KI In Der Fahrzeugtechnik at Fachhochschule Lübeck | Flashcards & Summaries

Lernmaterialien für KI in der Fahrzeugtechnik an der Fachhochschule Lübeck

Greife auf kostenlose Karteikarten, Zusammenfassungen, Übungsaufgaben und Altklausuren für deinen KI in der Fahrzeugtechnik Kurs an der Fachhochschule Lübeck zu.

TESTE DEIN WISSEN

Define Weak AI!

Lösung anzeigen
TESTE DEIN WISSEN
  • artificial intelligence that implements a limited part of mind
  • only some of the subproblems are implemented
Lösung ausblenden
TESTE DEIN WISSEN

Define Image Processing! What is the goal? Which operations are used?

Lösung anzeigen
TESTE DEIN WISSEN
  • Def - method of perfoming operations on images
  • goal - to get an enhanced image or to extract useful information from it
  • operations - computer vision algorithms and mathematical operations
Lösung ausblenden
TESTE DEIN WISSEN

What does the Canny Edge Detector?

Lösung anzeigen
TESTE DEIN WISSEN
  • algorithm that includes all necessary functions to detect edges
  • first derivative of Gaussiona approximates the operator, that optimizes the product of signal-to-noise ration and localization
  • theoretical model: step-edges corrupted by additive Gaussian noise
Lösung ausblenden
TESTE DEIN WISSEN

Which are the 4 sub-problems of autonomous driving?

Lösung anzeigen
TESTE DEIN WISSEN
  • Sensor processing
  • Perception
  • Path and Behavioural planning
  • Control
Lösung ausblenden
TESTE DEIN WISSEN

Name methods of classification!

Lösung anzeigen
TESTE DEIN WISSEN
  • Rule-bases, logic, data-based
  • machine learning
  • deep learning
Lösung ausblenden
TESTE DEIN WISSEN

What does rule-based mean?

Lösung anzeigen
TESTE DEIN WISSEN
  • easies way of machine leraning
  • following a set of rules/questions
Lösung ausblenden
TESTE DEIN WISSEN

How can you use a SVM for multi class classifications? What is the computational effort?

Lösung anzeigen
TESTE DEIN WISSEN
  • 1 vs. rest
    • evaluate one class against all others, treated as one class
    • output vector gives which class won
    • computational effort 0(IKI)
  • 1 vs. 1
    • compare one class to each other class one by one
    • in each comparison all other classes neglected
    • element classified in class decided upon the most
    • computational effort 0(IKI^2)
  • K - # of classes
Lösung ausblenden
TESTE DEIN WISSEN

What is the motivation for sequential analytic solution?

Lösung anzeigen
TESTE DEIN WISSEN
  • sample size is not fixed at beginning > sampling can be stopped when signicifcant results are observed
  • data are evaluated as they are collected > apply regression during operation of the product
  • not enough memory to store all data points
Lösung ausblenden
TESTE DEIN WISSEN

What is the basic principle of nearest neighbor classification?

Lösung anzeigen
TESTE DEIN WISSEN

Classify a new object based on it's nearest neighbor

Lösung ausblenden
TESTE DEIN WISSEN

What are quality measures for classifiers?

Lösung anzeigen
TESTE DEIN WISSEN
  • scalablility
  • compactness
  • accuracy
  • interpretability
  • efficiency
  • robustness
Lösung ausblenden
TESTE DEIN WISSEN

How does logistic regression work?

Lösung anzeigen
TESTE DEIN WISSEN
  • compute regression to data with sigmoid function (like linear regression)
  • combine with a rule for classification
    • new data point x gives value y via sigmoid function
    • rule for y gives classification (eg for y>0,5 tumor is malignant)

Lösung ausblenden
TESTE DEIN WISSEN

Write the pipeline to detect lines!

Lösung anzeigen
TESTE DEIN WISSEN

Perception!

