Chapter 22 Artificial Intelligence (AI) Flashcards
artificial intelligence
the ability of a computer to carry out tasks that are usually done by humans because they require human intelligence
A* algorithm
adds an extra heuristic value (smart guess) on how far we have to go to reach the destination most efficiently
machine learning
a subset of AI in which algorithms are trained and learn from their past experience
deep learning
subset of machine learning inspired by the structure of the human brain called artificial neural networks
extract pattern from data using neural networks
unlabeled data
data to which a label is not attached
labelled data
unlabeled data becomes labelled the moment a meaning is attached (label)
supervised learning
using known tasks with given outcomes to enable a computer program to improve its performance in accomplishing similar tasks
unsupervised learning
using a large number of tasks with unknown outcomes to enable a computer program to improve its performance in accomplishing similar tasks
reinforcement learning
using a large number of tasks with unknown outcomes and the use of feedback to enable a computer program to improve its performance in accomplishing a similar task
artificial neural networks
based on the interconnection between neurons in the human brain. the system is able to think like a human using these neural networks and its performance improves with more data
the hidden layers are where data from the input layer is processed into something that can be sent to the output layer
why are there multiple hidden layers in an ANN?
enables deep learning to take place
where the problems you’re trying to solve has a higher level of complexity it requires more layers to solve
to enable neural network to learn and make decisions on its own
to improve the accuracy of results
back propagation
initial outputs from the system are compared to the expected output
the system weightings are adjusted to minimise the difference between actual and expected result
once the errors in the output have been eliminated, the neural network is functioning correctly
if the errors are still too large, the weightings are altered
machine learning vs deep learning
ML enables machines to make decisions on their own based on past data while DL enables machines to make decisions using an artificial neural network
ML needs only a small amount of data to carry out the training while DL requires large amounts of data for the training stage
for ML, most features in the data need to be identified in advance and then manually coded into the system while DL learns the features of the data from the data itself and doesn’t need to be identified in advance
regression
-a way of analysing data before it is input into a system
- used to make predictions from given data by leaning some relationship between input and output
how do artificial neural networks enable machine learning
weights are assigned for each connection b/w nodes in the ANN
the data is input within the input layer and is passed into the system
data is analysed at each subsequent hidden layer where outputs are calculated
this process of learning is repeated many times to achieve optimum outputs
the deep learning network will have created complex feature detectors
output layer provides the results
back propagation of errors will be used to correct any errors that have been made
