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