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

Nathan B. - "There are many good answers to this that AI scientists around the world, I and my coworkers have tried over the years. For one, RAG is a great option to fact-check and enforce citation generation, update the data in the knowledge base of the generative AI, etc. "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

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

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

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