SlideShare ist ein Scribd-Unternehmen logo
1 von 123
Downloaden Sie, um offline zu lesen
Preferred Networks :
P
1. Preferred Networks
2. Chainer
3.
4. Chainer Chemistry
5. Optuna
11
PFN careers
Preferred Networks(PFN)
Automobile
Factory
Robot
Manufacturing
Bio /
Healthcare
Personal
Robot
Creative
2014 3
N 270 2019 7
NTT Fanuc Toyota DYHD
JXTG
•
•
● Mechanical Engineering
● Electrical Engineering
● Navigation
● Manipulation
● Embedded Systems
● SLAM / 3D Reconstruction
● Computer Vision
● Simulation
● Reinforcement Learning
● Data Collection / Annotation
● Speech Recognition
● Operating System
● Natural Language Processing(NLP)
● Human–Computer Interaction(HCI)
(Machine
Learning)
(Deep
Learning)
● User Interface (UI)
● Computer Network
● Motion Planning
● IoT data analysis
● Generative models
● 3D computer
graphics (CG)
● Full-stack dev.
● Bioinformatics
● Biology/Chemistry
● Medical Images
Researcher & Engineer
+ α
● 2017 12
DL
MN-1/1b/2
2560 GPU
2019
●
2018
●
● ODSC East 2018, the Open Source Data Science
Project Award
● CEATEC Award
2017
●
● Japan-U.S. Innovation Awards Emerging Leader
Award
● FT ArcelorMittal Boldness in Business Awards
2016
● JEITA
● Forbes JAPAN’s CEO OF THE YEAR 2016
1
(PFN Visual Inspection)
•
Crypko
14
PFDeNA
(PFN DeNA )
14
RSNA Pneumonia Detection Challenge
Kaggle X
X
IT
• IT
•
– (Sirtuin 1)
Chainer
Preferred Networks
(oono@preferred.jp)
2019 9 10
8 IIBMP2019
ü NN Python
→ NN
ü Define-by-Run NN
→ Python
→ NN
ü CuPy NumPy-like GPU
→ CPU/GPU agnostic
Speed up research and development of deep learning and its applications.
Awards
ODSC East 2018
Open Source Data Science Project
2018
https://www.youtube.com/watch?v=yNc5N1MOOt4 https://www.youtube.com/watch?v=lGOjchGdVQs
Wikipedia: Electrocardiography
AI
AI
Design networks Train and evaluate
networks
Dataset
Neural Network as a Computational Graph
• NN
• 2 DAG
y = x1 * x2
z = y - x3
x1 mul suby
x3
z
x2
Define-By-Run
1: x = Variable(np.array(3))
3
5*2 -1
- 4
**2
x z
6
9
3
x
y
3 5*2 -1
x
62: y = 2 * x - 1
3: z = x ** 2 - y
y
9
!, "
For # = 1, … , ##)*+,)#-.:
Get a minibatch (01, 21) (1 = 1, … , #4,)5ℎ7#8*)
9 = ∑;<=
#>?@ABCDEF
∇" !(0;, 2;; ")
" ← " – K9
Output " • L
• θ
Stochastic Gradient Descent, SGD
Backpropagation.
10
y = x1 * x2
ga * z * a ga ∇a z
x1 mul suby
x3
z
x2
z = y - x3
gx1 = gy * x2
gx2 = gy * x1
gz = 1
gy = gz
gx3 = -gz
gzgy
gx3
gx1
gx2
Multi Layer Perceptron; MLP
x Linear
W1 b1
h1 ReLU a1
Linear
W2 b2
h2
Soft
max
prob
Cross
Entropy
loss
t
11
1
2
12
class MLP(chainer.Chain):
def __init__(self):
super(MLP, self).__init__()
with self.init_scope():
self.fc1 = L.Linear(None, 100)
self.fc2 = L.Linear(100, 10)
def forward(self, x):
a1 = F.relu(self.fc1(x))
h2 = self.fc2(a1)
return h2
model = MLP()
model = L.Classifier(model)
x Linear
W1 b1
h1 ReLU
a1 Linear
W2 b2
h2
# Setup Trainer
trainer = training.Trainer(
updater, stop_trigger=(100, 'epoch’))
trainer.extend(extensions.ProgressBar())
trainer.run()
# Parameter Updater
opt = optimizers.SGD(lr=0.01)
opt.setup(model)
updater = training.StandardUpdater(it, opt)
13
# Dataset Preparation
dataset = [(x1, t1), (x2, t2), ...]
it = iterators.SerialIterator(dataset)
Example
https://github.com/pfnet/chainer/tree/master/examples
• (__len__ __getitem__
)
•
• Optimizer, Updater
•
• Extension Trainer
• Extension
Caffemodel
Caffe .caffemodel
VGG16, 19, GoogLeNet, ResNet50, 101, 152
model = links.ResNet50Layers(pretrained_model=‘auto')
image = np.random.uniform(0, 1, (224, 224, 3)).astype(np.float32)
image = prepare(image)
with chainer.using_config('train', False):
with chainer.using_config('enable_backprop', False):
feature = model.extract([image], layers=['pool5'])
• NoneImageNet ResNet
•
ChainerCV
• Detection: FasterRCNNVGG16, SDD300, 512, YOLOv2, v3
• Semantic Segmentation: SegNetBasic, PSPNetResNet101
• Instance Segmentation: FCISResNet101
• Classification: SEResNet50, 101, 152, SEResNeXt50, 101
CuPy GPU
ü NumPy API
ü NVIDIA GPU
cuBLAS, cuDNN, cuRAND, cuSPARSE, and NCCL
ü
ElementwiseKernel, ReductionKernel
To GPU
To CPU
ChainerMN
optimizer = chainer.optimizers.MomentumSGD()
