Day 1

Q1. What is the difference between AI, Data Science, ML, and DL?
Q2. What is the difference between supervised learning, unsupervised learning
and Reinforcement learning?
Q3. Describe the general architecture of Machine learning.
Q4. What is Linear Regression?
Q5. OLS Stats Model (Ordinary Least Square)
Q6. What is L1 Regularization (L1 = lasso)?
Q7. L2 Regularization (L2 = Ridge Regression)
Q8. What is R square (where to use and where not)?
Q9. What is Mean Square Error?
Day 2
Q1. What is Logistic Regression?
Q2. Difference between logistic and linear regression?
Q3. Why we can’t do a classification problem using Regression?
Q4. What is Decision Tree?
Q5. Entropy, Information Gain, Gini Index, Reducing Impurity?
Q6. How to control leaf height and Pruning?
Q7. How to handle a decision tree for numerical and categorical
data?
Q8. What is the Random Forest Algorithm?
Q9. What is Variance and Bias tradeoff?
Q10. What are Ensemble Methods?
Q11. What is SVM Classification?
Q11. What is Naive Bayes Classification and Gaussian Naive Bayes
Q12. What is the Confusion Matrix?
Q13. What is Accuracy and Misclassification Rate?
Q14. True Positive Rate & True Negative Rate
Q15. What is False Positive Rate & False negative Rate?
Q16. What are F1 Score, precision and recall?
Q17. What is RandomizedSearchCV?
Q18. What is GridSearchCV?
Q19. What is BaysianSearchCV?
Q20. What is ZCA Whitening?
Day 3
Q1. How do you treat heteroscedasticity in regression?
Q2. What is multicollinearity, and how do you treat it?
Q3. What is market basket analysis? How would you do it in Python?
Q4. What is Association Analysis? Where is it used?
Q5. What is KNN Classifier ?
Q6. What is Pipeline in sklearn ?
Q7. What is Principal Component Analysis(PCA), and why we do?
Q8. What is t-SNE?
Q9. VIF(Variation Inflation Factor),Weight of Evidence & Information Value.
Why and when to use?
Q10: How to evaluate that data does not have any outliers ?
Q11: What you do if there are outliers?
Q12: What are the encoding techniques you have applied with Examples ?
Q13: Tradeoff between bias and variances, the relationship between them.
Q14: What is the difference between Type 1 and Type 2 error and severity of the
error?
Q15: What is binomial distribution and polynomial distribution?
Q16: What is the Mean Median Mode standard deviation for the sample and
population?
Q17: What is Mean Absolute Error ?
Q18: What is the difference between long data and wide data?
Q19: What are the data normalization method you have applied, and why?
Q20: What is the difference between normalization and Standardization with
example?
Day 4
Q1. What is upsampling and downsampling with examples?
Q2. What is the statistical test for data validation with an example, Chi-square, ANOVA
test, Z statics, T statics, F statics, Hypothesis Testing?
Q3. What is the Central limit theorem?
Q4. What is the correlation and coefficient?
Q5: What is the difference between machine learning and deep learning?
Q6: What is perceptron and how it is related to human neurons?
Q7: Why deep learning is better than machine learning?
Q8: What kind of problem can be solved by using deep learning?
Q9: List down all the activation function using mathematical Expression and example.
What is the activation function?
Q10: Detail explanation about gradient decent using example and Mathematical
expression?
Q11: What is backward propagation?
Q12: How we assign weights in deep learning?
Q13: What is optimiser is deep learning, and which one is the best?
Q14: What is gradient descent, mini-batch gradient descent, batch gradient decent,
stochastic gradient decent and adam?
Q15: What are autoencoders?
Q16: What is CNN?
Q17: What is pooling, padding, filtering operations on CNN?
Q18: What is the Evolution technique of CNN?
Q19: How to initialise biases in deep learning?
Q20: What is learning Rate?
Day 5
Q1: What are Epochs?
Q2. What is the batch size?
Q3: What is dropout in Neural network?
Q4: List down hyperparameter tuning in deep learning
Q5: What do you understand by activation function and error functions?
Q6: Why do we need Non-linear activation functions?
Q7: What do you under by vanishing gradient problem and how can Do we solve that?
Q8: What is Transfer learning in deep learning ?
Q9: What is VGG16 and explain the architecture of VGG16?
Q10: What is RESNET?
Q11: What is ImageNet?
