set-8

351. ______ is Artificial Intelligence is a set of tools for machine learning that uses statistics and functional analysis.

1. Hebbian learning

2. Bayesian learning

3. Statistical learning

4. Supervised learning

Show me the answer

Answer: 3. Statistical learning

Explanation:

• Statistical learning is a set of tools in AI that uses statistical methods and functional analysis to analyze and interpret data.

• It is widely used in machine learning for predictive modeling and data analysis.

352. Fuzzy logic is a form of ______.

1. Binary valued logic

2. Many valued logic

3. Two valued logic

4. No value logic

Show me the answer

Answer: 2. Many valued logic

Explanation:

• Fuzzy logic is a form of many-valued logic that allows for intermediate values between true and false.

• It is used to handle uncertainty and imprecision in decision-making.

353. Fuzzy logic can be implemented in ______.

1. Software

2. Hardware

3. Network

4. Both A and B

Show me the answer

Answer: 4. Both A and B

Explanation:

• Fuzzy logic can be implemented in both software and hardware.

• It is used in various applications, including control systems and decision-making processes.

354. Fuzzy logic can produce ______ output.

1. Only 1

2. 2

3. 3

4. 4

Show me the answer

Answer: 2. 2

Explanation:

• Fuzzy logic can produce two outputs: one for the degree of truth and another for the degree of falsity.

• This allows for more nuanced decision-making compared to binary logic.

355. ______ are the methods of Fuzzy interface system.

1. Mamdani Fuzzy Inference System

2. Takagi-Sugeno Fuzzy Model (TS Method)

3. Ricart-Aagrawala Model

4. Both A and B

Show me the answer

Answer: 4. Both A and B

Explanation:

• Mamdani Fuzzy Inference System and Takagi-Sugeno Fuzzy Model are two common methods used in fuzzy logic systems.

• These methods are used to model complex systems with uncertainty.

356. The truth values of traditional set theory is ______ and that of fuzzy set is ______.

1. Either 0 or 1, between 0 & 1

2. Between 0 & 1, only 1

3. Between 0 & 1, only 0

4. Either 0 or 1, either 0 or 1

Show me the answer

Answer: 1. Either 0 or 1, between 0 & 1

Explanation:

• In traditional set theory, truth values are binary (either 0 or 1).

• In fuzzy set theory, truth values can be any value between 0 and 1, representing degrees of truth.

357. The store temperature is cold. Here the cold (use of linguistic variable is used) can be represented by ______.

1. Fuzzy Set

2. Crisp Set

3. Fuzzy & Crisp Set

4. Variable Set

Show me the answer

Answer: 1. Fuzzy Set

Explanation:

• The term "cold" is a linguistic variable that can be represented using a fuzzy set.

• Fuzzy sets allow for the representation of imprecise or vague concepts like "cold."

358. Fuzzy Set theory defines fuzzy operators. Choose the fuzzy operators from the following.

1. OR

2. NOT

3. AND

4. All of the mentioned

Show me the answer

Answer: 4. All of the mentioned

Explanation:

• Fuzzy set theory defines operators like OR, NOT, and AND to handle fuzzy logic operations.

• These operators are used to combine and manipulate fuzzy sets.

359. Fuzzy logic is usually represented as ______.

1. IF-THEN-ELSE rules

2. IF-ELSE-IF rules

3. IF-THEN rules

4. Both IF-THEN-ELSE rules & IF-THEN rules

Show me the answer

Answer: 3. IF-THEN rules

Explanation:

• Fuzzy logic is typically represented using IF-THEN rules.

• These rules define the relationship between input and output variables in a fuzzy system.

360. A ______ is a search heuristic that is inspired by Charles Darwin’s theory of natural evolution.

1. Generation Algorithm

2. Genetic Algorithm

3. Search Algorithm

4. None of above

Show me the answer

Answer: 2. Genetic Algorithm

Explanation:

• A genetic algorithm is a search heuristic inspired by the process of natural selection and evolution.

