Course Name: Cs101

1
Introduction

• Course Name Cs101
• Student ID bc120201817
• Student Name Zohaib Siddiq
• Study Program Bs information Technology

2
Topic NameNeural Network Learning Paradigm with
Applications

• Topic Introduction
• In the artificial intelligence field, artificial
  neural networks have been applied successfully to
  speech recognition, image analysis and adaptive
  control, in order to construct software agents
  (in computer and video games) or autonomous
  robots. Most of the currently employed artificial
  neural networks for artificial intelligence are
  based on statistical estimations, classification
  optimization and control theory.
• The cognitive modeling field involves the
  physical or mathematical modeling of the behavior
  of neural systems ranging from the individual
  neural level (e.g. modeling the spike response
  curves of neurons to a stimulus), through the
  neural cluster level (e.g. modeling the release
  and effects of dopamine in the basal ganglia) to
  the complete organism (e.g. behavioral modeling
  of the organism's response to stimuli).
  Artificial intelligence, cognitive modeling, and
  neural networks are information processing
  paradigms inspired by the way biological neural
  systems process data.

3
Description of Neural Network

• Neural networks, as used in artificial
  intelligence, have traditionally been viewed as
  simplified models of neural processing in the
  brain, even though the relation between this
  model and brain biological architecture is
  debated, as it is not clear to what degree
  artificial neural networks mirror brain function.
• A subject of current research in computational
  neuroscience is the question surrounding the
  degree of complexity and the properties that
  individual neural elements should have to
  reproduce something resembling animal cognition.
• Historically, computers evolved from the von
  Neumann model, which is based on sequential
  processing and execution of explicit
  instructions. On the other hand, the origins of
  neural networks are based on efforts to model
  information processing in biological systems,
  which may rely largely on parallel processing as
  well as implicit instructions based on
  recognition of patterns of 'sensory' input from
  external sources. In other words, at its very
  heart a neural network is a complex statistical
  processor (as opposed to being tasked to
  sequentially process and execute).
• Neural coding is concerned with how sensory and
  other information is represented in the brain by
  neurons. The main goal of studying neural coding
  is to characterize the relationship between the
  stimulus and the individual or ensemble neuronal
  responses and the relationship among electrical
  activity of the neurons in the ensemble.

4
Advantages disadvantages of Neural Networks

• Advantages
• Capable of handling large number of features
• Capable of detecting complex relationships
• Can solve numerous complex and miscellaneous
  tasks
• Easy to theorize
• Identify all possible connections
• Large amount of academic study
• Need less formal arithmetical training
• Speedy and fast calculation
• Several training algorithms are accessible
• Disadvantages
• Computing one input path needs calculating the
  network
• Cant resolve all machine learning difficulties
• Difficult to implement trial and error
  for choosing many neurons
• Experimental nature of model improvement
• Greater computational load

5
Conclusion

• Todays Computers and Technology orb can learn
  and achieve a lot from neural networks. Neural
  networks capability to learn from examples makes
  them great and influential. Moreover it is not
  essential to create an algorithm to complete a
  particular job. Have no need to know the inner
  parameters of the task. Furthermore neural
  networks are well-matched for systems due to
  their fast reaction and calculating times as to
  their consistent structure.
• They also add great values to other fields
  of medical science like neurology and psychology
  Neural networks used to design different parts of
  organisms and to inspect the inner structures of
  the brain.
• Possibly the great inspiring feature which
  also seems to be promising is, in the future
  conscious networks might come. Many experts and
  scientists claim that, consciousness is a
  mechanical property and it seems possible to
  create conscious neural networks.
• In conclusion, nevertheless neural
  networks have a massive potential but human kind
  can only take the great benefits, as soon as
  these networks are combined with computing.