Preferred Networks, profile picture
Uploaded byPreferred Networks
PDF, PPTX2,942 views

IIBMP2019 講演資料「オープンソースで始める深層学習」

The document discusses Preferred Networks (PFN), a technology company specializing in artificial intelligence and deep learning applications across various industries including healthcare, robotics, and automobile manufacturing. It highlights their contributions to deep learning frameworks like Chainer and Chainer Chemistry, along with several awards they have received for innovation. Additionally, it touches on their research in areas such as graph convolutional networks for chemical property prediction and the use of Optuna for optimizing machine learning models.

Technology◦
Related topics:
Deep Learning•
In this document
Powered by AI

Introduction to Preferred Networks and its components like Chainer and Chainer Chemistry.

Introduction to Preferred Networks and its components like Chainer and Chainer Chemistry.

Description of PFN's roles in industries such as automobile, healthcare, and robotics. Mention of company partnerships.

List of technical expertise areas related to engineering and machine learning including reinforcement learning and computer vision.

Mention of significant advancements in deep learning, notable awards, and recognitions related to PFN.

Explain Neural Networks (NN), Define-by-Run system in Chainer for training. Discuss computation graph structures and models.

Description of PFN's roles in industries such as automobile, healthcare, and robotics. Mention of company partnerships.

Information on Chainer Chemistry utilizing deep learning for molecular graph analysis and model training datasets.

Introduction to Optuna for hyperparameter optimization, define-by-run capabilities, and various performance metrics.

Download as PDF, PPTX
1 / 123
2 / 123
3 / 123
4 / 123
5 / 123
6 / 123
7 / 123
8 / 123
Most read
9 / 123
10 / 123
11 / 123
12 / 123
13 / 123
14 / 123
15 / 123
16 / 123
17 / 123
18 / 123
19 / 123
20 / 123
21 / 123
22 / 123
23 / 123
24 / 123
25 / 123
26 / 123
27 / 123
28 / 123
29 / 123
30 / 123
31 / 123
32 / 123
33 / 123
34 / 123
35 / 123
36 / 123
37 / 123
38 / 123
39 / 123
40 / 123
41 / 123
42 / 123
43 / 123
44 / 123
45 / 123
46 / 123
47 / 123
48 / 123
49 / 123
50 / 123
51 / 123
52 / 123
53 / 123
54 / 123
55 / 123
56 / 123
57 / 123
58 / 123
59 / 123
60 / 123
61 / 123
62 / 123
63 / 123
64 / 123
65 / 123
66 / 123
67 / 123
68 / 123
69 / 123
70 / 123
71 / 123
72 / 123
73 / 123
74 / 123
75 / 123
76 / 123
77 / 123
78 / 123
79 / 123
80 / 123
81 / 123
82 / 123
83 / 123
84 / 123
85 / 123
86 / 123
87 / 123
88 / 123
89 / 123
90 / 123
91 / 123
92 / 123
93 / 123
94 / 123
95 / 123
96 / 123
97 / 123
98 / 123
99 / 123
100 / 123
101 / 123
102 / 123
103 / 123
104 / 123
105 / 123
106 / 123
107 / 123
108 / 123
109 / 123
110 / 123
111 / 123
112 / 123
113 / 123
114 / 123
115 / 123
116 / 123
117 / 123
118 / 123
119 / 123
120 / 123
121 / 123
122 / 123
123 / 123
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

More Related Content

PDF
「世界モデル」と関連研究について
byMasahiro Suzuki
 
PPTX
【DL輪読会】Scale Efficiently: Insights from Pre-training and Fine-tuning Transfor...
byDeep Learning JP
 
PDF
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか？〜
bySSII
 
PDF
Transformer 動向調査 in 画像認識(修正版)
byKazuki Maeno
 
PPTX
近年のHierarchical Vision Transformer
byYusuke Uchida
 
PPTX
【DL輪読会】Flamingo: a Visual Language Model for Few-Shot Learning 画像×言語の大規模基盤モ...
byDeep Learning JP
 
PDF
“機械学習の説明”の信頼性
bySatoshi Hara
 
PDF
Layer Normalization@NIPS+読み会・関西
byKeigo Nishida
 
「世界モデル」と関連研究について
byMasahiro Suzuki
 
【DL輪読会】Scale Efficiently: Insights from Pre-training and Fine-tuning Transfor...
byDeep Learning JP
 
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか？〜
bySSII
 
Transformer 動向調査 in 画像認識(修正版)
byKazuki Maeno
 
近年のHierarchical Vision Transformer
byYusuke Uchida
 
【DL輪読会】Flamingo: a Visual Language Model for Few-Shot Learning 画像×言語の大規模基盤モ...
byDeep Learning JP
 