optimizer = chainermn.DistributedOptimizer(
chainer.optimizers.MomentumSGD())
ResNet-50 ImageNet
ImageNet 1024GPU, 15
[Akiba et al., 17] [Tokui et al. KDD19]
Chainer Family
Chainer UI Chainer Chemistry
• Chianer define-by-run
•
Caffe, Theano
• NN Chainer
https://chainer.org
Preferred Networks
(suga@preferred.jp)
2019 9 10
8 IIBMP2019
1.
u ~ DL ~
2.
u AI
u Chainer Tutorial
1.
u ~ DL ~
2.
u AI
u Chainer Tutorial
PFN
Humanoid Robot
Consumer Industrial
Cloud
Device
PhotoGame
Text
Speech
Infrastructure
Factory Robot
Automotive
Smart City
Industry4.0
Industrial IoT
Healthcare
…
DL (1)
DeepVariant ⇒ CNN
(Shanrong Zhao et al., Cloud Computing for Next-Generation Sequencing Data Analysis, 2017 )
(Poplin, Ryan et al., “A universal SNP and small-indel variant caller using deep neural networks.”, 2018 )
•
• DeepVariant (https://github.com/google/deepvariant)
Pileup image
DL (2)
AlphaFold
CASP (Critical Assessment of
techniques for protein Structure
Prediction)
2
(http://predictioncenter.org/casp13/doc/CAS
P13_Abstracts.pdf )
PFN
1.
u ~ DL ~
2.
u AI
u Chainer Tutorial
AI
• AI AI
• https://japan-medical-ai.github.io/medical-ai-course-materials/
• GitHub https://github.com/japan-medical-ai/medical-ai-course-materials
• AI AI https://www.japan-medical-ai.org/?page_id=26
•
• Python Google Colaboratory
1.
2.
3.
1)
• Google Colaboratory Web
• Google
• GPU
1. https://colab.research.google.com/
2. Colaboratory ( )
3. GPU
4.
5.
Colab
2)
•
•
•
•
•
•
•
•
•
•
•
• NumPy
•
• Scikit-learn
• Chainer
1
•
•
•
2
• /
• NumPy
• Scikit-learn
3
•
• NumPy
4 Deep Learning
•
• Chainer
3)
(Sequential regulatory activity prediction across chromosomes with convolutional neural networks, D. R. Kelly and et al., 2018)
5 MRI
• MRI
6
•
- “ ”
- ” ”
- ” ”
( )
7 DL
• DNA
8
• /
1.
u ~ DL ~
2.
u AI
u Chainer Tutorial
Chainer Tutorial
•
• Python
1.
2.
3. AI
•
• AI
• Python Pandas Matplotlib
Chainer Tutorial
• 2019 4 10
• (8 )
• 101 views
• 13 users
• AI
( )
• Python
• Cupy
• Pandas
• Matplotlib
•
• …
•
•
• AI
• Chainer Tutorial
Chainer Chemistry
Preferred Networks
2019 9 10
8 (IIBMP2019)
Chainer Chemistry: Chainer
• Deep learning ( Graph Convolution)
–
https://github.com/pfnet-research/chainer-chemistry
Chainer Chemistry: Chainer
• OSS
– https://github.com/pfnet-research/chainer-chemistry
● Data driven
● Deep learning
○ Graph Convolution
● Chainer Chemistry
○
○
●
○
○
→
A 1.8
B 8.8
C 3.2
D
E
F
→
D 4.4
E 6.3
F 10.5
A 1.8
B 8.8
C 3.2
VS
DFT (Density Functional Theory) MD
→ Pros: ( )
Cons:
→ Pros:
Cons: /
“Neural message passing for quantum chemistry” Justin et al
Deep
learning
Graph Convolution
Graph convolution ~ ~
CNN: Convolutional Neural Network
class label
Chemical
property
Graph convolutional network
Graph convolutional Neural Network
Graph convolution
Graph
Conv
Graph
Conv
Graph
Conv
Graph
Conv
Graph
Readout
Linear Linear
Graph convolutional Neural Network
Graph Graph→
( )
C
N
O
1.0 0.0 0.0 6.0 1.0
atom type
0.0 1.0 0.0 7.0 1.0
0.0 0.0 1.0 8.0 1.0
charge
chirality
Man-made features
Molecular Graph Convolutions: Moving Beyond Fingerprints
Steven Kearnes, Kevin McCloskey, Marc Berndl, Vijay Pande, Patrick Riley arXiv:1603.00856
Graph Convolution: ( )
Graph Convolution
Han Altae-Tran, Bharath Ramsundar, Aneesh S. Pappu, & Vijay Pande (2017). Low Data Drug
Discovery with One-Shot Learning. ACS Cent. Sci., 3 (4)
Graph Readout: ( )
Han Altae-Tran, Bharath Ramsundar, Aneesh S. Pappu, & Vijay Pande (2017). Low Data Drug
Discovery with One-Shot Learning. ACS Cent. Sci., 3 (4)
Graph convolutional Neural Network
Graph convolution
Graph
Conv
Graph
Conv
Graph
Conv
Graph
Conv
Graph
Readout
Linear Linear
Graph convolutional Neural Network
Graph Graph→
Chainer Chemistry
●
○
●
○ Graph Convolution
●
○ Imbalanced
○
File Parser
(SDF file, CSV file) QM 9, Tox21, molnet dataset
Graph convolution NN
GraphConvolution (Upate)
GraphReadout
Preprocessing
(NFP, GGNN, SchNet)
Example
Train and prediction
with
QM9/tox21/molnet
dataset
Model
Layer/Function
Dataset
Pretrained
Model
(TBD)
Preprocessor (Feature Extractor)
Dataset introduction - tox21
