Neural Networks MCQ

Test your knowledge with important Neural Networks MCQ and their applications. These MCQs are beneficial for competitive exams too. Explore 30 + more Neural Networks MCQs at Bissoy

• Before building a presentation with a multimedia authoring system, the designer would use a _________
  ক

  Flowchart

  খ

  Hypermedia database

  গ

  Button file

  ঘ

  Storyboard
• Errors are identified and the presentation is evaluated in terms of effectiveness in the __________ step.
  ক

  Planning

  খ

  Designing

  গ

  Creating

  ঘ

  Supporting
• The creation of a storyboard is essential to the development of the project. This is the __________ step of development.
  ক

  Planning

  খ

  Designing

  গ

  Creating

  ঘ

  Supporting
• When determining the overall objective of the project, the resources required and the persons or team who will work on the project, you are in the __________ step of developing a multimedia presentation.
  ক

  Planning

  খ

  Designing

  গ

  Creating

  ঘ

  Supporting
• Clicking on special areas called __________ activates the various features of a multimedia presentation.
  ক

  Activators

  খ

  Starters

  গ

  Pages

  ঘ

  Buttons
• The connection between a multimedia presentation and a file containing a song to be played is called a(n) _________
  ক

  Link

  খ

  Chain

  গ

  Pointer

  ঘ

  Tie
• Primary uses of business interactive multimedia include all of the following except
  ক

  Product demonstrations

  খ

  Web page development

  গ

  Entertainment

  ঘ

  High-quality presentations
• Multimedia can contain
  ক

  Graphics, animation, video, music, and voice

  খ

  Only numeric type data

  গ

  Numeric, text, and picture data

  ঘ

  Databases that turn contain other databases creative massive data collection
• The term that describes a user’s participation with a multimedia presentation is __________
  ক

  Hyperactivity

  খ

  Interactivity

  গ

  Inactivity

  ঘ

  Reactivity
• An essential ingredient for effective multimedia presentations incorporates user participation or __________
  ক

  Links

  খ

  Buttons

  গ

  Interactivity

  ঘ

  Integration
• Linear neurons can be useful for application such as interpolation, is it true?
  ক

  yes

  খ

  no
• What is the objective of a pattern storage task in a network?
  ক

  to store a given set of patterns

  খ

  to recall a give set of patterns

  গ

  both to store and recall

  ঘ

  none of the mentioned
• What property should a feedback network have, to make it useful for storing information?
  ক

  accretive behaviour

  খ

  interpolative behaviour

  গ

  both accretive and interpolative behaviour

  ঘ

  none of the mentioned
• If input is ‘ a(l) + e ‘ where ‘e’ is the noise introduced, then what is the output if system is interpolative in nature?
  ক

  a(l)

  খ

  a(l) + e

  গ

  could be either a(l) or a(l) + e

  ঘ

  e
• If input is ‘ a(l) + e ‘ where ‘e’ is the noise introduced, then what is the output if system is accretive in nature?
  ক

  a(l)

  খ

  a(l) + e

  গ

  could be either a(l) or a(l) + e

  ঘ

  e
• If input is ‘ a(l) + e ‘ where ‘e’ is the noise introduced, then what is the output in case of autoassociative feedback network?
  ক

  a(l)

  খ

  a(l) + e

  গ

  could be either a(l) or a(l) + e

  ঘ

  e
• Is there any error in linear autoassociative networks?
  ক

  yes

  খ

  no
• What is objective of linear autoassociative feedforward networks?
  ক

  to associate a given pattern with itself

  খ

  to associate a given pattern with others

  গ

  to associate output with input

  ঘ

  none of the mentioned
• What is a Boltzman machine?
  ক

  A feedback network with hidden units

  খ

  A feedback network with hidden units and probabilistic update

  গ

  A feed forward network with hidden units

  ঘ

  A feed forward network with hidden units and probabilistic update
• How can false minima be reduced in case of error in recall in feedback neural networks?
  ক

  by providing additional units

  খ

  by using probabilistic update

  গ

  can be either probabilistic update or using additional units

  ঘ

  none of the mentioned
• The number of units in hidden layers depends on?
  ক

  the number of inputs

  খ

  the number of outputs

  গ

  both the number of inputs and outputs

  ঘ

  the overall characteristics of the mapping problem
• How is hard learning problem solved?
  ক

  using nonlinear differentiable output function for output layers

  খ

  using nonlinear differentiable output function for hidden layers

  গ

  using nonlinear differentiable output function for output and hidden layers

  ঘ

  it cannot be solved
• The nature of mapping problem decides?
  ক

  number of units in second layer

  খ

  number of units in third layer

  গ

  overall number of units in hidden layers

  ঘ

  none of the mentioned
• Does an approximate system produce strictly an interpolated output?
  ক

  yes

  খ

  no
• To provide generalization capability to a network, what should be done?
  ক

  all units should be linear

  খ

  all units should be non – linear

  গ

  except input layer, all units in other layers should be non – linear

  ঘ

  none of the mentioned
• What is the objective of pattern mapping problem?
  ক

  to capture weights for a link

  খ

  to capture inputs

  গ

  to capture feedbacks

  ঘ

  to capture implied function
• Can mapping problem be a more general case of pattern classification problem?
  ক

  yes

  খ

  no
• What is a mapping problem?
  ক

  when no restrictions such as linear separability is placed on the set of input – output pattern pairs

  খ

  when there may be restrictions such as linear separability placed on input – output patterns

  গ

  when there are restriction but other than linear separability

  ঘ

  none of the mentioned
• Can all hard problems be handled by a multilayer feedforward neural network, with nonlinear units?
  ক

  yes

  খ

  no
• If the output produces nonconvex regions, then how many layered neural is required at minimum?
  ক

  2

  খ

  3

  গ

  4

  ঘ

  5