• It is used to solve optimization problems by mimicking biological evolution.

361. ______ involves five phases to solve the complex optimization problems.

1. Generation Algorithm

2. Genetic Algorithm

3. Search Algorithm

4. None of above

Show me the answer

Answer: 2. Genetic Algorithm

Explanation:

• The genetic algorithm involves five phases: initialization, selection, crossover, mutation, and termination.

• These phases are used to evolve solutions to complex optimization problems.

362. Fitness function is used to determine how ______ an individual is?

1. Fit

2. Weak

3. Tired

4. None of above

Show me the answer

Answer: 1. Fit

Explanation:

• The fitness function in a genetic algorithm is used to evaluate how well an individual (solution) performs.

• It determines the fitness or quality of the individual in the context of the problem.

363. This is one of the types of Selection methods available is ______.

1. Roulette wheel selection

2. Tournament selection

3. Rank-based selection

4. All of the above

Show me the answer

Answer: 4. All of the above

Explanation:

• Roulette wheel selection, tournament selection, and rank-based selection are all methods used in genetic algorithms to select individuals for reproduction.

• These methods help in choosing the fittest individuals for the next generation.

364. The operators involved in the reproduction phase are ______.

1. Mutation

2. Crossover

3. Genes

4. Both A and B

Show me the answer

Answer: 4. Both A and B

Explanation:

• The reproduction phase in genetic algorithms involves mutation and crossover operators.

• These operators are used to create new offspring from the selected individuals.

365. After the selection process; the creation of a child occurs in the ______ step.

1. Fitness Assignment

2. Reproduction

3. Termination

4. Initialization

Show me the answer

Answer: 2. Reproduction

Explanation:

• After the selection process, the reproduction step involves creating new offspring (children) through crossover and mutation.

• This step is crucial for generating the next generation of solutions.

366. Types of Crossover styles are ______.

1. One point crossover and Two-point crossover

2. Livery crossover

3. Inheritable Algorithms crossover

4. All of above

Show me the answer

Answer: 4. All of above

Explanation:

• One-point crossover, two-point crossover, and other crossover styles are used in genetic algorithms to combine genetic material from parents.

• These methods help in generating diverse offspring.

367. The ______ operator inserts random genes in the offspring (new child) to maintain the diversity in the population which can be done by flipping some bits in the chromosomes.

1. Mutation

2. Crossover

3. Genes

4. Allele

Show me the answer

Answer: 1. Mutation

Explanation:

• The mutation operator introduces random changes in the offspring's genes to maintain genetic diversity.

• This helps in exploring new solutions and avoiding premature convergence.

368. ______ is one of the types of mutation styles.

1. Flip bit mutation

2. Gaussian mutation

3. Exchange/Swap mutation

4. All of above

Show me the answer

Answer: 4. All of above

Explanation:

• Flip bit mutation, Gaussian mutation, and exchange/swap mutation are all types of mutation styles used in genetic algorithms.

• These methods introduce variability in the population.

369. ______ is a type of neural network which is based on a Feed-Forward strategy.

1. Artificial NN

2. Biological NN

3. Convolutional NN

4. None of above

Show me the answer

Answer: 1. Artificial NN

Explanation:

• Artificial Neural Networks (ANN) are based on a feed-forward strategy, where information flows in one direction from input to output.

• They are widely used in machine learning for tasks like classification and regression.

370. ______ is a structure that consists of Synapse, dendrites, cell body, and axon.

1. Artificial NN

2. Biological NN

3. Convolutional NN

4. None of above

Show me the answer

Answer: 2. Biological NN

Explanation:

• Biological Neural Networks (BNN) consist of structures like synapses, dendrites, cell bodies, and axons.

• These components are part of the human nervous system and are mimicked in artificial neural networks.