# of Dataset: Train 11757, Validation 295, Test 645
Label - Following 12 types of toxity is included:
'NR-AR', 'NR-AR-LBD', 'NR-AhR', 'NR-Aromatase', 'NR-ER', 'NR-ER-LBD',
'NR-PPAR-gamma', 'SR-ARE', 'SR-ATAD5', 'SR-HSE', 'SR-MMP', 'SR-p53'
Example:
SMILES:
C(=O)C1(O)Cc2c(O)c3c(c(O)c2C(OC2CC
(N)C(O)C(C)O2)C1)C(=O)c1c(O)cccc1C3
=O
LABEL: [ 0 1 -1 1 -1 1 -1 -1 1 -1 1 1]
SMILES:
CCCOc1ccc(C(=O)CCN2CCCCC2)cc1.Cl
LABEL: [ 0 0 0 -1 1 0 0 -1 -1 -1 0 0]
SMILES:
CCOP(=S)(OCC)SC(CCl)N1C(=O)c2cccc
c2C1=O
LABEL: [ 0 0 1 0 1 1 0 1 0 0 -1 -1]
SMILES: O=c1c(O)c(-
c2ccc(O)cc2)oc2cc(O)cc(O)c12
LABEL: [ 0 0 1 -1 1 1 -1 0 0 0 1 0]
2948 3895 6558 7381
Dataset introduction - molnet
http://moleculenet.ai/datasets-1
Chainer Chemistry molecutenet
molnet:
• PubChem PDBbind
•
Dataset introduction - molnet
http://moleculenet.ai/datasets-1
Chainer Chemistry
As of 2019/9/9 from https://github.com/pfnet-research/chainer-chemistry#supported-models
• NFP: Neural Fingerprint [2, 3]
• GGNN: Gated Graph Neural Network [4, 3]
• WeaveNet [5, 3]
• SchNet [6]
• RSGCN: Renormalized Spectral Graph Convolutional Network [10]
• RelGCN: Relational Graph Convolutional Network [14]
• GAT: Graph Attention Networks [15]
• GIN: Graph Isomorphism Networks [17]
• MPNN: Message Passing Neural Networks [3]
• Set2Set [19]
• Graph Warp Module (GWM) [18]-attached models
… →
4 IT (2017 )
• Sirtuin 1
250
•
• 400
200
• 2-stage
– Thermal Shift Assay
– Inhibitory assay → IC50 measurement Sirtuin 1
http://www.ipab.org/eventschedule/contest/contest4
Ours Average
(18 teams in total)
1st screening (TSA) 23 / 200 (11.5%) 69 / 3559 (1.9 %)
2nd screening (IC50) 1 5
We found one hit compound and
won one of Grand prize (IPAB )
Kaggle Molecular property prediction
Kaggle:
CHAMPS
NMR Coupling constant
https://www.kaggle.com/toshik/schnet-starter-kit
•
• JXTG
… and more!
BayesGrad
“BayesGrad: Explaining Predictions of Graph Convolutional Networks”
Akita et al., ICONIP 2018
https://arxiv.org/abs/1807.01985
https://github.com/pfnet-research/bayesgrad
Dropout Saliency
GWM
“Graph Warp Module: an Auxiliary Module for Boosting the Power of Graph
Neural Networks in Molecular Graph Analysis” Ishiguro et al.
https://arxiv.org/abs/1902.01020
https://github.com/pfnet-research/chainer-chemistry
Graph Convolution Neural Network
GraphNVP
“GraphNVP: An Invertible Flow Model for Generating Molecular Graphs”
Madhawa et al.
https://arxiv.org/abs/1905.11600
https://github.com/pfnet-research/graph-nvp
Flow
Optuna
Preferred Networks
2019 9 10
8 ( IIBMP2019 )
●
● :
○ Define-by-Run API
○
○
● Chainer
2
https://optuna.org
●
● Optuna
● :
○ Define-by-Run
○
○
●
3
5
● :
○
○ :
● :
○
:
•
•
6
×
PASCAL VOC2007
7
8
● SGD
● Momentum SGD
● Adam
● etc
9
● SGD
● Momentum SGD
○ learning rate (LR) = ?
○ momentum = ?
● Adam
● etc
:
• LR: 0.1
• Dropout: 0.5
… !
Accuracy: 0.6
Trial 1
?
• LR: 0.01
• Dropout: 0.0
… !
Accuracy: 0.5
Trial 2
• LR: 0.05
• Dropout: 0.3
… !
Accuracy: 0.8
Trial 3
10
:
• LR: 0.1
• Dropout: 0.5
… !
Accuracy: 0.6
Trial 1
?
• LR: 0.01
• Dropout: 0.0
… !
Accuracy: 0.5
Trial 2
?
• LR: 0.05
• Dropout: 0.3
… !
Accuracy: 0.8
Trial 3
11
Optuna
13
●
○ : f(X) → y
■ X:
■ y:
○ : argmin f(X)
■ X f(X)
■ f(X) X
f
: (x - 2)2
14
: (x - 2)2
15
: (x - 2)2
16
trial
: (x - 2)2
17
(SuggestAPI)
: (x - 2)2
18
: (x - 2)2
19
study
: (x - 2)2
20
: (x - 2)2
21
● :
○ (x): 1.99016
○ : 0.00009
: (x - 2)2
22
● :
○ TPE: Tree-structured Parzen Estimator
○
○
Define-by-Run
Define-by-Run API
24
● Define-by-Run:
○
○ : Chainer, PyTorch, TensorFlow Eager
●
:
25
0, 5, 3, 8, …
MNIST ( )
From: https://en.wikipedia.org/wiki/MNIST_database
26
27
Define-by-Run
28
:
● Python
●
(pruning)
30
•
31
• SVHN CNN
•
(Successive Halving)
SVHN: The Street View Housing Numbers Dataset
CNN: Convolutional Neural Network
32
34
•
•
• study :
○ study_name: study
○ storage: (RDB) URL
⇒ study
35
36
RDB
Storage
(e.g., MySQL)
RDBURLStudy
Kaggle: Open Images Challenge 2018
38
•
• NMW
mAP
○ NMW: Non-Maximum Weighted suppression
○ mAP: mean Average Precision
: HPL
39
• HPL (High Performance Linpack)
○
○ (MN-1b)
• :
○ E.g., LU Broadcast
○
⇒ Optuna
41
•
• Optuna
•
Make your optimization optimized!
42

