I have created an online quiz on Machine Learning and Deep Learning. This quiz contains objective type questions on various concepts of Machine Learning and Deep Learning.
Currently, there are 134 objective questions for machine learning and 205 objective questions for deep learning (total 339 questions). I will keep adding more and more questions to the quiz.
Machine Learning Quiz
Start Machine Learning Quiz
ML quiz contains objective questions on following Machine Learning concepts:
2. Data Wrangling: Missing values, Invalid and corrupted values, Outliers, Skewed data, Feature Scaling, Standardization, Normalization, Binning, Feature Encoding, Label Encoder, One Hot Encoder etc.
3. Dimensionality Reduction: Finding correlation, Feature Selection and Feature Extraction, PCA, t-SNE, SVD, LDA, MDS, ICA etc.
4. Algorithms: Supervised and Unsupervised Learning, Linear Regression, Logistic Regression, KNN, SVM, Naive Byes, Decision Tree, K-Means Clustering etc.
5. Overfitting: Overfitting, Underfitting, Bias, Variance, Cross-validation etc.
6. Ensemble Learning: Bagging, Boosting, Random Forest, Adaboost, GBM (Gradient Boosting Machine), XGBoost (Extreme Gradient Boosting) etc.
7. Regularization: Ridge Regression (L2 Regularization), Lasso Regression (L1 Regularization), Elastic Net Regression etc.
8. Accuracy Measurement: Confusion Matrix, Classification Report, Accuracy Score, F1 Score, Mean Absolute Error, Mean Square Error, Root Mean Square Error etc.
9. Python: Basic Datastructures, Libraries like Scikit Learn, Pandas, Numpy, Scipy, Seaborn, Matplotlib etc.
Deep Learning Quiz
DL quiz contains objective questions on following Deep Learning concepts:
1. Perceptrons: Working of a Perceptron, multi-layer Perceptron, advantages and limitations of Perceptrons, implementing logic gates like AND, OR and XOR with Perceptrons etc.
2. Neural Networks: Layers in a neural network, types of neural networks, deep and shallow neural networks, forward and backward propagation in a neural network etc.
3. Weights and Bias: Importance of weights and biases, things to keep in mind while initializing weights and biases, Xavier Weight Initialization technique etc.
4. Activation Functions: Importance of activation functions, Squashing functions, Step (Threshold), Logistic (Sigmoid), Hyperbolic Tangent (Tanh), ReLU (Rectified Linear Unit), Dying and Leaky ReLU, Softmax etc.
5. Batches: Epochs, Batches and Iterations, Batch Normalization etc.
6. Gradient Descent: Batch, Stochastic and Mini Batch Gradient Descent, SGD variants like Momentum, Nesterov Momentum, AdaGrad, AdaDelta, RMSprop and Adam, Local and Global Minima, Vanishing and Exploding Gradients, Learning Rate etc.
7. Loss Functions: categorical_crossentropy, sparse_categorical_crossentropy etc.
8. CNN: Convolutional Neural Network, Filters (Kernels), Stride, Padding, Zero Padding and Valid Padding, Pooling, Max Pooling, Min Pooling, Average Pooling and Sum Pooling, Hyperparameters in CNN, Capsule Neural Network (CapsNets), ConvNets vs CapsNets, Computer vision etc.
9. RNN: Recurrent Neural Network, Feedback loop, Types of RNN like One to One, One to Many, Many to One and Many to Many, Bidirectional RNN, Advantages and disadvantages of RNN, Applications of RNN, Differences between CNN and RNN etc.
10. LSTM: Long Short Term Memory, Gated cells like Forget gate, Input gate and Output gate, Applications of LSTM etc.
11. Regularization: Overfitting and underfitting in a neural network, L1 and L2 Regularization, Dropout, Data Augmentation, Early Stopping etc.
12. Fine-tuning: Transfer Learning, Fine-tuning a model, Steps to fine-tune a model, Advantages of fine-tuning etc.
13. Autoencoders: Components of an autoencoder like encoder, decoder and bottleneck, Latent space representation and reconstruction loss, Types of Autoencoders like Undercomplete autoencoder, Sparse autoencoder, Denoising autoencoder, Convolutional autoencoder, Contractive autoencoders and Deep autoencoders, Hyperparameters in an autoencoder, Applications of an Autoencoder, Autoencoders vs PCA, RBM (Restricted Boltzman Machine) etc.
14. NLP (Natural Language Processing): Tokenization, Stemming, Lemmatization and Vectorization (Count vectorization, N-grams vectorization, Term Frequency - Inverse Document Frequency (TF-IDF)), Document-term matrix, NLTK( Natural Language Toolkit) etc.