371. Artificial Neural Network (ANN) is ______.

1. Sequential and centralized

2. Non sequential and de-centralized

3. Parallel and distributed

4. Parallel and non-distributed

Show me the answer

Answer: 3. Parallel and distributed

Explanation:

• Artificial Neural Networks (ANN) are parallel and distributed systems, meaning they process information simultaneously across multiple nodes.

• This structure allows for efficient learning and computation.

372. Biological Neural Network (BNN) is ______

1. Sequential and centralized

2. Non sequential and de-centralized

3. Parallel and distributed

4. Parallel and non-distributed

Show me the answer

Answer: 3. Parallel and distributed

Explanation:

• Biological Neural Networks (BNN) are parallel and distributed, meaning they process information simultaneously across multiple neurons.

• This structure allows for efficient information processing in the brain.

373. Which NN is this?

[x_1 \quad x_2 \quad x_3 \quad \cdots \quad x_n \in {0, 1}]

[\begin{array}{c} \text{if} \ f \rightarrow y \in {0, 1} \end{array}]

1. McCulloch-pitts neuron

2. Minsky and Papert neuron

3. Both A and B

4. None of Above

Show me the answer

Answer: 1. McCulloch-pitts neuron

Explanation:

• The diagram represents a McCulloch-Pitts neuron, which is a simple model of a biological neuron.

• It takes binary inputs and produces a binary output based on a threshold function.

374. The McCulloch-Pitts neural model, which was the earliest ANN model, has only two types of inputs ______

1. Extraordinary and inhabitation

2. Excitatory and Inhibitory

3. Extraordinary and Inhibitory

4. Excitatory and Inhabitation

Show me the answer

Answer: 2. Excitatory and Inhibitory

Explanation:

• The McCulloch-Pitts neuron has two types of inputs: excitatory (which increase the neuron's activation) and inhibitory (which decrease the neuron's activation).

• These inputs determine whether the neuron fires or not.

375. The excitatory inputs have weights of ______ magnitude and the inhibitory weights have weights of ______ magnitude.

1. Positive, Negative

2. Negative, Negative

3. Negative, Negative

4. Positive, Positive

Show me the answer

Answer: 1. Positive, Negative

Explanation:

• In the McCulloch-Pitts neuron, excitatory inputs have positive weights, while inhibitory inputs have negative weights.

• This determines the effect of each input on the neuron's activation.

376. The inputs of the McCulloch-Pitts neuron could be either ______ or ______

1. 0 or -1

2. 0 or 1

3. 0 or infinity

4. 0 or 2

Show me the answer

Answer: 2. 0 or 1

Explanation:

• The inputs to a McCulloch-Pitts neuron are binary, meaning they can only be 0 or 1.

• This simplicity makes the model easy to analyze and understand.

377. Artificial Neural system are called ______

1. Neural networks and neurocomputers

2. Parallel distributed processors

3. Connectionists system

4. All of above

Show me the answer

Answer: 4. All of above

Explanation:

• Artificial Neural Systems are referred to as neural networks, neurocomputers, parallel distributed processors, and connectionist systems.

• These terms highlight different aspects of how neural networks function.

378. An artificial neuron is designed to mimic the first-order characteristics of a ______

1. Physiological neuron

2. Geological neuron

3. Biological neuron

4. None of above

Show me the answer

Answer: 3. Biological neuron

Explanation:

• An artificial neuron is designed to mimic the behavior of a biological neuron, which is the basic unit of the nervous system.

• It captures the first-order characteristics of how biological neurons process information.

379. Processing of ANN depends upon ______

1. Network Topology

2. Adjustments of Weights or Learning

3. Activation Functions

4. All of above

Show me the answer

Answer: 4. All of above

Explanation:

• The processing of an Artificial Neural Network (ANN) depends on network topology, weight adjustments, and activation functions.

• These factors determine how the network learns and processes information.

