-
Notifications
You must be signed in to change notification settings - Fork 29k
[MLLIB] [spark-2352] Implementation of an Artificial Neural Network (ANN) #1290
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Changes from 1 commit
5bba9dd
5874743
8c3ff4a
96a0970
69b0e59
3f528b9
b1972b1
dd79615
1f6de6a
011c10b
e7e29aa
100ad4b
c9fc3f4
78f99dc
43103f0
2ecc7d5
d80fe63
149a726
ace988e
9f75f59
c81de0c
3c456b5
3807e73
5236a9d
443ea7e
3466f95
aed39c6
1972c69
d04c1d6
bd4508b
c032476
3e90c4d
71ca727
293d013
18ac979
daf1375
5e3345c
6c657c3
5ab0263
577a13a
d048878
90195fa
7c90249
87f630b
986f37a
8e3e2d5
d2b80fe
1a1c10b
2a9554b
40197ef
589205f
6390947
abfb0f5
039df76
aff66ae
e78dcd6
ccbed58
e3dc003
dd47d75
3e7eca1
f8d5a05
57b9147
c189bb2
c4baf79
d0836ed
01bbca0
c7e5323
90f5ae5
243e667
96ba82a
576ef79
c5cb54d
1af7f25
99f0581
b01fc3c
cae6dc2
9eee6f1
fec8691
060ae3a
d1619c8
7c3a5b3
fef4776
c086751
21d95d0
d4764a4
4623f25
10242b7
402ad79
07218eb
f7cfa4e
d3211db
51ca78b
ceaf2f7
6f79c96
2972747
6740981
c22c3dc
d320d76
181c29b
7ac9a67
8e0dc8b
0a3fca6
50ca819
c2da9b0
73ba0dc
a024c6b
95e5299
5a3531b
85050ba
5f51305
95ed2a2
4b83de4
7828327
84ac2e8
e2e94b2
a7fb749
3995be8
b44aec3
6265bd6
325ffab
099ff85
1c0aab4
5db2b60
b13019a
e2d4e92
fefe08e
2fbbe23
57565ae
bd74834
12fb903
a0d1da0
9b10666
3cf5f9b
398e3dd
62b1d91
3f93a2a
2fb67f6
799b277
6166ad9
5205fda
e660ee8
d18e9b5
5de5bad
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
Fix ScalaStyle
- Loading branch information
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -130,7 +130,7 @@ class ArtificialNeuralNetwork private[mllib]( | |
| setConvergenceTol(convergenceTol). | ||
| setMaxNumIterations(maxNumIterations) | ||
|
|
||
| /** | ||
| /** | ||
| * Trains the ANN model. | ||
| * Uses default convergence tolerance 1e-4 for LBFGS. | ||
|
Contributor
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I think the convergence is parameter in the constructor and you are setting it for the optimizer
Author
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. The convergenceTol is used by the LBFGS algorithm. So the convergenceTol is taken from the ArtificialNeuralNetwork header and serves as input to the LBFGS algorithm. (setConvergenceTol accesses the LBFGS class, not the ArtificialNeuralNetwork class.) |
||
| * | ||
|
|
@@ -304,10 +304,10 @@ object ArtificialNeuralNetwork { | |
| * @return random weights vector. | ||
| */ | ||
| def randomWeights( | ||
| inputLayerSize: Int, | ||
| outputLayerSize: Int, | ||
| hiddenLayersTopology: Array[Int], | ||
| seed: Int): Vector = { | ||
| inputLayerSize: Int, | ||
| outputLayerSize: Int, | ||
| hiddenLayersTopology: Array[Int], | ||
| seed: Int): Vector = { | ||
| val topology = inputLayerSize +: hiddenLayersTopology :+ outputLayerSize | ||
| return randomWeights(topology, true, seed) | ||
| } | ||
|
|
||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think the doc is misaligned by one space.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Fixed