Concept Interview Questions

Mayank M. - "There are 2 main methods Intrinsic Evaluation i) Preplexity ii) BLEU Extrinsic Evaluation i) Response consistency/ Correctness / Factual score/ Security However, this question requires a follow-up question and clarification about where we are going to use the LLM models."See full answer

Anchal V. - "supervised learning: model is trained on the labeled data unsupervised learning: no labels provided - model learns by finding patterns , structure and groupings in the data. Semi-supervised learning: use small set of labels to guide learning for the larger pool of unlabeled data. reinforcement learning: leans by interacting with students the environment, receives reward and penalties based on actions self supervised: no labelled data . The model makes its own practice problems by"See full answer

Raja raghudeep E. - "There can be multiple effects on adjusting the context window of LLM, some I can think of are below: If window size is large then more tokens are in context which could increase memory and compute costs because of O(n2) attention complexity. Larger window can help in better responses in multi turn conversations but attention dilution can also happen."See full answer

Amney M. - "it is really good explanation thanks it is really good explanation thanks"See full answer

Amy M. - "Clarifying questions: Do we want to focus on front end or backend? Front end Do we want to focus on any particular platform? For ex: Site, mobile, apps Interviewer: Desktop Is there anything tools on gmail that you'd like me to focus on? For ex: Meet, Hangouts, Notes Interviewer: Just the main product Are there any specific product buckets that you'd like me to go through? For ex: Sign up flows, login flows, security, product experience, sign out flow, recommend"See full answer

Megha V. - "Gradient Descent is an optimisation strategy used in several supervised learning models. It is the technique for finding the optimum solution of an objective function. Typically, for a linear regression use case, it is used to find the weights and bias that produce the lowest loss. It involves computing the partial derivative of the objective function with respect to the weight and bias vectors. To find the optima of the function, the derivative is equated to 0, and iteratively the weight and b"See full answer

Louie Z. - "DNNs can learn hierarchical features, with each layer learning progressively more abstract features, and generalizes better. SNNs are better for simplier problems involving smaller datasets and if low latency is required."See full answer

Maedu E. - "Imagine a blockchain as a magical, unchangeable diary that keeps track of all the candies you share with your friends. Whenever you share a candy, you write it down in this special diary, and your friends also write it down in their diaries. But here's the cool part – all the diaries are connected and can talk to each other! So, when you want to know who has borrowed your candy or if you borrowed candy from someone else, you just check this special diary. It shows you the history of all the can"See full answer

Anonymous Aardvark - "in simple words, linear regression helps in predicting the value whereas logistics regression helps in predicting the binary classification. But lets talk through some example Linear regression model: E-commerce website pricing recommendation engine is built on linear regression model where we do have some variables such as competitor price, internal economics and consumer demand etc when we put this in a supervised learning model, it helps in predicting prices Logistics regression model"See full answer