380. A network topology in neural network is the arrangement of a network along with its ______

1. Nodes and connecting lines

2. Lines and curves

3. Graphs and vectors

4. Symbols and functions

Show me the answer

Answer: 1. Nodes and connecting lines

Explanation:

• Network topology in neural networks refers to the arrangement of nodes (neurons) and connecting lines (synapses).

• This structure defines how information flows through the network.

381. According to the topology, ANN can be classified as ______

1. Feed forward Network

2. Feed backward Network

3. Both Feed forward and Backward Network

4. None

Show me the answer

Answer: 3. Both Feed forward and Backward Network

Explanation:

• Artificial Neural Networks (ANN) can be classified as feedforward networks (information flows in one direction) and feedback networks (information flows in loops).

• Both types are used in different applications.

382. ______ is a non-recurrent network having processing units/nodes in layers and all the nodes in a layer are connected with the nodes of the previous layers.

1. Feed forward Network

2. Feed backward Network

3. Both Feed forward and Backward Network

4. None

Show me the answer

Answer: 1. Feed forward Network

Explanation:

• A feedforward network is a non-recurrent network where nodes are organized in layers, and each layer is connected to the previous one.

• Information flows in one direction, from input to output.

383. Feed-forward network can be divided into ______

1. Single-layer feed forward

2. Multi-layer feed forward

3. No-layer feed forward

4. Both A and B

Show me the answer

Answer: 4. Both A and B

Explanation:

• Feedforward networks can be divided into single-layer and multi-layer networks.

• Single-layer networks have one layer of nodes, while multi-layer networks have multiple layers.

384. The concept is of ______ ANN having only one weighted layer.

1. Single-layer feed forward

2. Multi-layer feed forward

3. No-layer feed forward

4. Both A and B

Show me the answer

Answer: 1. Single-layer feed forward

Explanation:

• A single-layer feedforward network has only one weighted layer of nodes.

• This type of network is simpler but less powerful than multi-layer networks.

385. Identify which Neural Network Topology is this?

• Inputs

• Outputs

1. Single-layer feed forward

2. Multi-layer feed forward

3. No-layer feed forward

4. None

Show me the answer

Answer: 1. Single-layer feed forward

Explanation:

• The described topology has only inputs and outputs, indicating a single-layer feedforward network.

• This is the simplest form of a neural network.

386. The concept is of ______ ANN having more than one weighted layer.

1. Single-layer feed forward

2. Multi-layer feed forward

3. No-layer feed forward

4. None

Show me the answer

Answer: 2. Multi-layer feed forward

Explanation:

• A multi-layer feedforward network has more than one weighted layer of nodes.

• These networks are more powerful and capable of learning complex patterns.

387. Identify which Neural network topology is this?

• Inputs

• Hidden

• Outputs

1. Single-layer feed forward

2. Multi-layer feed forward

3. No-layer feed forward

4. None

Show me the answer

Answer: 2. Multi-layer feed forward

Explanation:

• The described topology includes inputs, hidden layers, and outputs, indicating a multi-layer feedforward network.

• Hidden layers allow the network to learn more complex relationships.

388. ______ network has feedback paths, which means the signal can flow in both directions using loops.

1. Feed forward Network

2. Feedback/Feed backward Network

3. Both Feed forward and Backward Network

4. None

Show me the answer

Answer: 2. Feedback/Feed backward Network

Explanation:

• A feedback/feed backward network has loops that allow signals to flow in both directions.

• This type of network is used in applications like recurrent neural networks (RNNs).

389. Feedback/ Feed backward network can be divided into ______

1. Recurrent Network

2. Fully recurrent Network

3. Jordan Network

4. None

Show me the answer

Answer: 1. Recurrent Network

Explanation:

• Feedback/feed backward networks can be divided into recurrent networks, where connections form cycles.

• These networks are used for tasks involving sequential data, such as time series prediction.

390. Identify which Neural network topology is this?

• Input layer

• Hidden layer

• Output layer

1. Feed-forward

2. Feedback

3. Linear

4. None of above

Show me the answer

Answer: 2. Feedback

Explanation:

• The described topology includes input, hidden, and output layers, with feedback loops, indicating a feedback network.

