🤖 Top AI Interview Questions: Part-1
Brush up your AI knowledge with these essential interview questions and answers.
Artificial Intelligence (AI) is the branch of computer science that focuses on building machines or systems that can perform tasks that typically require human intelligence — such as understanding language, recognizing images, making decisions, and learning from data.
- AI: The broad concept of machines simulating human intelligence.
- Machine Learning (ML): A subset of AI that enables systems to learn from data and improve over time without being explicitly programmed.
- Deep Learning (DL): A subfield of ML that uses neural networks with many layers to model complex patterns, especially in images, audio, and text.
- Supervised Learning: The model learns from labeled data (input-output pairs). Example: Predicting house prices from past data.
- Unsupervised Learning: The model finds patterns in data without labels. Example: Grouping customers based on buying behavior (clustering).
- Overfitting: The model learns noise and details in the training data, performing poorly on new data.
- Underfitting: The model is too simple to capture the data patterns and performs poorly on both training and testing data.
- A good model generalizes well to unseen data.
- Classification: Predicts discrete labels. Example: Email spam detection (spam or not).
- Regression: Predicts continuous values. Example: Predicting stock price or temperature.
A table used to evaluate the performance of a classification model by comparing predicted vs. actual results.
Shows: True Positives (TP), True Negatives (TN), False Positives (FP), False Negatives (FN)
- Precision: TP / (TP + FP) → How many predicted positives are correct.
- Recall: TP / (TP + FN) → How many actual positives are captured.
- F1-Score: Harmonic mean of precision and recall. Useful for imbalanced datasets.
- Batch Learning: Trained on the entire dataset at once.
- Online Learning: Updated incrementally as new data arrives — useful for real-time systems.
- Bias: Error from incorrect assumptions (underfitting).
- Variance: Error from model sensitivity to training data (overfitting).
- Goal: Balance both to minimize total error.
Decide whether a neuron should fire. Introduce non-linearity into the network.
Common types:
- ReLU: max(0, x)
- Sigmoid: squashes values between 0 and 1
- Tanh: squashes between -1 and 1
Comments (0)
No comments yet
Be the first to share your thoughts!
Leave a Comment