Weitere ähnliche Inhalte

Was ist angesagt?

Was ist angesagt? (20)

数学で解き明かす深層学習の原理
数学で解き明かす深層学習の原理数学で解き明かす深層学習の原理
数学で解き明かす深層学習の原理
 
(DL hacks輪読) Deep Kernel Learning
(DL hacks輪読) Deep Kernel Learning(DL hacks輪読) Deep Kernel Learning
(DL hacks輪読) Deep Kernel Learning
 
深層学習の数理:カーネル法, スパース推定との接点
深層学習の数理:カーネル法, スパース推定との接点深層学習の数理:カーネル法, スパース推定との接点
深層学習の数理:カーネル法, スパース推定との接点
 
PyMCがあれば,ベイズ推定でもう泣いたりなんかしない
PyMCがあれば,ベイズ推定でもう泣いたりなんかしないPyMCがあれば,ベイズ推定でもう泣いたりなんかしない
PyMCがあれば,ベイズ推定でもう泣いたりなんかしない
 
合成経路探索 -論文まとめ- (PFN中郷孝祐)
合成経路探索 -論文まとめ-  (PFN中郷孝祐)合成経路探索 -論文まとめ-  (PFN中郷孝祐)
合成経路探索 -論文まとめ- (PFN中郷孝祐)
 
