BYJU'S Interview Questions and Answers

Build an airline system to recommend routes from city 1 to city 2 with direct and connecting flights.

• Create a graph with cities as nodes and connections as edges

• Use Dijkstra's algorithm to find shortest path between city 1 and city 2

• For connecting flights, find all possible paths with one or more stops

• Sort and recommend routes based on total distance and number of stops

Optimizers exist in FFNs to update weights, but many exist due to different optimization techniques and trade-offs.

• Different optimizers use different optimization techniques such as momentum, adaptive learning rates, and regularization.

• Optimizers have different trade-offs such as convergence speed, generalization, and robustness to noisy data.

• The choice of optimizer depends on the specific problem and data set.

• Examples of optimizers include SGD, Adam, Adagrad, and RMSprop.

This function takes a string input and returns all possible combinations of characters in that string without repeated letters.

• Use the itertools module to generate all possible permutations of the string.

• Filter out the permutations that have repeated letters using a set.

• Convert the filtered permutations into a list of strings.

Layer normalisation is a technique used to normalise the inputs to each layer of a feedforward neural network.

• It is similar to batch normalisation but normalises the inputs to each layer instead of the entire batch.

• It helps in reducing the internal covariate shift problem.

• It can be applied to any type of activation function.

• It is particularly useful in recurrent neural networks.

• Example: LayerNorm in PyTorch.

Effort estimation is the process of predicting the amount of time, resources, and cost required to complete a project or task.

• Effort estimation is crucial for project planning and management.

• It involves breaking down the project into smaller tasks and estimating the time and resources required for each task.

• Various techniques can be used for effort estimation, such as expert judgment, historical data analysis, and parametric modeling.

• Factors that can affect effort estimation ...read more

The project life cycle consists of initiation, planning, execution, monitoring and control, and closure.

• Initiation: Defining the project scope, objectives, and stakeholders.

• Planning: Developing a detailed project plan, including timelines, budget, and resources.

• Execution: Implementing the project plan and completing the work.

• Monitoring and Control: Tracking progress, identifying and managing risks, and making necessary adjustments.

• Closure: Completing the project, delivering t...read more

A WBS is a hierarchical breakdown of project deliverables into smaller, manageable components.

• WBS is used to organize and define the scope of a project

• It breaks down the project into smaller, more manageable components

• Each component is called a work package

• The WBS is hierarchical, with the top level being the project deliverable and the lower levels being the work packages

• It helps in estimating project costs, time and resources required

• Example: WBS for building a house - Leve...read more

Text embedding is a technique to convert text data into numerical vectors for machine learning models.

• Text embedding captures semantic meaning of words in a continuous vector space.

• Popular methods include Word2Vec, GloVe, and BERT.

• Embeddings can be pre-trained or learned from scratch depending on the task.

• They are used in NLP tasks like sentiment analysis, text classification, and machine translation.