system design for ads filtering system
Applied Scientist Interview Questions
1,182 applied scientist interview questions shared by candidates
Coding, case study
ML: 1. Data Imbalance 2. Unsupervised Learning 3. Evaluation Metric 4. Detection 5. ResNet 6. Transformer ... Coding: 1. Alien Dictionary
Problem Solving on Data structure and algorithm
Hypothesis testing and bayed theorem.
Equations for: SGD, Momentum, L1 and L2 loss, linear regression etc. Statistics deep dive: maximum likelihood estimates, hypothesis testing, PDF etc. Deep Learning: number of parameters in a model, coding Conv, MaxPool and embedding layer etc
The interview questions are confidential
Describe PCA , Regression, regression metrics, logistic regression, bias variance tradeoff, regularization techniques
Problem: Top K Most Similar Documents You are given: an integer array queryEmb of length D, representing a query embedding a 2D integer array docEmbs of size N x D, representing N document embeddings an integer k All embeddings are already L2-normalized. The cosine similarity between two normalized vectors is equal to their dot product. Return the indices of the k documents with the highest cosine similarity to queryEmb, ordered from most similar to least similar. If k > N, return all document indices sorted by similarity. Function Signature def topKSimilar(queryEmb: np.ndarray, docEmbs: np.ndarray, k: int) -> np.ndarray
How can you convince me that a number is irrational?
Viewing 951 - 960 interview questions
See Interview Questions for Similar Jobs
Deep Learning ScientistMl EngineerData Scientist NlpSenior Machine Learning ScientistDeep Learning Data ScientistApplied Research ScientistNlp Data ScientistAi Machine Learning EngineerDeep Learning Research EngineerApplied ResearchJr Data ScientistArtificial Intelligence ScientistData Scientist TraineeDeep Learning / Machine Learning ResearcherJunior Machine Learning EngineerApplied Machine Learning EngineerSenior Machine Learning EngineerMachine Learning Researcher