Sliced Wasserstein距離と生成モデル
Sliced Wasserstein距離と生成モデルSliced Wasserstein距離と生成モデル
Sliced Wasserstein距離と生成モデル
 
モデル高速化百選
モデル高速化百選モデル高速化百選
モデル高速化百選
 
CUDAプログラミング入門
CUDAプログラミング入門CUDAプログラミング入門
CUDAプログラミング入門
 
全力解説!Transformer
全力解説!Transformer全力解説!Transformer
全力解説!Transformer
 
PCAの最終形態GPLVMの解説
PCAの最終形態GPLVMの解説PCAの最終形態GPLVMの解説
PCAの最終形態GPLVMの解説
 
機械学習による統計的実験計画(ベイズ最適化を中心に)
機械学習による統計的実験計画(ベイズ最適化を中心に)機械学習による統計的実験計画(ベイズ最適化を中心に)
機械学習による統計的実験計画(ベイズ最適化を中心に)
 
混合モデルとEMアルゴリズム(PRML第9章)
混合モデルとEMアルゴリズム(PRML第9章)混合モデルとEMアルゴリズム(PRML第9章)
混合モデルとEMアルゴリズム(PRML第9章)
 
ソフト高速化の専門家が教える!AI・IoTエッジデバイスの選び方
ソフト高速化の専門家が教える!AI・IoTエッジデバイスの選び方ソフト高速化の専門家が教える!AI・IoTエッジデバイスの選び方
ソフト高速化の専門家が教える!AI・IoTエッジデバイスの選び方
 
深層学習の不確実性 - Uncertainty in Deep Neural Networks -
深層学習の不確実性 - Uncertainty in Deep Neural Networks -深層学習の不確実性 - Uncertainty in Deep Neural Networks -
深層学習の不確実性 - Uncertainty in Deep Neural Networks -
 
SSII2021 [TS2] 深層強化学習 〜 強化学習の基礎から応用まで 〜
SSII2021 [TS2] 深層強化学習 〜 強化学習の基礎から応用まで 〜SSII2021 [TS2] 深層強化学習 〜 強化学習の基礎から応用まで 〜
SSII2021 [TS2] 深層強化学習 〜 強化学習の基礎から応用まで 〜
 
工学系大学4年生のための論文の読み方
工学系大学4年生のための論文の読み方工学系大学4年生のための論文の読み方
工学系大学4年生のための論文の読み方
 
ノンパラベイズ入門の入門
ノンパラベイズ入門の入門ノンパラベイズ入門の入門
ノンパラベイズ入門の入門
 
PRML第6章「カーネル法」
PRML第6章「カーネル法」PRML第6章「カーネル法」
PRML第6章「カーネル法」
 
[DL輪読会]逆強化学習とGANs
[DL輪読会]逆強化学習とGANs[DL輪読会]逆強化学習とGANs
[DL輪読会]逆強化学習とGANs
 
機械学習と機械発見:自然科学研究におけるデータ利活用の再考
機械学習と機械発見:自然科学研究におけるデータ利活用の再考機械学習と機械発見:自然科学研究におけるデータ利活用の再考
機械学習と機械発見:自然科学研究におけるデータ利活用の再考
 

Ähnlich wie IIBMP2019 講演資料「オープンソースで始める深層学習」

Developing applications with rules, workflow and event processing (it@cork 2010)
Developing applications with rules, workflow and event processing (it@cork 2010)Developing applications with rules, workflow and event processing (it@cork 2010)
Developing applications with rules, workflow and event processing (it@cork 2010)
Geoffrey De Smet
 
Optimization of Continuous Queries in Federated Database and Stream Processin...
Optimization of Continuous Queries in Federated Database and Stream Processin...Optimization of Continuous Queries in Federated Database and Stream Processin...
Optimization of Continuous Queries in Federated Database and Stream Processin...
Zbigniew Jerzak
 
RAPIDS cuGraph – Accelerating all your Graph needs
RAPIDS cuGraph – Accelerating all your Graph needsRAPIDS cuGraph – Accelerating all your Graph needs
RAPIDS cuGraph – Accelerating all your Graph needs
Connected Data World
 
Python for Chemistry
Python for ChemistryPython for Chemistry
Python for Chemistry
guest5929fa7
 
Python for Chemistry
Python for ChemistryPython for Chemistry
Python for Chemistry
baoilleach
 
Building Deep Reinforcement Learning Applications on Apache Spark with Analyt...
Building Deep Reinforcement Learning Applications on Apache Spark with Analyt...Building Deep Reinforcement Learning Applications on Apache Spark with Analyt...
Building Deep Reinforcement Learning Applications on Apache Spark with Analyt...
Databricks
 

Ähnlich wie IIBMP2019 講演資料「オープンソースで始める深層学習」 (20)