• Feedback networks are used in applications like recurrent neural networks (RNNs).

391. ______ neural network architecture because all nodes are connected to all other nodes and each node works as both input and output.

1. Fully recurrent

2. Jordan

3. McClutch

4. None of above

Show me the answer

Answer: 1. Fully recurrent

Explanation:

• In a fully recurrent network, all nodes are connected to all other nodes, and each node can act as both input and output.

• This architecture is used in complex tasks like sequence modeling.

392. Identify which Neural network topology is this?

• Input layer

• Hidden layer

• Output layer

1. Jordan

2. McClutch

3. Fully recurrent

4. None of above

Show me the answer

Answer: 3. Fully recurrent

Explanation:

• The described topology includes input, hidden, and output layers, with all nodes connected to each other, indicating a fully recurrent network.

• This architecture is used in tasks requiring memory and sequential processing.

393. Identify which Neural network topology is this?

1. Jordan

2. McClutch

3. Fully recurrent

4. None of above

Show me the answer

Answer: 1. Jordan

Explanation:

• The described topology is a Jordan network, which is a type of recurrent neural network with feedback connections from the output layer to the hidden layer.

• It is used in tasks involving sequential data.

394. ______ is defined as the extra force or effort applied over the input to obtain an exact output.

1. Deactivation function

2. Activation function

3. Parallel function

4. Distributed function

Show me the answer

Answer: 2. Activation function

Explanation:

• The activation function in a neural network determines the output of a neuron based on its input.

• It introduces non-linearity, allowing the network to learn complex patterns.

395. Non-linear activation function can be divided on the basis of their ______.

1. Signs and ranges

2. Range and curves

3. Range and symbols

4. Symbols and curves

Show me the answer

Answer: 2. Range and curves

Explanation:

• Non-linear activation functions are categorized based on their range (output values) and curves (shape of the function).

• Examples include sigmoid, tanh, and ReLU functions.

396. The main reason why we use sigmoid function is because it exists between ______.

1. 0 to 2

2. -1 to 1

3. -1 to 0

4. 0 to 1

Show me the answer

Answer: 4. 0 to 1

Explanation:

• The sigmoid function outputs values between 0 and 1, making it useful for binary classification tasks.

• It is also differentiable, which is important for backpropagation in neural networks.

397. The range of the tanh function is from ______.

1. 0 to 2

2. -1 to 1

3. -1 to 0

4. 0 to 1

Show me the answer

Answer: 2. -1 to 1

Explanation:

• The tanh function outputs values between -1 and 1, making it useful for tasks where the output needs to be centered around zero.

• It is also differentiable, like the sigmoid function.

398. The range of the Re-Lu function is from ______.

1. 0 to infinity

2. -1 to 1

3. Infinity to 0

4. 0 to 1

Show me the answer

Answer: 1. 0 to infinity

Explanation:

• The ReLU (Rectified Linear Unit) function outputs values from 0 to infinity, making it computationally efficient and widely used in deep learning.

• It helps mitigate the vanishing gradient problem.

399. The range of the Leaky Re-Lu function is from ______.

1. 0 to infinity

2. -1 to 1

3. -infinity to infinity

4. 0 to 1

Show me the answer

Answer: 3. -infinity to infinity

Explanation:

• The Leaky ReLU function outputs values from -infinity to infinity, allowing for small negative outputs when the input is negative.

• This helps address the "dying ReLU" problem.

400. The Neural Network architecture is made of individual units called ______ that mimic the biological behavior of the brain.

1. Nerves

2. Neurons

3. Genes

4. Chromosomes

Show me the answer

Answer: 2. Neurons

Explanation:

• The basic units of a Neural Network are called neurons, which mimic the behavior of biological neurons in the brain.

• These neurons are connected in layers to form the network.