“機械学習の説明”の信頼性
bySatoshi Hara
 
Layer Normalization@NIPS+読み会・関西
byKeigo Nishida
 

What's hot

PDF
確率的推論と行動選択
byMasahiro Suzuki
 
PDF
[DL輪読会]近年のオフライン強化学習のまとめ —Offline Reinforcement Learning: Tutorial, Review, an...
byDeep Learning JP
 
PDF
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〜
byPreferred Networks
 
PPTX
【DL輪読会】Hopfield network　関連研究について
byDeep Learning JP
 
PDF
[DL輪読会]data2vec: A General Framework for Self-supervised Learning in Speech,...
byDeep Learning JP
 
PPTX
これからの Vision & Language ～ Acadexit した4つの理由
byYoshitaka Ushiku
 
PPTX
【DL輪読会】ViT + Self Supervised Learningまとめ
byDeep Learning JP
 
PPTX
【DL輪読会】マルチモーダル 基盤モデル
byDeep Learning JP
 
PPTX
[DL輪読会]Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
byDeep Learning JP
 
PDF
ゼロから始める深層強化学習（NLP2018講演資料）/ Introduction of Deep Reinforcement Learning
byPreferred Networks
 
PDF
変分推論法（変分ベイズ法）(PRML第10章)
byTakao Yamanaka
 
PDF
[DL輪読会]The Neural Process Family−Neural Processes関連の実装を読んで動かしてみる−
byDeep Learning JP
 
PDF
強化学習と逆強化学習を組み合わせた模倣学習
byEiji Uchibe
 
PPTX
[Ridge-i 論文よみかい] Wasserstein auto encoder
byMasanari Kimura
 
PDF
ELBO型VAEのダメなところ
byKCS Keio Computer Society
 
PDF
Deeplearning輪読会
by正志 坪坂
 
PPTX
[DL輪読会]Neural Ordinary Differential Equations
byDeep Learning JP
 
PDF
ConvNetの歴史とResNet亜種、ベストプラクティス
byYusuke Uchida
 
PPTX
A3C解説
byharmonylab
 
PDF
最近のDeep Learning (NLP) 界隈におけるAttention事情
byYuta Kikuchi
 
確率的推論と行動選択
byMasahiro Suzuki
 
[DL輪読会]近年のオフライン強化学習のまとめ —Offline Reinforcement Learning: Tutorial, Review, an...
byDeep Learning JP
 
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〜
byPreferred Networks
 
【DL輪読会】Hopfield network　関連研究について
byDeep Learning JP
 
[DL輪読会]data2vec: A General Framework for Self-supervised Learning in Speech,...
byDeep Learning JP
 
これからの Vision & Language ～ Acadexit した4つの理由
byYoshitaka Ushiku
 
【DL輪読会】ViT + Self Supervised Learningまとめ
byDeep Learning JP
 
【DL輪読会】マルチモーダル 基盤モデル
byDeep Learning JP
 
[DL輪読会]Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
byDeep Learning JP
 
ゼロから始める深層強化学習（NLP2018講演資料）/ Introduction of Deep Reinforcement Learning
byPreferred Networks
 
変分推論法（変分ベイズ法）(PRML第10章)
byTakao Yamanaka
 
[DL輪読会]The Neural Process Family−Neural Processes関連の実装を読んで動かしてみる−
byDeep Learning JP
 
強化学習と逆強化学習を組み合わせた模倣学習
byEiji Uchibe
 
[Ridge-i 論文よみかい] Wasserstein auto encoder
byMasanari Kimura
 
ELBO型VAEのダメなところ
byKCS Keio Computer Society
 
Deeplearning輪読会
by正志 坪坂
 
[DL輪読会]Neural Ordinary Differential Equations
byDeep Learning JP
 
ConvNetの歴史とResNet亜種、ベストプラクティス
byYusuke Uchida
 
A3C解説
byharmonylab
 
最近のDeep Learning (NLP) 界隈におけるAttention事情
byYuta Kikuchi
 

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

PDF
Deep learning for molecules, introduction to chainer chemistry
byKenta Oono
 
PDF
Overview of Machine Learning for Molecules and Materials Workshop @ NIPS2017
byKenta Oono
 
PDF
Introduction to Chainer 11 may,2018
byPreferred Networks
 
PDF
Introduction to Chainer
byPreferred Networks
 
PDF
Natural Language Processing with CNTK and Apache Spark with Ali Zaidi
byDatabricks
 