Achitecture Aware Algorithms and Software for Peta and Exascale
Achitecture Aware Algorithms and Software for Peta and ExascaleAchitecture Aware Algorithms and Software for Peta and Exascale
Achitecture Aware Algorithms and Software for Peta and Exascale
 
End-to-end Big Data Projects with Python - StampedeCon Big Data Conference 2017
End-to-end Big Data Projects with Python - StampedeCon Big Data Conference 2017End-to-end Big Data Projects with Python - StampedeCon Big Data Conference 2017
End-to-end Big Data Projects with Python - StampedeCon Big Data Conference 2017
 
Deep Convolutional GANs - meaning of latent space
Deep Convolutional GANs - meaning of latent spaceDeep Convolutional GANs - meaning of latent space
Deep Convolutional GANs - meaning of latent space
 
Bogdan Kecman INIT Presentation
Bogdan Kecman INIT PresentationBogdan Kecman INIT Presentation
Bogdan Kecman INIT Presentation
 
Developing applications with rules, workflow and event processing (it@cork 2010)
Developing applications with rules, workflow and event processing (it@cork 2010)Developing applications with rules, workflow and event processing (it@cork 2010)
Developing applications with rules, workflow and event processing (it@cork 2010)
 
Optimization of Continuous Queries in Federated Database and Stream Processin...
Optimization of Continuous Queries in Federated Database and Stream Processin...Optimization of Continuous Queries in Federated Database and Stream Processin...
Optimization of Continuous Queries in Federated Database and Stream Processin...
 
Hardware Accelerated Machine Learning Solution for Detecting Fraud and Money ...
Hardware Accelerated Machine Learning Solution for Detecting Fraud and Money ...Hardware Accelerated Machine Learning Solution for Detecting Fraud and Money ...
Hardware Accelerated Machine Learning Solution for Detecting Fraud and Money ...
 
Bogdan Kecman Advanced Databasing
Bogdan Kecman Advanced DatabasingBogdan Kecman Advanced Databasing
Bogdan Kecman Advanced Databasing
 
RAPIDS cuGraph – Accelerating all your Graph needs
RAPIDS cuGraph – Accelerating all your Graph needsRAPIDS cuGraph – Accelerating all your Graph needs
RAPIDS cuGraph – Accelerating all your Graph needs
 
Building an ML Platform with Ray and MLflow
Building an ML Platform with Ray and MLflowBuilding an ML Platform with Ray and MLflow
Building an ML Platform with Ray and MLflow
 
【論文紹介】Relay: A New IR for Machine Learning Frameworks
【論文紹介】Relay: A New IR for Machine Learning Frameworks【論文紹介】Relay: A New IR for Machine Learning Frameworks
【論文紹介】Relay: A New IR for Machine Learning Frameworks
 
DSD-INT 2018 Work with iMOD MODFLOW models in Python - Visser Bootsma
DSD-INT 2018 Work with iMOD MODFLOW models in Python - Visser BootsmaDSD-INT 2018 Work with iMOD MODFLOW models in Python - Visser Bootsma
DSD-INT 2018 Work with iMOD MODFLOW models in Python - Visser Bootsma
 
FPGA-BASED-CNN.pdf
FPGA-BASED-CNN.pdfFPGA-BASED-CNN.pdf
FPGA-BASED-CNN.pdf
 
Toronto meetup 20190917
Toronto meetup 20190917Toronto meetup 20190917
Toronto meetup 20190917
 
Using Bayesian Optimization to Tune Machine Learning Models
Using Bayesian Optimization to Tune Machine Learning ModelsUsing Bayesian Optimization to Tune Machine Learning Models
Using Bayesian Optimization to Tune Machine Learning Models
 
Using Bayesian Optimization to Tune Machine Learning Models
Using Bayesian Optimization to Tune Machine Learning ModelsUsing Bayesian Optimization to Tune Machine Learning Models
Using Bayesian Optimization to Tune Machine Learning Models
 
Python for Chemistry
Python for ChemistryPython for Chemistry
Python for Chemistry
 
Python for Chemistry
Python for ChemistryPython for Chemistry
Python for Chemistry
 
pgconfasia2016 plcuda en
pgconfasia2016 plcuda enpgconfasia2016 plcuda en
pgconfasia2016 plcuda en
 
Building Deep Reinforcement Learning Applications on Apache Spark with Analyt...
Building Deep Reinforcement Learning Applications on Apache Spark with Analyt...Building Deep Reinforcement Learning Applications on Apache Spark with Analyt...
Building Deep Reinforcement Learning Applications on Apache Spark with Analyt...
 

