Interview Questions:
- How is machine learning different from general programming?
- What is Overfitting in Machine Learning and how can it be avoided?
- Why do we perform normalization?
- What is the difference between precision and recall?
- What is the bias-variance tradeoff?
- What is Principal Component Analysis?
- What is one-shot learning?
- What is the difference between stochastic gradient descent (SGD) and gradient descent (GD)?
- What is the Central Limit theorem?
- Explain the working principle of SVM.
- What is the difference between L1 and L2 regularization? What is their significance?
- What is the purpose of splitting a given dataset into training and validation data?
- Why removing highly correlated features are considered a good practice?
- Reverse a linked list in place.
- What is the reason behind the curse of dimensionality?
- What is Linear Discriminant Analysis?
- Can you explain the differences between supervised, unsupervised, and reinforcement learning?
- What are convolutional networks? Where can we use them?
- What is cost function?
- List different activation neurons or functions.
- Explain Epoch vs. Batch vs. Iteration.
- What is regularization, why do we use it, and give some examples of common methods?
- Explain why the performance of XGBoost is better than that of SVM?
- What is the difference between correlation and causality?
- What is stemming?
- What is Lemmatization?
- What is Static Memory Allocation?
- What are some tools used to discover outliers?
- What are some methods to improve inference time?