PDF
Introduction to Chainer Chemistry
byPreferred Networks
 
PPTX
241223_JW_labseminar[Neural Message Passing for Quantum Chemistry].pptx
bythanhdowork
 
PDF
Neural Networks in the Wild: Handwriting Recognition
byJohn Liu
 
PDF
Chainer Update v1.8.0 -> v1.10.0+
bySeiya Tokui
 
PDF
Scaling Deep Learning Algorithms on Extreme Scale Architectures
byinside-BigData.com
 
PDF
Introduction to Chainer
byShunta Saito
 
PDF
Overview of Chainer and Its Features
bySeiya Tokui
 
PDF
Introduction to Chainer
bySeiya Tokui
 
PDF
Chainer v4 and v5
byPreferred Networks
 
PDF
Chainer OpenPOWER developer congress HandsON 20170522_ota
byPreferred Networks
 
PDF
Introduction to Chainer: A Flexible Framework for Deep Learning
bySeiya Tokui
 
PDF
OpenPOWER Workshop in Silicon Valley
byGanesan Narayanasamy
 
PPTX
Keras on tensorflow in R & Python
byLonghow Lam
 
PDF
Chainer GTC 2016
byShohei Hido
 
PDF
Alex Smola at AI Frontiers: Scalable Deep Learning Using MXNet
byAI Frontiers
 
Deep learning for molecules, introduction to chainer chemistry
byKenta Oono
 
Overview of Machine Learning for Molecules and Materials Workshop @ NIPS2017
byKenta Oono
 
Introduction to Chainer 11 may,2018
byPreferred Networks
 
Introduction to Chainer
byPreferred Networks
 
Natural Language Processing with CNTK and Apache Spark with Ali Zaidi
byDatabricks
 
Introduction to Chainer Chemistry
byPreferred Networks
 
241223_JW_labseminar[Neural Message Passing for Quantum Chemistry].pptx
bythanhdowork
 
Neural Networks in the Wild: Handwriting Recognition
byJohn Liu
 
Chainer Update v1.8.0 -> v1.10.0+
bySeiya Tokui
 
Scaling Deep Learning Algorithms on Extreme Scale Architectures
byinside-BigData.com
 
Introduction to Chainer
byShunta Saito
 
Overview of Chainer and Its Features
bySeiya Tokui
 
Introduction to Chainer
bySeiya Tokui
 
Chainer v4 and v5
byPreferred Networks
 
Chainer OpenPOWER developer congress HandsON 20170522_ota
byPreferred Networks
 
Introduction to Chainer: A Flexible Framework for Deep Learning
bySeiya Tokui
 
OpenPOWER Workshop in Silicon Valley
byGanesan Narayanasamy
 
Keras on tensorflow in R & Python
byLonghow Lam
 
Chainer GTC 2016
byShohei Hido
 
Alex Smola at AI Frontiers: Scalable Deep Learning Using MXNet
byAI Frontiers
 

More from Preferred Networks

PDF
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
byPreferred Networks
 
PDF
Kaggle Happywhaleコンペ優勝解法でのOptuna使用事例 - 2022/12/10 Optuna Meetup #2
byPreferred Networks
 
PPTX
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」）
byPreferred Networks
 
PPTX
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」）
byPreferred Networks
 
PDF
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
byPreferred Networks
 
PDF
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
byPreferred Networks
 
PDF
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」）
byPreferred Networks
 
PDF
KubeCon + CloudNativeCon Europe 2022 Recap - Batch/HPCの潮流とScheduler拡張事例 / Kub...
byPreferred Networks
 
PDF
KubeCon + CloudNativeCon Europe 2022 Recap / Kubernetes Meetup Tokyo #51 / #k...
byPreferred Networks
 
PDF
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
byPreferred Networks
 
PDF
最新リリース：Optuna V3の全て - 2022/12/10 Optuna Meetup #2
byPreferred Networks
 
PDF
Optuna Dashboardの紹介と設計解説 - 2022/12/10 Optuna Meetup #2
byPreferred Networks
 
PDF
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...
byPreferred Networks
 
PDF
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
byPreferred Networks
 
PDF
Kubernetes ControllerをScale-Outさせる方法 / Kubernetes Meetup Tokyo #55
byPreferred Networks
 
PDF
Kubernetes Service Account As Multi-Cloud Identity / Cloud Native Security Co...
byPreferred Networks
 
PDF
PodSecurityPolicy からGatekeeper に移行しました / Kubernetes Meetup Tokyo #57
byPreferred Networks
 
PDF
独断と偏見で選んだ Kubernetes 1.24 の注目機能と今後! / Kubernetes Meetup Tokyo 50
byPreferred Networks
 