Mehr von Preferred Networks

Mehr von Preferred Networks (20)

PodSecurityPolicy からGatekeeper に移行しました / Kubernetes Meetup Tokyo #57
PodSecurityPolicy からGatekeeper に移行しました / Kubernetes Meetup Tokyo #57PodSecurityPolicy からGatekeeper に移行しました / Kubernetes Meetup Tokyo #57
PodSecurityPolicy からGatekeeper に移行しました / Kubernetes Meetup Tokyo #57
 
Optunaを使ったHuman-in-the-loop最適化の紹介 - 2023/04/27 W&B 東京ミートアップ #3
Optunaを使ったHuman-in-the-loop最適化の紹介 - 2023/04/27 W&B 東京ミートアップ #3Optunaを使ったHuman-in-the-loop最適化の紹介 - 2023/04/27 W&B 東京ミートアップ #3
Optunaを使ったHuman-in-the-loop最適化の紹介 - 2023/04/27 W&B 東京ミートアップ #3
 
Kubernetes + containerd で cgroup v2 に移行したら "failed to create fsnotify watcher...
Kubernetes + containerd で cgroup v2 に移行したら "failed to create fsnotify watcher...Kubernetes + containerd で cgroup v2 に移行したら "failed to create fsnotify watcher...
Kubernetes + containerd で cgroup v2 に移行したら "failed to create fsnotify watcher...
 
深層学習の新しい応用と、 それを支える計算機の進化 - Preferred Networks CEO 西川徹 (SEMICON Japan 2022 Ke...
深層学習の新しい応用と、 それを支える計算機の進化 - Preferred Networks CEO 西川徹 (SEMICON Japan 2022 Ke...深層学習の新しい応用と、 それを支える計算機の進化 - Preferred Networks CEO 西川徹 (SEMICON Japan 2022 Ke...
深層学習の新しい応用と、 それを支える計算機の進化 - Preferred Networks CEO 西川徹 (SEMICON Japan 2022 Ke...
 
Kubernetes ControllerをScale-Outさせる方法 / Kubernetes Meetup Tokyo #55
Kubernetes ControllerをScale-Outさせる方法 / Kubernetes Meetup Tokyo #55Kubernetes ControllerをScale-Outさせる方法 / Kubernetes Meetup Tokyo #55
Kubernetes ControllerをScale-Outさせる方法 / Kubernetes Meetup Tokyo #55
 
Kaggle Happywhaleコンペ優勝解法でのOptuna使用事例 - 2022/12/10 Optuna Meetup #2
Kaggle Happywhaleコンペ優勝解法でのOptuna使用事例 - 2022/12/10 Optuna Meetup #2Kaggle Happywhaleコンペ優勝解法でのOptuna使用事例 - 2022/12/10 Optuna Meetup #2
Kaggle Happywhaleコンペ優勝解法でのOptuna使用事例 - 2022/12/10 Optuna Meetup #2
 
最新リリース:Optuna V3の全て - 2022/12/10 Optuna Meetup #2
最新リリース:Optuna V3の全て - 2022/12/10 Optuna Meetup #2最新リリース:Optuna V3の全て - 2022/12/10 Optuna Meetup #2
最新リリース:Optuna V3の全て - 2022/12/10 Optuna Meetup #2
 
Optuna Dashboardの紹介と設計解説 - 2022/12/10 Optuna Meetup #2
Optuna Dashboardの紹介と設計解説 - 2022/12/10 Optuna Meetup #2Optuna Dashboardの紹介と設計解説 - 2022/12/10 Optuna Meetup #2
Optuna Dashboardの紹介と設計解説 - 2022/12/10 Optuna Meetup #2
 
スタートアップが提案する2030年の材料開発 - 2022/11/11 QPARC講演
スタートアップが提案する2030年の材料開発 - 2022/11/11 QPARC講演スタートアップが提案する2030年の材料開発 - 2022/11/11 QPARC講演
スタートアップが提案する2030年の材料開発 - 2022/11/11 QPARC講演
 
Deep Learningのための専用プロセッサ「MN-Core」の開発と活用(2022/10/19東大大学院「 融合情報学特別講義Ⅲ」)
Deep Learningのための専用プロセッサ「MN-Core」の開発と活用(2022/10/19東大大学院「 融合情報学特別講義Ⅲ」)Deep Learningのための専用プロセッサ「MN-Core」の開発と活用(2022/10/19東大大学院「 融合情報学特別講義Ⅲ」)
Deep Learningのための専用プロセッサ「MN-Core」の開発と活用(2022/10/19東大大学院「 融合情報学特別講義Ⅲ」)
 
PFNにおける研究開発(2022/10/19 東大大学院「融合情報学特別講義Ⅲ」)
PFNにおける研究開発(2022/10/19 東大大学院「融合情報学特別講義Ⅲ」)PFNにおける研究開発(2022/10/19 東大大学院「融合情報学特別講義Ⅲ」)
PFNにおける研究開発(2022/10/19 東大大学院「融合情報学特別講義Ⅲ」)
 
