Edited, memorised or added to reading list

on 20-Sep-2019 (Fri)

Do you want BuboFlash to help you learning these things? Click here to log in or create user.

Flashcard 4395604249868

Question
Abstraction
Answer
The process of describing the essential features of a problem and ignoring other details. It permits you to concentrate on a problem at some level of generalisation, without regard to irrelevant detail. It also permits you to work with concepts, terms and models that are familiar in the problem environment (or domain)


statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

pdf

cannot see any pdfs







Flashcard 4395607395596

Question
acceptance testing
Answer
The formal testing of an entire system, conducted by a customer, to determine whether it satisfies its acceptance criteria and thus whether the customer should accept the system.


statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

pdf

cannot see any pdfs







Flashcard 4395609492748

Question
acceptance testing
Answer
[default - edit me]


statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

pdf

cannot see any pdfs







The terms are different:

  • Equivariant to translation means that a translation of input features results in an equivalent translation of outputs. So if your pattern 0,3,2,0,0 on the input results in 0,1,0,0 in the output, then the pattern 0,0,3,2,0 might lead to 0,0,1,0

  • Invariant to translation means that a translation of input features doe not change the outputs at all. So if your pattern 0,3,2,0,0 on the input results in 0,1,0 in the output, then the pattern 0,0,3,2,0 would also lead to 0,1,0

For feature maps in convolutional networks to be useful, they typically need both properties in some balance. The equivariance allows the network to generalise edge, texture, shape detection in different locations. The invariance allows precise location of the detected features to matter less. These are two complementary types of generalisation for many image processing tasks.

statusnot read reprioritisations
last reprioritisation on reading queue position [%]
started reading on finished reading on

neural network - What is the difference between "equivariant to translation" and "invariant to translation" - Data Science Stack Exchange
at 22:53 Laurent DuvalLaurent Duval 89288 silver badges2121 bronze badges 4 Great! I really admire your effort for the detailed reply @Laurent Duval – Aamir Jan 5 '17 at 8:32 add a comment | 22 <span>The terms are different: Equivariant to translation means that a translation of input features results in an equivalent translation of outputs. So if your pattern 0,3,2,0,0 on the input results in 0,1,0,0 in the output, then the pattern 0,0,3,2,0 might lead to 0,0,1,0 Invariant to translation means that a translation of input features doe not change the outputs at all. So if your pattern 0,3,2,0,0 on the input results in 0,1,0 in the output, then the pattern 0,0,3,2,0 would also lead to 0,1,0 For feature maps in convolutional networks to be useful, they typically need both properties in some balance. The equivariance allows the network to generalise edge, texture, shape detection in different locations. The invariance allows precise location of the detected features to matter less. These are two complementary types of generalisation for many image processing tasks. share Share a link to this answer Copy link |improve this answer edited Jan 4 '17 at 20:45 answered Jan 4 '17 at 20:39 Neil SlaterNeil Slater 19.2k33 gold badges3636 silver badges6969 b