Q12: What is DarkNet?
Q13: What is YOLO and explain the architecture of YOLO (you only Look Once). One use case?
Day 6:
Q1. What is NLP?
Q2. What are the Libraries we used for NLP?
Q3. What do you understand by tokenisation?
Q4. What do you understand by stemming?
Q5. What is lemmatisation?
Q6. What is Bag-of-words model?
Q7.What do you understand by TF-IDF?
Q8. What is Word2vec? Continuous Bag-of-Words (CBOW)
Q9. What is Doc2vec?
Q9. What is Time-Series forecasting?
Q10. What is the difference between in Time series and regression?
Q11. What is the difference between stationery and non- stationary data?
Q12. Why you cannot take non-stationary data to solve time series Problem?
Day 7
Q1. What is the process to make data stationery from non-stationary in time series?
Q2. What is the process to check stationary data ?
Q3. What are ACF and PACF?.
Q4. What do you understand by the trend of data?
Q5. What is the Augmented Dickey-Fuller Test?
Q6. What is AIC and BIC into time series?
Q7. What are the components of the Time -Series?
Q8. What is Time Series Analysis?
Q9. Give some examples of the Time-Series forecast?
Q10. What are the techniques of Forecasting?
Q11. What is the Moving Average?
Q12. What is Exponential smoothing?
Day 8
Q1. What is Tensorflow?
Q2. What are Tensors?
Q3. What is TensorBoard?
Q4. What are the features of TensorFlow?
Q5. What are the advantages of TensorFlow?
Q6. List a few limitations of Tensorflow.
Q7. What are the use cases of Tensor flow?
Q8. What are the very important steps of Tensorflow architecture?
Q9. What is Keras?
Q10. What is a pooling layer?
Q11. What is the difference between CNN and RNN?
Q12. What are the benefits of Tensorflow over other libraries?
Day 9
Q1: How would you define Machine Learning?
Q2. What is a labeled training set?
Q3. What are the two common supervised tasks?
Q4. Can you name four common unsupervised tasks?
Q5. What type of Machine Learning algorithm we use to allow a robot to walk in various
unknown terrains?
Q6. What type of algorithm would we use to segment your customers into multiple
groups?
Q7: What is an online machine learning?
Q8: What is out-of-core learning?
Q9. What is the Model Parameter?
Q11: What is Model Hyperparameter?
Q12. What is cross-validation?
Day 10
Q1. What is a Recommender System?
Q2. Compare SAS, R and Python programming?
Q3. Why is important in data analysis?
Q4. What are the various aspects of a Machine Learning process?
Q4. What is Interpolation and Extrapolation?
Q5. What does P-value signify about the statistical data?
Q6. During analysis, how do you treat missing values?
Q7. Explain the difference between a Test Set and a Validation Set?
Q8. What is the curse of dimensionality? Can you list some ways to deal with it?
Q9. What is data augmentation? Can you give some examples?
Q10. What is stratified cross-validation and when should we use it?
Day 11
Q1. What are tensors?
Q2. Define the concept of RNN?
Q3. What is a ResNet, and where would you use it? Is it efficient?
Q4. Transfer learning is one of the most useful concepts today. Where can it be
used?
Q5. What does tuning of hyperparameters signify? Explain with examples.
Q6. Why are deep learning models referred as black boxes?
Q7. Why do we have gates in neural networks?
Q8. What is a Sobel filter?
Q9. What is the purpose of a Boltzmann Machine?
Q10. What are the types of weight initialization?
Day 12
Q1. Where is the confusion matrix used? Which module would you use to show it?
Q2: What is Accuracy?
Q3: What is Precision?
Q4: What is Recall?
Q5: What is F1 Score?
Q6: What is Bias and Variance trade-off?
Q7. What is data wrangling? Mention three points to consider in the process.
Q8. Why is normalization required before applying any machine learning model? What
module can you use to perform normalization?
Q9. What is the difference between feature selection and feature extraction?
Q10. Why is polarity and subjectivity an issue?
Q11. When would you use ARIMA?
Day 13
Q1. What is Autoregression?
Q2. What is Moving Average?
Q3. What is Autoregressive Moving Average (ARMA)?
Q4. What is Autoregressive Integrated Moving Average (ARIMA)?
Q5.What is SARIMA (Seasonal Autoregressive Integrated Moving-Average)?