15. Frameworks: TesnorFlow, Keras, PyTorch, Theano, CNTK, Caffe, MXNet, DL4J etc.
Rules and Guidelines
1. All questions are objective type questions with 4 options. Only one option is correct.
2. 60 seconds are allotted for each question.
3. Correct answer gives you 4 marks and wrong answer takes away 1 mark (25% negative marking).
4. We will take short breaks during the quiz after every 10 questions.
5. Passing score is 75%. Quiz contains very simple Machine Learning objective questions, so I think 75% marks can be easily scored.
6. Please don't refresh the page or click any other link during the quiz.
7. Please don't use Internet Explorer to run this quiz.
Helplines
There are 4 helplines given in this quiz:
1. Weed Out
2. Blink
3. Magic Wand
4. Hands Up
You can use one helpline per question except "Hands Up". You can use each helpline 4 times during the quiz. Below is the description of all these helplines:
1. Weed Out
"Weed Out" helpline weeds out two incorrect options. So, now you have to guess the answer only from 2 options from which one is the right answer.
2. Blink
Keep your eyes wide open while using the "Blink" helpline. "Blink" helpline first lights the bulb against the right option and then in fraction of a second (100 milliseconds), it goes on lighting the bulbs against wrong options. So you have to identify against which option, the bulb was lighted first.
3. Magic Wand
This is the most flexible helpline in which you have nothing to do. Just click on the "Magic Wand" and you get the right answer magically.
4. Hands Up
By using "Hands Up" helpline, you are not adding up score but saving your quiz time. You can use it as many times you want. I would suggest you to use this helpline when you have exhausted all your other helplines. If you find a question whose answer is not clear to you, and you don’t have any helpline left, please don’t waste time on that question and just raise your hands to save your time.
Next Question
Once you are done with the question, you can go to the next question by using this option.
Quit Quiz
Quiz contains a lot of objective questions on Machine Learning which will take a lot of time and patience to complete. If you feel tired at any point of time and don't want to continue, you can just quit the quiz and your results will be displayed based on the number of questions you went through.
Quiz Results
At the end of the quiz, you will get your score and time taken to complete the quiz. You can take screenshot of the result for any future reference.
Currently, there are 134 objective questions for machine learning and 205 objective questions for deep learning (total 339 questions). I will keep adding more and more questions to the quiz.
Machine Learning Quiz
Start Machine Learning Quiz
ML quiz contains objective questions on following Machine Learning concepts:
1. Data Exploration and Visualization: Hypothesis Generation, Seaborn, Matplotlib, Bar Plot, Box Plot, Histogram, Heatmap, Scatter Plot, Regression Plot, Joint Plot, Distribution Plot, Strip Plot, Violin Plot, KDE, Pair Plot, Pair Grid, Facet Grid etc.
2. Data Wrangling: Missing values, Invalid and corrupted values, Outliers, Skewed data, Feature Scaling, Standardization, Normalization, Binning, Feature Encoding, Label Encoder, One Hot Encoder etc.
3. Dimensionality Reduction: Finding correlation, Feature Selection and Feature Extraction, PCA, t-SNE, SVD, LDA, MDS, ICA etc.
4. Algorithms: Supervised and Unsupervised Learning, Linear Regression, Logistic Regression, KNN, SVM, Naive Byes, Decision Tree, K-Means Clustering etc.
5. Overfitting: Overfitting, Underfitting, Bias, Variance, Cross-validation etc.
6. Ensemble Learning: Bagging, Boosting, Random Forest, Adaboost, GBM (Gradient Boosting Machine), XGBoost (Extreme Gradient Boosting) etc.
7. Regularization: Ridge Regression (L2 Regularization), Lasso Regression (L1 Regularization), Elastic Net Regression etc.
8. Accuracy Measurement: Confusion Matrix, Classification Report, Accuracy Score, F1 Score, Mean Absolute Error, Mean Square Error, Root Mean Square Error etc.
9. Python: Basic Datastructures, Libraries like Scikit Learn, Pandas, Numpy, Scipy, Seaborn, Matplotlib etc.
Deep Learning Quiz
1. Perceptrons: Working of a Perceptron, multi-layer Perceptron, advantages and limitations of Perceptrons, implementing logic gates like AND, OR and XOR with Perceptrons etc.
2. Neural Networks: Layers in a neural network, types of neural networks, deep and shallow neural networks, forward and backward propagation in a neural network etc.
3. Weights and Bias: Importance of weights and biases, things to keep in mind while initializing weights and biases, Xavier Weight Initialization technique etc.
4. Activation Functions: Importance of activation functions, Squashing functions, Step (Threshold), Logistic (Sigmoid), Hyperbolic Tangent (Tanh), ReLU (Rectified Linear Unit), Dying and Leaky ReLU, Softmax etc.
