Scribd
Upload
4 views1 page

ML Assignment

The document discusses various concepts related to Artificial Neural Networks (ANN), including the definition, types of problems they can solve, and the structure of a Perceptron. It covers training rules, conditions for rule failures, and differentiates between Gradient Descent and Stochastic Gradient Descent. Additionally, it addresses learning in multilayer networks, hypothesis space search in decision tree algorithms, and issues such as overfitting and generalization in ANN.

Uploaded by

koushikabhi.dev
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
4 views1 page

ML Assignment

The document discusses various concepts related to Artificial Neural Networks (ANN), including the definition, types of problems they can solve, and the structure of a Perceptron. It covers training rules, conditions for rule failures, and differentiates between Gradient Descent and Stochastic Gradient Descent. Additionally, it addresses learning in multilayer networks, hypothesis space search in decision tree algorithms, and issues such as overfitting and generalization in ANN.

Uploaded by

koushikabhi.dev
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

1. What is Artificial Neural Network?

What are the type of problemsinwhich


Artificial Neural Network canbe applied.
2. Explainthe concept of a Perceptronwitha neat diagram. Give examplesfor
linearseparable and notlinearly separable problems. Explain.
3. Discuss the Perceptrontraining rule.
4. Underwhat conditions the perceptronrule fails andit becomes necessary to
applythe delta rule. Derive Deltarule.
5. Differentiate betweenGradient Descent and Stochastic Gradient Descent
6. Derive the Backpropagation rule considering the training rule forOutput Unit
weights and TrainingRule for HiddenUnit weights
7. ExplainhowtolearnMultilayerNetworks using Gradient Descent Algorithm.
8. Describe hypothesis Space searchinID3 and contrast it with
Candidate-Eliminationalgorithm. Relate Inductive bias with respect toDecision
tree learning.
9. Illustrate Occam’s razorandrelate the importance of Occam’s razor with
respectto ID3 algorithm.
10. List the issues in DecisionTree Learning. Interpret the algorithmwithrespect to
Overfitting the data.
11. Explaintheconceptofgeneralization,overfittingand Stoppingcriteria inANN.

You might also like