Q6. What is Seasonal Autoregressive Integrated Moving-Average with Exogenous
Regressors (SARIMAX)?
Q7. What is Vector autoregression (VAR)?
Q8. What is Vector Autoregression Moving-Average (VARMA)?
Q9. What is Vector Autoregression Moving-Average with Exogenous Regressors
(VARMAX)?
Q10. What is Simple Exponential Smoothing (SES)?
Day 14
Q1. What is Alexnet?
Q2. What is VGGNet?
Q3. What is VGG16?
Q4. What is ResNet?
Q5. What is HAAR CASCADE?
Q6. What is Transfer Learning?
Q7. What is Faster, R-CNN?
Q8. What is RCNN?
Q9.What is GoogLeNet/Inception?
Q10. What is LeNet-5?
Day 15
Q1. What is Autoencoder?
Q2. What Is Text Similarity?
Q3. What is dropout in neural networks?
Q4. What is Forward Propagation?
Q5. What is Text Mining?
Q6. What is Information Extraction?
Q7. What is Text Generation?
Q8. What is Text Summarization?
Q9. What is Topic Modelling?
Q10.What is Hidden Markov Models?
Day 16
Q1.What is Statistics Learning?
Q2. What is ANOVA?
Q3. What is ANCOVA?
Q4. What is MANOVA?
Q5. What is MANCOVA?
Q6. Explain the differences between KNN classifier and KNN regression
methods.
Q7. What is t-test?
Q8. What is Z-test?
Q9. What is Chi-Square test?
Q10. What is correlation and the covariance in the statistics?
Day 17
Q1. What is ERM (Empirical Risk Minimization)?
Q2. What is PAC (Probably Approximately Correct)?
Q3. What is ELMo?
Q4. What is Pragmatic Analysis in NLP?
Q5. What is Syntactic Parsing?
Q6. What is ULMFit?
Q7. What is BERT?
Q8.What is XLNet?
Q9. What is the transformer?
Q10. What is Text summarization?
Day 18
Q1. What is Levenshtein Algorithm?
Q2. What is Soundex?
Q3. What is Constituency parse?
Q4. What is LDA(Latent Dirichlet Allocation)?
Q5.What is LSA?
Q6. What is PLSA?
Q7. What is LDA2Vec?
Q8. What is Expectation-Maximization Algorithm(EM)?
Q9.What is Text classification in NLP?
Q10. What is Word Sense Disambiguation (WSD)?
Day 19
Q1. What is LSI(Latent Semantic Indexing)?
Q2. What is Named Entity Recognition? And tell some use cases of NER?
Q3. What is perplexity?
Q4. What is the language model?
Q5. What is Word Embedding?
Q6. Do you have an idea about fastText?
Q7. What is GloVe?
Q8. Explain Gensim?
Q9. What is Encoder-Decoder Architecture?
Q10. What is Context2Vec?
Day 20
Q1. Do you have any idea about Event2Mind in NLP?
Q2. What is SWAG in NLP?
Q3. What is the Pix2Pix network?
Q4. Explain UNet Architecture?
Q5. What is pair2vec?
Q6. What is Meta-Learning?
Q7. What is ALiPy(Active Learning in Python)?
Q8. What is the Lingvo model?
Q9. What is Dropout Neural Networks?
Q10. What is GAN?
Day 21
Q1. Explain Grad-CAM architecture?
Q2. Explain squeeze-net architecture?
Q3. ZFNet architecture
Q4. What is NAS (Neural Architecture Search)?
Q5. What is SENets?
Q6. Feature Pyramid Network (FPN)
Q7. DeepID-Net( Def-Pooling Layer)
Q8. What is FractalNet Architecture?
Q9. What is the SSPNet architecture?
Day 22
Q1. Explain V-Net (Volumetric Convolution) Architecture with related to
Biomedical Image Segmentation?
Q2. Highway Networks- Gating Function to highway
Q3. What is DetNAS: Neural Architecture Search(NAS) on Object
Detection?
Q4. You have any idea about ECE (Emotion cause extraction)
Q5. What is DST (Dialogue state tracking)?
Q6. What is NMT(Neural machine translation)?
Q7. What is Character-Level models (CLM)?
Q8. What is LexNLP package?
Q9. Explain The Architecture of LeNet-5.
Day 23
Q1. Explain Overfeat in Object detection.
