Artificial Intelligence Interview Questions and Answers
Question - 41 : - Is KNN different from K-means Clustering?
Answer - 41 : -
| KNN | K-means Clustering |
| Supervised | Unsupervised |
| Classification algorithms | Clustering algorithms |
| Minimal training model | Exhaustive training model |
| Used in the classification and regression of the known data | Used in population demographics, market segmentation, social media trends, anomaly detection, etc. |
Question - 42 : - What methods are used for reducing dimensionality?
Answer - 42 : -
Dimensionality reduction is the process of reducing the number of random variables. We can reduce dimensionality using techniques such as missing values ratio, low variance filter, high correlation filter, random forest, principal component analysis, etc.
Question - 43 : - List different methods for sequential supervised learning.
Answer - 43 : -
- Sliding window methods
- Recurrent sliding windows methods
- Hidden Markov models
- Maximum entropy Markov models
- Conditional random fields
- Graph transformer networks
Question - 44 : - What are the advantages of neural networks?
Answer - 44 : -
- Require less formal statistical training
- Have the ability to detect nonlinear relationships between variables
- Detect all possible interactions between predictor variables
- Availability of multiple training algorithms
Question - 45 : - What is vanishing gradient?
Answer - 45 : -
As we add more and more hidden layers, backpropagation becomes less useful in passing information to the lower layers. In effect, as information is passed back, the gradients begin to vanish and become small relative to the weights of the network.
Question - 46 : - What are the hyper parameters of ANN?
Answer - 46 : -
- Learning rate: The learning rate is how fast the network learns its parameters.
- Momentum: It is a parameter that helps to come out of the local minima and smoothen the jumps while gradient descent.
- Number of epochs: The number of times the entire training data is fed to the network while training is referred to as the number of epochs. We increase the number of epochs until the validation accuracy starts decreasing, even if the training accuracy is increasing (overfitting).
Question - 47 : - List different activation neurons or functions.
Answer - 47 : -
- Linear neuron
- Binary threshold neuron
- Stochastic binary neuron
- Sigmoid neuron
- Tanh function
- Rectified linear unit (ReLU)
Question - 48 : - What is a cost function?
Answer - 48 : -
A cost function is a scalar function that quantifies the error factor of the neural network. Lower the cost function better the neural network. For example, while classifying the image in the MNIST dataset, the input image is digit 2, but the neural network wrongly predicts it to be 3.
Question - 49 : - What are the TensorFlow objects?
Answer - 49 : -
- Constants
- Variables
- Placeholder
- Graph
- Session
Question - 50 : - How to install TensorFlow?
Answer - 50 : -
TensorFlow Installation Guide:
CPU: pip install tensorflow-cpu
GPU: pip install tensorflow-gpu