Övrigt Massa Bra Flashcards

1
Q

Overshooting

A

When the learning rate of the model is too high so that the optimal point is missed and prevents the model from converging to minimal loss and makes it instable

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Overfitting

A

Model is overtrained on the trainingdata, it learns noise and other factors. It can no longer generalize and will result in a decrease in loss of training data but an increase in loss of evaluation data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Underfitting

A

The model is not trained on enough data and will result in a fail of training set

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Sigmoid Function vs Heavside

A

A sigmoid activation function will result in a output between 0 - 1. It is best used for say classification where the output then resembles the certainty/probability.

Heavside on the other hand results in either 0,1, good for binary classifications or boolean values

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Temporal Difference

A

Temporal Difference Error is the difference between the observed Value of a state and the expected. value

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Difference Between DSS and ES and KBS

A

DSS contains a model base of mathematical models

ES and KBS contains knowledge bases and inference engines

ES and KBS are designed to emulate a domain expert

DSS can work in any domain

KBS is modular and its knowledge base can be exchanged, in difference to ES

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Differences Database and KB

A

A database contains facts and files of information, internal and external data. But the representation and use is limited in comparison to KBs.

A knowledge base also stores facts but also contains rules for applying the knowledge and relations about the fact.

Knowledge stored in the KB can be represented in many different way
- As production rules, heuristics or rules of thumb, logic, pseudo code etc.

A knowledge base stores knowledge specifically represented for use in intelligent agents and systems.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Pruning of NN?

A

Pruning is a method where the network drops 50 % of the neurons in the hidden layers to avoid overfitting

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Performance Measure of Agents

A

How a Agent is measured on their performance, eg. A goal based agent is easy to evaluate based on if the goal is fulfilled or not

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What are requirements of intelligent Agents?

A

Autonomous, problem solving, reactive to their environment, ability to adapt etc. Depending on.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What are factors of problem domains

A

Time Complexity, Space complexity, Branching factor, problem instance and problem space

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Machine Learning?

A

Machine Learning is the training of machines to find and recognize patterns in data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Deep Q Networks?

A

Deep Q Networks utilizes Deep neural networks to approximate Q-value function

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Temporal Difference learning Algorithm

A

A learning algorithm that is used to find the best paths to the goal.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Learning rates

A

The size of adjustments of weights

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Epochs

A

A full run through of the training set. Allows the model to iteratively adjust the weights, too many epochs can lead to overfitting