Back to Subject

Unit 5: Dimensionality Reduction and Neural Networks - Practice Quiz

INT234 — Predictive Analytics 50 Questions
0 Correct 0 Wrong 50 Left
0/50

1 What is the primary objective of dimensionality reduction in predictive analytics?

A. To reduce the number of input variables while retaining essential information
B. To increase the computational complexity of the model
C. To create artificial data points for training
D. To increase the number of features to capture more data

2 Which phenomenon refers to the problem where the amount of data needed to generalize accurately grows exponentially with the dimensionality?

A. The Overfitting Paradox
B. The Curse of Dimensionality
C. The Vanishing Gradient
D. The Law of Large Numbers

3 Principal Component Analysis (PCA) is best described as which type of machine learning technique?

A. Supervised Learning
B. Semisupervised Learning
C. Unsupervised Learning
D. Reinforcement Learning

4 In PCA, what do the Principal Components represent?

A. The original features sorted by importance
B. New orthogonal variables that maximize variance
C. The error terms of a regression model
D. The cluster centroids of the data

5 Which mathematical concept is central to calculating Principal Components in PCA?

A. Eigenvalues and Eigenvectors
B. Derivatives and Integrals
C. Fourier Transforms
D. Sine and Cosine functions

6 Why is feature scaling (standardization) important before applying PCA?

A. To convert negative numbers to positive
B. To increase the number of dimensions
C. Because PCA requires categorical data
D. Because PCA is sensitive to the scale of the variables

7 What is the relationship between the first principal component and the second principal component?

A. They are orthogonal (uncorrelated) to each other
B. They are parallel to each other
C. They are identical
D. The second is the inverse of the first

8 Which plot is commonly used to determine the optimal number of principal components to retain?

A. Scatter plot
B. Scree plot
C. Box plot
D. Histogram

9 What is the main difference between Feature Selection and Feature Extraction?

A. Feature selection creates new variables; Feature extraction selects a subset
B. They are exactly the same
C. Feature selection selects a subset of original variables; Feature extraction creates new variables
D. Feature selection is for images; Feature extraction is for text

10 If a dataset has 50 variables and you apply PCA to select the top 5 components, what happens to the dimensionality?

A. It increases to 55
B. It remains 50
C. It reduces to 5
D. It becomes 0

11 What is a Feedforward Neural Network?

A. A network where output is fed back into the input
B. A network that does not use weights
C. A network that only processes images
D. A network where information moves in only one direction, forward, from the input nodes

12 What is the fundamental building block of a neural network?

A. Pixel
B. Eigenvector
C. Decision Tree
D. Neuron (Perceptron)

13 In a neural network, what is the role of the 'weight'?

A. To calculate the accuracy
B. To store the input data
C. To represent the strength or importance of a connection between neurons
D. To determine the number of layers

14 What is the purpose of an activation function in a neural network?

A. To reduce the size of the dataset
B. To sort the input data
C. To initialize the weights to zero
D. To introduce non-linearity into the network

15 Which of the following is a commonly used activation function that outputs values between 0 and 1?

A. Linear
B. ReLU (Rectified Linear Unit)
C. Tanh
D. Sigmoid

16 What is a Multi-layer Perceptron (MLP)?

A. A network that only has an input and an output layer
B. A perceptron with no weights
C. A type of PCA
D. A neural network with at least one hidden layer between input and output

17 What limitation of the single-layer perceptron did the MLP solve?

A. It was too slow
B. It could not handle numbers
C. It required too much memory
D. It could not solve the XOR problem (non-linearly separable data)

18 What algorithm is commonly used to train Multi-layer Perceptrons?

A. Backpropagation
B. Principal Component Analysis
C. Apriori Algorithm
D. K-Means Clustering

19 In the context of Backpropagation, what is the role of the 'Loss Function'?

A. To measure the difference between the predicted output and the actual target
B. To randomly assign weights
C. To increase the speed of the network
D. To visualize the neural network

20 What does 'Gradient Descent' do in a neural network?

A. It removes outliers from data
B. It converts images to text
C. It increases the number of neurons
D. It iteratively adjusts weights to minimize the loss function

21 What is an 'Epoch' in neural network training?

A. The number of hidden layers
B. The initial learning rate
C. The time it takes to code the model
D. One forward pass and one backward pass of all the training examples

22 Which activation function is defined as f(x) = max(0, x)?

A. Softmax
B. Tanh
C. ReLU (Rectified Linear Unit)
D. Sigmoid

23 What is the 'Bias' term in a neuron equation?

A. A constant added to the product of inputs and weights to shift the activation function
B. The number of inputs
C. A prejudice in the data
D. The error rate of the model

24 Convolutional Neural Networks (CNNs) are primarily used for which type of data?

A. Image and video data
B. Text sentiment analysis
C. Time-series financial data
D. Tabular sales data

25 What is the core operation in a CNN that allows it to detect features like edges?

A. Recursion
B. Multiplication
C. Convolution
D. Flattening

26 In a CNN, what is a 'Kernel' or 'Filter'?

A. The loss function
B. A small matrix of weights that slides over the input
C. A virus protection software
D. The output layer of the network

