Svamaan Financial Services Learning and Development Lead Interview Questions and Answers

Q1. Difference between BERT and GPT
Ans. 
BERT is bidirectional, GPT is unidirectional. BERT uses transformer encoder, GPT uses transformer decoder.
• BERT is bidirectional, meaning it can look at both left and right context in a sentence. GPT is unidirectional, it can only look at the left context.

• BERT uses transformer encoder architecture, while GPT uses transformer decoder architecture.

• BERT is pretrained on masked language model and next sentence prediction ta...read more
Answered by AI
Add your answer
Q2. Explain the attention mechanism
Ans. 
Attention mechanism allows models to focus on specific parts of input sequence when making predictions.
• Attention mechanism helps models to weigh the importance of different parts of the input sequence.

• It is commonly used in sequence-to-sequence models like machine translation.

• Examples include Bahdanau Attention and Transformer models.
Answered by AI
Add your answer
Q3. Bias and variance trade off
Add your answer
Q4. How to deal if the distribution of a variable is skewed
Ans. 
To deal with skewed distribution of a variable, transformations like log, square root, or box-cox can be applied.
• Apply log transformation to reduce right skewness

• Apply square root transformation to reduce left skewness

• Apply box-cox transformation for a more generalized approach

• Consider removing outliers before applying transformations
Answered by AI
Add your answer

Python code to determine the least common sub word in a given list with strings