A) FALSE B) TRUE
A) All of these B) Clustering C) Classification D) Pattern recognition
A) IF-The-Else Analysis Questions B) What-if question C) For Loop questions
A) Fault tolerance B) Robustness C) Self Organization D) Adaptive Learning
A) Self Organization B) What-If Analysis C) Supervised Learning D) Adaptive Learning
A) nodes or neurons B) weights C) Soma D) axons
A) activation function B) weights C) bias D) neurons
A) TRUE B) FALSE
A) Weight B) None of these C) Bias D) activation or activity level of neuron
A) none B) one C) multiple D) any number of
A) Perceptrons B) Self organizing maps C) Recurrent neural network D) Multi layered perceptron
A) Unsupervised learning B) Supervised learning C) Active learning D) Reinforcement learning
A) Both inputs and outputs are given B) specific output values are not given C) Specific output values are given D) No specific Inputs are given
A) Linear Functions B) Exponential Functions C) Discrete Functions D) Nonlinear Functions
A) Feedforward neural networks B) Recurrent neural networks
A) Feedforward neural networks B) Recurrent neural networks
A) Static B) Deterministic C) Dynamic
A) human perceive everything as a pattern while machine perceive it merely as data B) human have sense organs C) human have more IQ & intellect D) human have emotions
A) neuron B) nucleus C) axon D) brain
A) the system recalls previous reference inputs & respective ideal outputs B) the system learns from its past mistakes C) the strength of neural connection get modified accordingly |