Skip to Main Content
Table 3:
Current Task Accuracy for the Different Models for the Associative Recall Task Distribution.
Task IDsmall-Lstm-Gem-Net2Netlarge-Lstmlarge-Lstm-Gem
75.99 76.17 76.17 
74.5* 76.57 75.63 
75.6 76.9 75.79 
76.1 76.03 75.49 
75.29 75.3 74.99 
74.56 74.9 74.38 
 75.38  
 75.5  
 75.38  
10  75.07  
11  74.8  
Task IDsmall-Lstm-Gem-Net2Netlarge-Lstmlarge-Lstm-Gem
75.99 76.17 76.17 
74.5* 76.57 75.63 
75.6 76.9 75.79 
76.1 76.03 75.49 
75.29 75.3 74.99 
74.56 74.9 74.38 
 75.38  
 75.5  
 75.38  
10  75.07  
11  74.8  

Notes: The row with the asterisk denotes the task at which the proposed model expanded. The capacity expansion technique allows our proposed model to clear more tasks than it would have cleared otherwise. The proposed small-Lstm-Gem-Net2Net model clears as many levels as the large-Lstm-Gem model.

Close Modal

or Create an Account

Close Modal
Close Modal