Larger run results

Created on October 28|Last edited on October 28
Comment
﻿
Overall resultsResults obtained over 20 runs of each of the eight configurations we considered.
Experimental settings: Adam with default settings; minibatches of size 500; training for 5000 + 10000 epochs. 
Expansion: Start with 2 hidden units, and expand into 4.
﻿
Validation accuracy during training
Validation accuracy during training
02k4k6k8k10k12k14kEpoch0.20.30.40.50.60.70.8Validation accuracy
run_type: U[copy, copy; FR:False] W[copy, copy; FR:False]   val_accuracy_pretrain
run_type: U[copy, random; FR:True] W[copy, random; FR:True]   val_accuracy_pretrain
run_type: U[copy, random; FR:False] W[copy, random; FR:False]   val_accuracy_pretrain
run_type: U[random, random; FR:False] W[random, random; FR:False]   val_accuracy_pretrain
run_type: U[copy, copy; FR:False] W[copy, copy; FR:False]   val_accuracy_expand
run_type: U[copy, random; FR:True] W[copy, random; FR:True]   val_accuracy_expand
run_type: U[copy, random; FR:False] W[copy, random; FR:False]   val_accuracy_expand
run_type: U[random, random; FR:False] W[random, random; FR:False]   val_accuracy_expand
exp8-large (20 runs)24
﻿
Effective rank﻿
Run set24
﻿
﻿
﻿
Add a comment