5. Batches: Epochs, Batches and Iterations, Batch Normalization etc.
6. Gradient Descent: Batch, Stochastic and Mini Batch Gradient Descent, SGD variants like Momentum, Nesterov Momentum, AdaGrad, AdaDelta, RMSprop and Adam, Local and Global Minima, Vanishing and Exploding Gradients, Learning Rate etc.
7. Loss Functions: categorical_crossentropy, sparse_categorical_crossentropy etc.
8. CNN: Convolutional Neural Network, Filters (Kernels), Stride, Padding, Zero Padding and Valid Padding, Pooling, Max Pooling, Min Pooling, Average Pooling and Sum Pooling, Hyperparameters in CNN, Capsule Neural Network (CapsNets), ConvNets vs CapsNets, Computer vision etc.
9. RNN: Recurrent Neural Network, Feedback loop, Types of RNN like One to One, One to Many, Many to One and Many to Many, Bidirectional RNN, Advantages and disadvantages of RNN, Applications of RNN, Differences between CNN and RNN etc.
10. LSTM: Long Short Term Memory, Gated cells like Forget gate, Input gate and Output gate, Applications of LSTM etc.
11. Regularization: Overfitting and underfitting in a neural network, L1 and L2 Regularization, Dropout, Data Augmentation, Early Stopping etc.
12. Fine-tuning: Transfer Learning, Fine-tuning a model, Steps to fine-tune a model, Advantages of fine-tuning etc.
13. Autoencoders: Components of an autoencoder like encoder, decoder and bottleneck, Latent space representation and reconstruction loss, Types of Autoencoders like Undercomplete autoencoder, Sparse autoencoder, Denoising autoencoder, Convolutional autoencoder, Contractive autoencoders and Deep autoencoders, Hyperparameters in an autoencoder, Applications of an Autoencoder, Autoencoders vs PCA, RBM (Restricted Boltzman Machine) etc.
14. NLP (Natural Language Processing): Tokenization, Stemming, Lemmatization and Vectorization (Count vectorization, N-grams vectorization, Term Frequency - Inverse Document Frequency (TF-IDF)), Document-term matrix, NLTK( Natural Language Toolkit) etc.
15. Frameworks: TesnorFlow, Keras, PyTorch, Theano, CNTK, Caffe, MXNet, DL4J etc.
1. All questions are objective type questions with 4 options. Only one option is correct.
2. 60 seconds are allotted for each question.
3. Correct answer gives you 4 marks and wrong answer takes away 1 mark (25% negative marking).
4. We will take short breaks during the quiz after every 10 questions.
5. Passing score is 75%. Quiz contains very simple Machine Learning objective questions, so I think 75% marks can be easily scored.
6. Please don't refresh the page or click any other link during the quiz.
7. Please don't use Internet Explorer to run this quiz.
Helplines
There are 4 helplines given in this quiz:
1. Weed Out
2. Blink
3. Magic Wand
4. Hands Up
You can use one helpline per question except "Hands Up". You can use each helpline 4 times during the quiz. Below is the description of all these helplines:
1. Weed Out
"Weed Out" helpline weeds out two incorrect options. So, now you have to guess the answer only from 2 options from which one is the right answer.
2. Blink
Keep your eyes wide open while using the "Blink" helpline. "Blink" helpline first lights the bulb against the right option and then in fraction of a second (100 milliseconds), it goes on lighting the bulbs against wrong options. So you have to identify against which option, the bulb was lighted first.
3. Magic Wand
This is the most flexible helpline in which you have nothing to do. Just click on the "Magic Wand" and you get the right answer magically.
4. Hands Up
By using "Hands Up" helpline, you are not adding up score but saving your quiz time. You can use it as many times you want. I would suggest you to use this helpline when you have exhausted all your other helplines. If you find a question whose answer is not clear to you, and you don’t have any helpline left, please don’t waste time on that question and just raise your hands to save your time.
Next Question
Once you are done with the question, you can go to the next question by using this option.
Quit Quiz
Quiz contains a lot of objective questions on Machine Learning which will take a lot of time and patience to complete. If you feel tired at any point of time and don't want to continue, you can just quit the quiz and your results will be displayed based on the number of questions you went through.
Quiz Results
At the end of the quiz, you will get your score and time taken to complete the quiz. You can take screenshot of the result for any future reference.
It would be useful to have a "next" button, or for it to go to the next question automatically once you answer the current one.
ReplyDeleteThanks for your suggestion. I will let you know once it is done.
DeleteI have put the NEXT button. Please visit the quiz again and let me know if any other improvement required?
Delete