ChainerでDeep Learningを試すために必要なこと
Download as PPTX, PDF2 likes1,266 views
2016/12/21 dots.DeepLearning部「数式がわからなくたってDeep Learningやってみたい！人集合- dots. DeepLearning部 発足！」で講演した資料です。
![Deep Learningの手法をためそう!
tterance at atime with better results than evaluating with alargebatch.
ples of varying length posesomealgorithmic challenges. Onepossible solution is
opagation through time [68], so that all examples have the same sequence length
2]. However, this can inhibit the ability to learn longer term dependencies. Other
that presenting examples in order of dif?culty can accelerate online learning [6,
theme in many sequence learning problems including machine translation and
n isthat longer examples tend to bemorechallenging [11].
ction that weuseimplicitly depends on thelength of theutterance,
L(x, y; ?) = ? log
X
`2 Align(x,y)
TY
t
pctc(`t |x; ?). (9)
is the set of all possible alignments of the characters of the transcription y to
under theCTC operator. In equation 9, theinner term isaproduct over time-steps
which shrinks with the length of the sequence since pctc(`t |x; ?) < 1. This moti-
OK実装だ!](https://image.slidesharecdn.com/dotsnishitoba-170330013855/85/Chainer-Deep-Learning-7-320.jpg)
![Deep Learningの手法をためそう!
tterance at atime with better results than evaluating with alargebatch.
ples of varying length posesomealgorithmic challenges. Onepossible solution is
opagation through time [68], so that all examples have the same sequence length
2]. However, this can inhibit the ability to learn longer term dependencies. Other
that presenting examples in order of dif?culty can accelerate online learning [6,
theme in many sequence learning problems including machine translation and
n isthat longer examples tend to bemorechallenging [11].
ction that weuseimplicitly depends on thelength of theutterance,
L(x, y; ?) = ? log
X
`2 Align(x,y)
TY
t
pctc(`t |x; ?). (9)
is the set of all possible alignments of the characters of the transcription y to
under theCTC operator. In equation 9, theinner term isaproduct over time-steps
which shrinks with the length of the sequence since pctc(`t |x; ?) < 1. This moti-
OK実装だ!](https://image.slidesharecdn.com/dotsnishitoba-170330013855/85/Chainer-Deep-Learning-8-320.jpg)
More Related Content
What's hot (20)
Similar to ChainerでDeep Learningを試すために必要なこと (20)
![[DL Hacks]Visdomを使ったデータ可視化](https://cdn.slidesharecdn.com/ss_thumbnails/dlhacks20181115-181116004623-thumbnail.jpg?width=560&fit=bounds)
![[AI08] 深層学習フレームワーク Chainer × Microsoft で広がる応用](https://cdn.slidesharecdn.com/ss_thumbnails/ai08-170705031536-thumbnail.jpg?width=560&fit=bounds)
More from Retrieva inc. (16)
Recently uploaded (8)
![ElasticsearchでSPLADEする [Search Engineering Tech Talk 2025 Winter]](https://cdn.slidesharecdn.com/ss_thumbnails/searchtech-250228102455-ddc5ce09-thumbnail.jpg?width=560&fit=bounds)
ChainerでDeep Learningを試すために必要なこと
- 2. 自己紹介 ? 西鳥羽二郎 ? ID: jnishi ? 略歴 ? 東京大学情報理工学系研究科コンピュータ科学専攻 修士課程卒業 ? 2006年 Preferred Infrastructureに創業メンバーとして参画 ? プロトタイプ開発 ? プロフェッショナルサービス?サポートサービス ? 研究開発 ? 2016年 レトリバ創業 ? 取締役?リサーチャーとして研究開発に従事 ? 主に音声認識や自然言語処理を担当
- 3. Deep Learning(DL)への取り組み ? 2015年 3月頃に音声認識でDLが使えそうなことを知る ? 2015年 6月からChainerを用いて音声認識エンジンの開発開始 ? 最適化関数 NesterovAG ? 活性化関数 ClippedReLU ? 損失関数 Connectionist Temporal Classification Torch7: Baiduが 2016年1月に公開 TensorFlow: 2016年2月に搭載 Chainer: 2015年 10月に搭載
- 7. Deep Learningの手法をためそう! tterance at atime with better results than evaluating with alargebatch. ples of varying length posesomealgorithmic challenges. Onepossible solution is opagation through time [68], so that all examples have the same sequence length 2]. However, this can inhibit the ability to learn longer term dependencies. Other that presenting examples in order of dif?culty can accelerate online learning [6, theme in many sequence learning problems including machine translation and n isthat longer examples tend to bemorechallenging [11]. ction that weuseimplicitly depends on thelength of theutterance, L(x, y; ?) = ? log X `2 Align(x,y) TY t pctc(`t |x; ?). (9) is the set of all possible alignments of the characters of the transcription y to under theCTC operator. In equation 9, theinner term isaproduct over time-steps which shrinks with the length of the sequence since pctc(`t |x; ?) < 1. This moti- OK実装だ!
