maggicl
/
ml
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

hw1: final touch on training procedure description

This commit is contained in:
Claudio Maggioni 2021-05-07 17:12:59 +02:00
parent 0ea15ff3c9
commit 0841e7a723
3 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@ -422,3 +422,5 @@ TSWLatexianTemp*
# option is specified. Footnotes are the stored in a file with suffix Notes.bib. # option is specified. Footnotes are the stored in a file with suffix Notes.bib.
# Uncomment the next line to have this generated file ignored. # Uncomment the next line to have this generated file ignored.
#*Notes.bib #*Notes.bib
*.zip

3
as1_Maggioni_Claudio/report_Maggioni_Claudio.md
View File

@ -112,6 +112,9 @@ The model I've chosen is a feed-forward neural network with 2 hidden layers:
Finally, the output neuron has a linear activation function. As described Finally, the output neuron has a linear activation function. As described
before, the validation set was used to manually tailor the NNs architecture. before, the validation set was used to manually tailor the NNs architecture.
The network was trained using the `adam` optimizer with 5000 maximum number of
epochs and with an early stopping procedure that has a patience of 120 epochs.
The fitted model has these final performance parameters: The fitted model has these final performance parameters:
- Final MSE on validation set $\approx 0.0143344$ - Final MSE on validation set $\approx 0.0143344$

BIN
as1_Maggioni_Claudio/report_Maggioni_Claudio.pdf
View File

Binary file not shown.