diff options
| author | Miguel <m.i@gmx.at> | 2019-03-22 12:23:19 +0100 |
|---|---|---|
| committer | Miguel <m.i@gmx.at> | 2019-03-22 12:23:19 +0100 |
| commit | 683ce9f3dc564766c2b3be3d9e186c222d843332 (patch) | |
| tree | a8bbea578f81576ad77519011508a494b2a9a760 /mnist/Neuronet.hs | |
| parent | 45bb141c38867d582824ec8e473bb01c42dfe574 (diff) | |
first experiments with MNIST
Diffstat (limited to 'mnist/Neuronet.hs')
| -rw-r--r-- | mnist/Neuronet.hs | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/mnist/Neuronet.hs b/mnist/Neuronet.hs index 7a3a159..517f3b8 100644 --- a/mnist/Neuronet.hs +++ b/mnist/Neuronet.hs @@ -3,7 +3,8 @@ N E U R O T I C U S A small and straight forward neural network coded in Haskell - from scratch. It uses the beatuiful backpropagation for learning. + from scratch. It uses gradient descent and the beatuiful + backpropagation for learning. Michal Idziorek <m.i@gmx.at> March 2019 @@ -11,7 +12,8 @@ -} module Neuronet - ( neuronet -- initalize neuronet + ( Neuronet -- the neuronet + ,neuronet -- initalize neuronet ,train -- train with one sample ,trainBatch -- train with batch ,asknet -- ask the neuroal net |