- 8. Deep Learningの手法をためそう! tterance at atime with better results than evaluating with alargebatch. ples of varying length posesomealgorithmic challenges. Onepossible solution is opagation through time [68], so that all examples have the same sequence length 2]. However, this can inhibit the ability to learn longer term dependencies. Other that presenting examples in order of dif?culty can accelerate online learning [6, theme in many sequence learning problems including machine translation and n isthat longer examples tend to bemorechallenging [11]. ction that weuseimplicitly depends on thelength of theutterance, L(x, y; ?) = ? log X `2 Align(x,y) TY t pctc(`t |x; ?). (9) is the set of all possible alignments of the characters of the transcription y to under theCTC operator. In equation 9, theinner term isaproduct over time-steps which shrinks with the length of the sequence since pctc(`t |x; ?) < 1. This moti- OK実装だ!
- 12. Deep Learningのシステムを実装する際 ? きちんと処理を理解するには数式を理解することが大事 ? 実際に処理を記述する際には構造を図示したグラフを見ること が多い
- 13. ニューラルネットワークの基本単位 x1 x2 xn … n個の入力 1個の出力 w1 w2 wn u = w1x1 + w2x2 + …+ wnxn ユニット
- 16. 活性化関数 x1 x2 xn … u 出力にスケーリングや制限を かける処理を行うことがある 活性化関数の例 ? ReLU: 負の時は0にする ? sigmoid: 大小関係を維したまま0?1にする ? tanh: 大小関係を維持したまま-1?1にする
- 18. ネットワークとして示す ? ニューラルネットワーク以下のものをコンポーネントとする ネットワークで表すことができる ? 入力 ? Linear ? 活性化関数 ? 損失関数 ? Convolution層 ? 正則化関数 ? etc.
- 26. Deep Learningを行う際に必要なこと ? forward処理 ? back propagation ? 行列計算 ? 微分計算 ? 処理に用いる関数 ? 入出力の関係 ? 入力の大きさ ? 出力の大きさ フレームワークが実行 フレームワークを用いて 実装する時に考えること
- 27. Chainerのexampleコード class MLP(Chain): def __init__(self, n_units=100, n_out=10): super(MLP, self).__init__( l1=L.Linear(None, n_units), l2=L.Linear(None, n_units), l3=L.Linear(None, n_out), ) def __call__(self, x): h1 = F.relu(self.l1(x)) h2 = F.relu(self.l2(h1)) y = self.l3(h2) return y Linear MNIST画像 Linear Linear 784(28x28) 100 100 0?９の判定 10
- 28. layer1 class MLP(Chain): def __init__(self, n_units=100, n_out=10): super(MLP, self).__init__( l1=L.Linear(None, n_units), l2=L.Linear(None, n_units), l3=L.Linear(None, n_out), ) def __call__(self, x): h1 = F.relu(self.l1(x)) h2 = F.relu(self.l2(h1)) y = self.l3(h2) return y Linear MNIST画像 Linear Linear 784(28x28) 100 100 0?９の判定 10 l1
- 29. layer2 class MLP(Chain): def __init__(self, n_units=100, n_out=10): super(MLP, self).__init__( l1=L.Linear(None, n_units), l2=L.Linear(None, n_units), l3=L.Linear(None, n_out), ) def __call__(self, x): h1 = F.relu(self.l1(x)) h2 = F.relu(self.l2(h1)) y = self.l3(h2) return y Linear MNIST画像 Linear Linear 784(28x28) 100 100 0?９の判定 10 l1 l2
- 30. layer3 class MLP(Chain): def __init__(self, n_units=100, n_out=10): super(MLP, self).__init__( l1=L.Linear(None, n_units), l2=L.Linear(None, n_units), l3=L.Linear(None, n_out), ) def __call__(self, x): h1 = F.relu(self.l1(x)) h2 = F.relu(self.l2(h1)) y = self.l3(h2) return y Linear MNIST画像 Linear Linear 784(28x28) 100 100 0?９の判定 10 l1 l2 l3
- 31. forward処理 class MLP(Chain): def __init__(self, n_units=100, n_out=10): super(MLP, self).__init__( l1=L.Linear(None, n_units), l2=L.Linear(None, n_units), l3=L.Linear(None, n_out), ) def __call__(self, x): h1 = F.relu(self.l1(x)) h2 = F.relu(self.l2(h1)) y = self.l3(h2) return y Linear MNIST画像 Linear Linear x h1 h2 0?９の判定 y l1 l2 l3
- 32. forward処理 class MLP(Chain): def __init__(self, n_units=100, n_out=10): super(MLP, self).__init__( l1=L.Linear(None, n_units), l2=L.Linear(None, n_units), l3=L.Linear(None, n_out), ) def __call__(self, x): h1 = F.relu(self.l1(x)) h2 = F.relu(self.l2(h1)) y = self.l3(h2) return y Linear MNIST画像 Linear Linear x h1 h2 0?９の判定 y l1 l2 l3
- 33. forward処理 class MLP(Chain): def __init__(self, n_units=100, n_out=10): super(MLP, self).__init__( l1=L.Linear(None, n_units), l2=L.Linear(None, n_units), l3=L.Linear(None, n_out), ) def __call__(self, x): h1 = F.relu(self.l1(x)) h2 = F.relu(self.l2(h1)) y = self.l3(h2) return y Linear MNIST画像 Linear Linear x h1 h2 0?９の判定 y l1 l2 l3
- 34. まとめ ? Deep Learningを行う際にはネットワーク構造が大事 ? 構造が決まれば後はフレームワークが処理を行う ? Chainerの場合、MNISTのtrain_example.pyの例がシンプル ? Chainerに限らない