自然言語処理を 役立てるのはなぜ難しいのか(2022/10/25東大大学院「自然言語処理応用」)
自然言語処理を 役立てるのはなぜ難しいのか(2022/10/25東大大学院「自然言語処理応用」)自然言語処理を 役立てるのはなぜ難しいのか(2022/10/25東大大学院「自然言語処理応用」)
自然言語処理を 役立てるのはなぜ難しいのか(2022/10/25東大大学院「自然言語処理応用」)
 
Kubernetes にこれから入るかもしれない注目機能!(2022年11月版) / TechFeed Experts Night #7 〜 コンテナ技術を語る
Kubernetes にこれから入るかもしれない注目機能!(2022年11月版) / TechFeed Experts Night #7 〜 コンテナ技術を語るKubernetes にこれから入るかもしれない注目機能!(2022年11月版) / TechFeed Experts Night #7 〜 コンテナ技術を語る
Kubernetes にこれから入るかもしれない注目機能!(2022年11月版) / TechFeed Experts Night #7 〜 コンテナ技術を語る
 
Matlantis™のニューラルネットワークポテンシャルPFPの適用範囲拡張
Matlantis™のニューラルネットワークポテンシャルPFPの適用範囲拡張Matlantis™のニューラルネットワークポテンシャルPFPの適用範囲拡張
Matlantis™のニューラルネットワークポテンシャルPFPの適用範囲拡張
 
PFNのオンプレ計算機クラスタの取り組み_第55回情報科学若手の会
PFNのオンプレ計算機クラスタの取り組み_第55回情報科学若手の会PFNのオンプレ計算機クラスタの取り組み_第55回情報科学若手の会
PFNのオンプレ計算機クラスタの取り組み_第55回情報科学若手の会
 
続・PFN のオンプレML基盤の取り組み / オンプレML基盤 on Kubernetes 〜PFN、ヤフー〜 #2
続・PFN のオンプレML基盤の取り組み / オンプレML基盤 on Kubernetes 〜PFN、ヤフー〜 #2続・PFN のオンプレML基盤の取り組み / オンプレML基盤 on Kubernetes 〜PFN、ヤフー〜 #2
続・PFN のオンプレML基盤の取り組み / オンプレML基盤 on Kubernetes 〜PFN、ヤフー〜 #2
 
Kubernetes Service Account As Multi-Cloud Identity / Cloud Native Security Co...
Kubernetes Service Account As Multi-Cloud Identity / Cloud Native Security Co...Kubernetes Service Account As Multi-Cloud Identity / Cloud Native Security Co...
Kubernetes Service Account As Multi-Cloud Identity / Cloud Native Security Co...
 
KubeCon + CloudNativeCon Europe 2022 Recap / Kubernetes Meetup Tokyo #51 / #k...
KubeCon + CloudNativeCon Europe 2022 Recap / Kubernetes Meetup Tokyo #51 / #k...KubeCon + CloudNativeCon Europe 2022 Recap / Kubernetes Meetup Tokyo #51 / #k...
KubeCon + CloudNativeCon Europe 2022 Recap / Kubernetes Meetup Tokyo #51 / #k...
 
KubeCon + CloudNativeCon Europe 2022 Recap - Batch/HPCの潮流とScheduler拡張事例 / Kub...
KubeCon + CloudNativeCon Europe 2022 Recap - Batch/HPCの潮流とScheduler拡張事例 / Kub...KubeCon + CloudNativeCon Europe 2022 Recap - Batch/HPCの潮流とScheduler拡張事例 / Kub...
KubeCon + CloudNativeCon Europe 2022 Recap - Batch/HPCの潮流とScheduler拡張事例 / Kub...
 
独断と偏見で選んだ Kubernetes 1.24 の注目機能と今後! / Kubernetes Meetup Tokyo 50
独断と偏見で選んだ Kubernetes 1.24 の注目機能と今後! / Kubernetes Meetup Tokyo 50独断と偏見で選んだ Kubernetes 1.24 の注目機能と今後! / Kubernetes Meetup Tokyo 50
独断と偏見で選んだ Kubernetes 1.24 の注目機能と今後! / Kubernetes Meetup Tokyo 50
 

Kürzlich hochgeladen

Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
WSO2
 

Kürzlich hochgeladen (20)

Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWEREMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
EMPOWERMENT TECHNOLOGY GRADE 11 QUARTER 2 REVIEWER
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu SubbuApidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
 
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data DiscoveryTrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
TrustArc Webinar - Unlock the Power of AI-Driven Data Discovery
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 
Navi Mumbai Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Navi Mumbai Call Girls 🥰 8617370543 Service Offer VIP Hot ModelNavi Mumbai Call Girls 🥰 8617370543 Service Offer VIP Hot Model
Navi Mumbai Call Girls 🥰 8617370543 Service Offer VIP Hot Model
 
FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024FWD Group - Insurer Innovation Award 2024
FWD Group - Insurer Innovation Award 2024
 

IIBMP2019 講演資料「オープンソースで始める深層学習」