Artificial neural networks

8 important questions on Artificial neural networks

What is neural network?

Adaptive system which gives answers to a problem after it has been trained for similar problems

What is the difference between a recurrent and feedforward network?

Recurrent feedbacks to it's input

What is a perceptron?

Network of treshold nodes for pattern classification. First learning algorithm
  • Higher grades + faster learning
  • Never study anything twice
  • 100% sure, 100% understanding
Discover Study Smart

How does a neuronal network learn?

Calculate predicted outputs, check with actual output change the weights so that it is less likely to make the same mistake again

What is the perceptron learning algorithm?

Wnew=wold+ndx
n= is a learning rate parameter, d is either -1 or +1

What solved the linear problem?

Backpropagation-> learning for multi later feed forward nets
Unsupervised learning

Why is it important not to overtrain the network?

It will exclude samples which are slightly off

What is a methodology to see how well your network generalises?

Training set
Validation set-> is it overtrained or not
Test set-> measurement of how the system performs

The question on the page originate from the summary of the following study material:

  • A unique study and practice tool
  • Never study anything twice again
  • Get the grades you hope for
  • 100% sure, 100% understanding
Remember faster, study better. Scientifically proven.
Trustpilot Logo