Artificial Intelligence

Question 1

Explain the use of graphs to aid Artificial Intelligence.

Answer 1

Artificial Neural Networks can be represented using graphs.
Graphs provide relationships between nodes.
Graphs can be analyzed by using a range of algorighms E.g: A* and Dijksta’s algorithm used in machine learning.
Ai problems can be solved as finding a path in a graph.

Question 2

State the reason for having multiple hidden layers in an artificial neural network.

Answer 2

Enables deep learning to take place
To improve the accuracy of the result
If a problem has more complexity it will require more layers to solve

Question 3

What is back propagation?

Answer 3

Training program is Iterative
The errors are propagated back into the nural networks in order to update the initial netwrok weightings
The training process is repeated until the desired output is obtained.

Question 4

Describe the process of Back Propagation

Answer 4

Initial output from the system is compared to the expected output.
The system weightings are adjusted to mminimize the difference between actual and expected output.
Once the errors in the output has been eliminated, the neural network is working correctly.
If the errors are still too large, the weightings are adjusted.

Question 5

What is Regression.

Answer 5

It is used to make predictions from given data by learning some relationship between the input and output

Question 6

Explain how Artificial Neural Netwroks enable machine learning.

Answer 6

Artificial Neural networks are meant to replicate how human brains work.
Weights are assisgned for each connection etween nodes
The data are input at the input layer and passed into the system.
They are analyzed at each hidden layer where output is calculated
The process of learning is reapeted many times to achieve desired output.

Question 7

What is the difference between Machine Learning and Deep learning?

Answer 7

1) Machine learning enables machines to make desicions on their own based on past data.
Deep learning enables machines to make desicions based on Artificial Neural Network

2) Machine Learning needs small amount of data to carry out Training
Deep learning requires large amount of data during training

Question 8

Describe three catagories of Machine Learning.

Answer 8

1)Supervised Learning:
The model learns from Labeled data, to predict outputs for new, similar inputs.
2)Unsupervised Learning:
The Model finds patterns or Groupings in unlabled data.
3)Reinforcement Learning:
An agent learns by taking actions and getting feedback as rewards or penalties