learning | |
| 40 | Implementing a Custom Dense Layer in Python | hard | Deep Learning | |
| 62 | Implement a Simple RNN with Backpropagation Through Time (BPTT) | hard | Deep Learning | |
| 63 | Implement the Conjugate Gradient Method for Solving Linear Systems | hard | Linear Algebra | |
| 85 | Positional Encoding Calculator | hard | Deep Learning | |
| 88 | GPT-2 Text Generation | hard | NLP | |
| 94 | Implement Multi-Head Attention | hard | Deep Learning | |
| 101 | Implement the GRPO Objective Function | hard | Reinforcement Learning | |
| 105 | Train Softmax Regression with Gradient Descent | hard | Machine Learning | |
| 106 | Train Logistic Regression with Gradient Descent | hard | Machine Learning | |
| 122 | Policy Gradient with REINFORCE | hard | Reinforcement Learning | |
| 125 | Implement a Sparse Mixture of Experts Layer | hard | Deep Learning | |
| 130 | Implement a Simple CNN Training Function with Backpropagation | hard | Deep Learning | |
| 137 | Implement a Dense Block with 2D Convolutions | hard | Deep Learning | |
| 164 | Gambler's Problem: Value Iteration | hard | Reinforcement Learning | |
| 174 | Train a Simple GAN on 1D Gaussian Data | hard | Deep Learning |
Reference and Resources⚓︎
Below is the list of internet online website and offline resources, used to practice
- https://www.deep-ml.com/problems
- https://www.deep-ml.com/deep-0
- https://machinelearningmastery.com/#