Sign in Start Learning

← Question Bank

Deep Learning & Generative AI

Sequence Modelling Interview Questions and Answers

Interview questions on Sequence Modelling Interview Questions and Answers.

2 questions

All subtopics Recurrent Neural Networks (RNNs)Gated Architectures (LSTM & GRU)Sequence-to-Sequence & Attention Mechanisms Transformers & Self-Attention Training Dynamics & Challenges

Transformers & Self-Attention

Q1. What is Scaled Dot-Product Attention in Transformers, and why is scaling factor $\sqrt{d_k}$ necessary?

Sign in to bookmark

Transformers & Self-Attention

Q2. Why do Transformers require Positional Encodings?

Sign in to bookmark