27 What is the purpose of 'Pooling' layers (e.g., Max Pooling) in a CNN?

A. To add color to the image
B. To inverse the colors
C. To reduce the spatial dimensions and computation while retaining important features
D. To increase the dimensions of the image

28 What does 'Stride' refer to in the context of CNNs?

A. The size of the pooling window
B. The step size the filter moves across the input image
C. The number of filters used
D. The learning rate

29 What is 'Padding' in a CNN?

A. Coloring the image black and white
B. Compressing the image file
C. Removing pixels from the image
D. Adding pixels (usually zeros) around the border of the input image

30 Before passing the output of convolutional layers to a fully connected dense layer, what operation must be performed?

A. Expanding
B. Rotating
C. Flattening
D. Inverting

31 Recurrent Neural Networks (RNNs) are best suited for what type of data?

A. Sequential data (e.g., time series, text)
B. Unstructured noise
C. Independent tabular records
D. Static images

32 What distinguishes an RNN from a standard Feedforward Neural Network?

A. RNNs cannot have hidden layers
B. RNNs have a feedback loop allowing information to persist
C. RNNs have no activation functions
D. RNNs only work on GPUs

33 In an RNN, what is the 'Hidden State'?

A. Data that is deleted after processing
B. The final output prediction
C. A layer that is never trained
D. The memory of the network capturing information about previous steps

34 What is the 'Vanishing Gradient Problem' commonly faced by standard RNNs?

A. Gradients become extremely small, preventing weights from updating effectively in earlier layers
B. The loss function becomes zero immediately
C. Gradients become too large and explode
D. The network runs out of memory

35 Which architecture was designed specifically to solve the Vanishing Gradient problem in RNNs?

A. CNN (Convolutional Neural Network)
B. LSTM (Long Short-Term Memory)
C. Perceptron
D. PCA (Principal Component Analysis)

36 What is 'Dropout' in the context of Neural Networks?

A. A regularization technique that randomly ignores neurons during training to prevent overfitting
B. Stopping the training early
C. Removing bad data from the input
D. A type of activation function

37 In a multi-class classification problem (e.g., classifying an image as a Cat, Dog, or Bird), which activation function is used in the output layer?

A. Softmax
B. Linear
C. ReLU
D. Sigmoid

38 Which of the following is a hyperparameter in a neural network?

A. Learning Rate
B. Biases
C. Weights
D. Output predictions

39 What does a Learning Rate of 0.001 imply?

A. The accuracy will be 0.1%
B. The weights are updated by a small step size in the direction of the gradient
C. The model will learn very fast
D. The model has 1000 layers

40 In the context of PCA, if the first two principal components explain 95% of the variance, what can be concluded?

A. The other components contain 95% of the information
B. The data is useless
C. You need at least 10 components
D. The data can be effectively reduced to 2 dimensions with minimal information loss

41 Which concept allows a CNN to recognize an object in an image regardless of where it is located in the image?

A. Overfitting
B. Vanishing Gradient
C. Translation Invariance
D. Linearity

42 What is the 'Gate' mechanism in LSTM used for?

A. To speed up the GPU
B. To control what information is added to or removed from the cell state
C. To calculate the convolution
D. To connect to the internet

43 Which of the following is an example of a Many-to-One RNN architecture?

A. Video Frame Prediction
B. Machine Translation (Sequence to Sequence)
C. Image Captioning (Image to Text)
D. Sentiment Analysis (Text to Sentiment Score)

44 In a fully connected (dense) layer, how are neurons connected?

A. Each neuron is connected to every neuron in the previous layer
B. Neurons are not connected
C. Randomly connected
D. Only to the corresponding neuron in the previous layer

45 Why is Non-Linearity important in dimensionality reduction (e.g., t-SNE vs PCA)?

A. Non-linear methods are always faster
B. PCA captures linear relationships; non-linear methods capture complex manifolds
C. PCA cannot handle numbers
D. It is not important

46 What is the primary disadvantage of using a Deep Neural Network compared to a Decision Tree?

A. Simplicity
B. Lack of interpretability (Black Box nature)
C. Lower accuracy
D. Cannot handle large data

47 In PCA, the Covariance Matrix is usually:

A. Symmetric
B. Diagonal with zeros
C. Asymmetric
D. Undefined

48 What is 'Weight Initialization'?

A. Setting all weights to 0
B. Setting all weights to 1
C. Setting initial values for weights (often small random numbers) before training
D. Calculating the final weights

49 Which of the following best describes 'Overfitting' in neural networks?

A. The model performs well on training data but poorly on unseen test data
B. The model performs poorly on training data and test data
C. The model performs well on test data but poorly on training data
D. The model has too few parameters

50 The Universal Approximation Theorem states that:

A. CNNs are better than RNNs
B. A feedforward network with a single hidden layer can approximate any continuous function
C. PCA is universal
D. A neural network can never reach 100% accuracy
Previous MCQ
Unit 4
Next MCQ
Unit 6