Concept Interview Questions

Alex N. - "Perplexity - the measure LLM is surprised when it predicts next word. For example: I love to eat --- if LLM selects as next word "fruits" it will be less surprising than if LLM selects as next word "metal". It is better to have lower perplexity score. Cross Entropy is the measure how well model match true labels. So if the next word is "cat" and LLM assigns 0.5 to it then cross entropy value is -log(0.5) = 0.69 and if it assigns 0.9 probability to word cat then cross entropy value is - log(0.9"See full answer

Anonymous Partridge - "We will have to use a second more powerful LLM Model to validate the answers. LLM as a judge"See full answer

Alex N. - "The adjusting context window size in LLM change trade off between reasoning capability, accuracy, computation cost. It influence how attention mechanist allocate resources across the input. Longer context window let it you input greater number of words and have more context to generate proper next token. However llms have lost in the middle issue. They remember the beginning of text and end of text but lost information located in the middle of long input. Another problem is Attention Dilution."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

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

Hardik saurabh G. - "Hallucinations are evaluated by measuring how often generated outputs contain information that is not supported by trusted sources. what hallucination means in context: Intrinsic hallucination: contradicts provided context Extrinsic hallucination: introduces unsupported facts Fabrication: confidently incorrect answers"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

J R. - "These are a set of utilities used to manage the heap memory as part of an application. The C standard library implements these functions. malloc(bytes) takes a number of bytes and returns a pointer to the start of the allocated buffer. If the allocation failed, a null pointer is returned instead. calloc(count, size) behaves like malloc(count * size), but also zero-initializes the allocated buffer, assuming the allocation succeeded. realloc(ptr, size) takes a pointer to a previously al"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

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

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

Will I. - "Is it bad to get the answer a different way? Will they mark that as not knowing Bayes Theorem or just correct as it is an easier way to get the answer? The way I went is to look at what happens when the factory makes 100 light bulbs. Machine A makes 60 of which 3 are faulty, Machine B makes 40 of which 1.2 are faulty. Therefore the pool of faulty lightbulbs is 3/4.2 = 5/7 from machine A and 1.2/4.2 = 3/7 from Machine B."See full answer

Sue G. - "Abstract class A class that can have Abstract methods - without implementations and Concerete Methods i.e with implementation. Can have private, protected and public access modifiers. Supports Single inheritance i.e a class can extend only 1 abstract class Can have constructors Mainly used when sharing common behaviors Interface Class A collection of abstract methods ( can have static and default methods also - onwards of java 8) Public, static, final are the access"See full answer

Erjan G. - "1) select avg(session) from table where session> 180 2) select round(sessiontime/300)*300 as sessionbin, count() as sessioncount from table group by round(sessiontime/300)300 order by session_bin 3) SELECT t1.country AS country_a, t2.country AS country_b FROM ( SELECT country, COUNT(*) AS session_count FROM yourtablename GROUP BY country ) AS t1 JOIN ( SELECT country, COUNT(*) AS session_count FROM yourtablename `GROUP BY countr"See full answer