Lernkarten

Karten 151 Karten
Lernende 2 Lernende
Sprache English
Stufe Universität
Erstellt / Aktualisiert 01.11.2017 / 27.01.2018
Weblink
Einbinden
15 Exakte Antworten 59 Text Antworten 77 Multiple Choice Antworten
Fenster schliessen

8: Viewpoint invariance refers to the idea that

objects schould be just as easy to recognize from any viewpoint

Fenster schliessen

8: Yasmins and colleagues from the DiCarlo lab at MIT published an artivle in 2014 in which the presented their HMO model, standing for ---

hierarchical modular optimization

Fenster schliessen

8: Yasmins and colleagues from the DiCarlo lab at MIT published an artivle in 2014 in which the presented their HMO model, standing for hierarchical modular optimization.

The HMO model belongs in the larger class of --- models, standing for --- model.

DNN

deep neural network

Fenster schliessen

8: Yasmins and colleagues from the DiCarlo lab at MIT published an artivle in 2014 in which the presented their HMO model, standing for hierarchical modular optimization.

The HMO model's essential architectural characteristic is its --- : There are, for example, many --- connections and different parameter ---.

heteroogeneity

bypass

settings even at the same level

Fenster schliessen

8: Yasmins and colleagues from the DiCarlo lab at MIT published an artivle in 2014 in which the presented their HMO model, standing for hierarchical modular optimization.

---, the basic operations performed locally are --- troughout the network.

However

the same

Fenster schliessen

8: Yasmins and colleagues from the DiCarlo lab at MIT published an artivle in 2014 in which the presented their HMO model, standing for hierarchical modular optimization.

In the Yamins et al. (2014) article they report a large-scale modelling effort, evaluating around ---. Yamins et al. compared their models both to the response of cells in IT cortex (roughly N = --- cells) as well as on how well the models categorized a set of images (roughly N = --- images). One central finding was that models optimized for --- were also superior at --- .

5000DNN architectures

300 oder 100

6.000

categorization performance

explaining variance in IT

 

Fenster schliessen

8: Yasmins and colleagues from the DiCarlo lab at MIT published an artivle in 2014 in which the presented their HMO model, standing for hierarchical modular optimization.

In order to obtain a categorization performance from the HMO model, a --- decoder was --- the activity of units at the --- level(s) of the HMO network. Using such a procedure, the HMO model's performance was --- than that of --- models of object recognition on the difficult  --- variation task.

linear

trained on

highest

better

both computer vision and neuronally inspired

high