Q2. What is Multipath: Multiple Probabilistic Anchor Trajectory Hypotheses for
Behavior Prediction?
Q3. An Object detection approach using MR-CNN
Q4. Object detection using Segmentation-aware CNN
Q5. What is CRAFT (Object detection)?
Q6. Explain YOLOv1 for Object Detection.
Q7. Adversarial Examples Improve Image Recognition
Q8. Advancing NLP with Cognitive Language Processing Signals
Q8. Do you have any idea how can we use NLP on News headlines to predict
index trends?
Day 24
Q1. What is STN?
Q2. What is decaNLP?
Q3. Universal Transformers
Q4. What is StarSpace in NLP?
Q5. TransferTransfo in NLP
Q6. Wizard of Wikipedia: Knowledge-Powered Conversational
Q7. ERASER: A Benchmark to Evaluate Rationalized NLP Models
Q8. End to End memory networks
Q9. What is LinkNet?
Day 25
Q1. What is WRN?
Q2. What is SIMCO: SIMilarity-based object Counting?
Q3. What is Voice-Face Cross-modal Matching and Retrieval?
Q4. What is CenterNet: Object Detection with Keypoint Triplets
Q5. What is Task2Vec: Task Embedding for Meta-Learning?
Q6. What is GLMNet: Graph Learning-Matching Networks for Feature
Matching?
Q7. What is SSAP: Single-Shot Instance Segmentation With Affinity
Pyramid?
Q8. What is TENER: Adapting Transformer Encoder for Name Entity
Recognition?
Q9. What is Subword ELMo?
Day 26
Q1. What is DCGANs (Deep Convolutional Generative Adversarial
Networks)?
Q2. Explain EnAET.
Q3. What is Data Embedding Learning?
Q4. Do you have any idea about Rookie?
Q5. SECRET: Semantically Enhanced Classification of Real-world Tasks
Q6. Semantic bottleneck for computer vision tasks
Q7. Gender Bias in Neural Natural Language Processing
Q8. DSReg: Using Distant Supervision as a Regularizer
Q9. What is Multimodal Emotion Classification?
Day 27
Q1. Learning to Caption Images with Two-Stream Attention and Sentence Auto-
Encoder
Q2. Explain PQ-NET.
Q3. What is EDIT?
Q4. What is Doctor2Vec?
Q5. Explain PAG-Net.
Q6. An End-to-End Audio Classification System based on Raw Waveforms and
Mix-Training Strategy
Q7. What is Cnak? : Cluster Number Assisted K-means
Q8. What is D3S?
Q9. What is DRNet?
Day 28
Q1. Explain StructEdit(Learning Structural Shape Variations).
Q2. EmpGAN: Multi-resolution Interactive Empathetic Dialogue Generation
Q3. G-TAD: Sub-Graph Localization for Temporal Action Detection
Q4. What is F3Net?
Q5. Natural Language Generation using Reinforcement Learning with
External Rewards
Q6. LaFIn: Generative Landmark Guided Face Inpainting
Q7. Image2StyleGAN++: How to Edit the Embedded Images?
Q8. oops! Predicting Unintentional Action in Video
Q9. FairyTED: A Fair Rating Predictor for TED Talk Data
Day 29
Q1. What is SuperGlue?
Q2. What is MixNMatch?
Q3. FAN: Feature Adaptation Network
Q5. WSOD with PSNet and Box Regression
Q6. Autonomous Driving Assistance Systems (ADAS) and Vehicle
Automation.
Q7. Robot Learning and Execution of Collaborative Manipulation
Plans from YouTube Videos.
Q8. JEC-QA: A Legal-Domain Question Answering Dataset
Q9. SpoC: Spoofing Camera Fingerprints
Day 30
Q1. Tell me about your current project.
Q2. What was the size of the data?
Q3. What was the data type?
Q4. What was the team size and distribution?
Q5. What Hadoop distribution were you using?
Q6. What is the version of distribution?
Q7. What was the size of the cluster?
Q8. How many nodes were there in all the Dev, UAT, and Prod
environments?
Q9. How were you creating and maintaining the logs?
Q10.What techniques were you using for data pre-processing for
various data science use cases and visualization?
Q11. How were you maintaining the failure cases?
Q12. What kind of automation have you done for data processing
Q13. Have you used any scheduler?
Q14. How are you monitoring your job?
Q15. What were your roles and responsibilities in the project?