  • Extract image shape
  • tranform to greyscale
  • blur image
  • detect canny edges
  • mark special regions
  • detect hough lines
Lösung ausblenden
  • 16664 Karteikarten
  • 443 Studierende
  • 1 Lernmaterialien

Beispielhafte Karteikarten für deinen KI in der Fahrzeugtechnik Kurs an der Fachhochschule Lübeck - von Kommilitonen auf StudySmarter erstellt!

Q:

Define Weak AI!

A:
  • artificial intelligence that implements a limited part of mind
  • only some of the subproblems are implemented
Q:

Define Image Processing! What is the goal? Which operations are used?

A:
  • Def - method of perfoming operations on images
  • goal - to get an enhanced image or to extract useful information from it
  • operations - computer vision algorithms and mathematical operations
Q:

What does the Canny Edge Detector?

A:
  • algorithm that includes all necessary functions to detect edges
  • first derivative of Gaussiona approximates the operator, that optimizes the product of signal-to-noise ration and localization
  • theoretical model: step-edges corrupted by additive Gaussian noise
Q:

Which are the 4 sub-problems of autonomous driving?

A:
  • Sensor processing
  • Perception
  • Path and Behavioural planning
  • Control
Q:

Name methods of classification!

A:
  • Rule-bases, logic, data-based
  • machine learning
  • deep learning
Mehr Karteikarten anzeigen
Q:

What does rule-based mean?

A:
  • easies way of machine leraning
  • following a set of rules/questions
Q:

How can you use a SVM for multi class classifications? What is the computational effort?

A:
  • 1 vs. rest
    • evaluate one class against all others, treated as one class
    • output vector gives which class won
    • computational effort 0(IKI)
  • 1 vs. 1
    • compare one class to each other class one by one
    • in each comparison all other classes neglected
    • element classified in class decided upon the most
    • computational effort 0(IKI^2)
  • K - # of classes
Q:

What is the motivation for sequential analytic solution?

A:
  • sample size is not fixed at beginning > sampling can be stopped when signicifcant results are observed
  • data are evaluated as they are collected > apply regression during operation of the product
  • not enough memory to store all data points
Q:

What is the basic principle of nearest neighbor classification?

A:

Classify a new object based on it's nearest neighbor

Q:

What are quality measures for classifiers?

A:
  • scalablility
  • compactness
  • accuracy
  • interpretability
  • efficiency
  • robustness
Q:

How does logistic regression work?

A:
  • compute regression to data with sigmoid function (like linear regression)
  • combine with a rule for classification
    • new data point x gives value y via sigmoid function
    • rule for y gives classification (eg for y>0,5 tumor is malignant)

Q:

Write the pipeline to detect lines!

A:

Perception!

  • Extract image shape
  • tranform to greyscale
  • blur image
  • detect canny edges
  • mark special regions
  • detect hough lines
KI in der Fahrzeugtechnik

Erstelle und finde Lernmaterialien auf StudySmarter.

Greife kostenlos auf tausende geteilte Karteikarten, Zusammenfassungen, Altklausuren und mehr zu.

Jetzt loslegen

Das sind die beliebtesten StudySmarter Kurse für deinen Studiengang KI in der Fahrzeugtechnik an der Fachhochschule Lübeck

Für deinen Studiengang KI in der Fahrzeugtechnik an der Fachhochschule Lübeck gibt es bereits viele Kurse, die von deinen Kommilitonen auf StudySmarter erstellt wurden. Karteikarten, Zusammenfassungen, Altklausuren, Übungsaufgaben und mehr warten auf dich!

Das sind die beliebtesten KI in der Fahrzeugtechnik Kurse im gesamten StudySmarter Universum

Künstliche Intelligenz in der Fahrzeugtechnik

TU München

Zum Kurs

Die all-in-one Lernapp für Studierende

Greife auf Millionen geteilter Lernmaterialien der StudySmarter Community zu
Kostenlos anmelden KI in der Fahrzeugtechnik
Erstelle Karteikarten und Zusammenfassungen mit den StudySmarter Tools
Kostenlos loslegen KI in der Fahrzeugtechnik