PDF
Kubernetes + containerd で cgroup v2 に移行したら "failed to create fsnotify watcher...
byPreferred Networks
 
PDF
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
byPreferred Networks
 
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
byPreferred Networks
 
Kaggle Happywhaleコンペ優勝解法でのOptuna使用事例 - 2022/12/10 Optuna Meetup #2
byPreferred Networks
 
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」）
byPreferred Networks
 
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」）
byPreferred Networks
 
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
byPreferred Networks
 
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
byPreferred Networks
 
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」）
byPreferred Networks
 
KubeCon + CloudNativeCon Europe 2022 Recap - Batch/HPCの潮流とScheduler拡張事例 / Kub...
byPreferred Networks
 
KubeCon + CloudNativeCon Europe 2022 Recap / Kubernetes Meetup Tokyo #51 / #k...
byPreferred Networks
 
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
byPreferred Networks
 
最新リリース：Optuna V3の全て - 2022/12/10 Optuna Meetup #2
byPreferred Networks
 
Optuna Dashboardの紹介と設計解説 - 2022/12/10 Optuna Meetup #2
byPreferred Networks
 
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...
byPreferred Networks
 
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
byPreferred Networks
 
Kubernetes ControllerをScale-Outさせる方法 / Kubernetes Meetup Tokyo #55
byPreferred Networks
 
Kubernetes Service Account As Multi-Cloud Identity / Cloud Native Security Co...
byPreferred Networks
 
PodSecurityPolicy からGatekeeper に移行しました / Kubernetes Meetup Tokyo #57
byPreferred Networks
 
独断と偏見で選んだ Kubernetes 1.24 の注目機能と今後! / Kubernetes Meetup Tokyo 50
byPreferred Networks
 
Kubernetes + containerd で cgroup v2 に移行したら "failed to create fsnotify watcher...
byPreferred Networks
 
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
byPreferred Networks
 

Recently uploaded

PDF
Supercharge Your JVM with Project Leyden
byAna-Maria Mihalceanu
 
PDF
From Pixels to Insights: Getting Started with Imagery in FME
bySafe Software
 
PPTX
Your First Deep Learning project With CNN (workshop).pptx
byMuhammad Fahad Bashir
 
PDF
How Tridens DevSecOps Ensures Compliance, Security, and Agility
byTridens
 
PDF
The Future-Ready PMO: Unlocking Project Success with Copilot and AI Innovatio...
byWellingtone
 
PPTX
OutSystems ONE 2025-recap presentation.pptx
bymostafaothman27
 
PDF
Session 4 - Agentic Testing with UiPath Agents
byDianaGray10
 
PDF
Q8 DIGITAL IDENTITY HUB - WSO2 Oxygenate Italy 2025
byProfesia Srl, Lynx Group
 
PDF
Wrapping up unowned UTF8 C strings: CStringView
byIgalia
 
PDF
RR B.Ed. educational trust. Ashish Tiwari
byat386834
 
PDF
Transform Your Online Store with AltiusNxt AI Enriched data
byAltiusNxt Technologies
 
PDF
Exclusive Hands-On Workshop: Agentic Automation with UiPath (First Edition)
byanabulhac
 
PDF
Revolutionizing SQL Database Design for the Modern Era.pdf
bySQL DBM
 
PPTX
GenAI GraphTalk - Kuala Lumpur - 4 Nov 2025
bygourisachdeva2
 
PDF
Manage Local Users and Groups - RHCSA (RH124)
byLinuxCert Guru
 
PDF
Transparency Exchange API: How Do You Find the SBOM for a Smart Light Bulb?
byPavel Shukhman
 
PDF
Dr. Robert Krug - Specializes In Predictive Modeling
byDr. Robert Krug
 
PDF
Q3'25 Financial Results and Earnings Presentation
byDropbox
 
PDF
Private Governance: How Decentralized Mechanisms Can Regulate the Crypto Economy
byFederico Ast
 
PDF
"Visual Guide to DSA: Big O Notation, Data Structures, and Algorithms Fundame...
byNusrat Gulbarga
 
Supercharge Your JVM with Project Leyden
byAna-Maria Mihalceanu
 
From Pixels to Insights: Getting Started with Imagery in FME
bySafe Software
 
Your First Deep Learning project With CNN (workshop).pptx
byMuhammad Fahad Bashir
 
How Tridens DevSecOps Ensures Compliance, Security, and Agility
byTridens
 
The Future-Ready PMO: Unlocking Project Success with Copilot and AI Innovatio...
byWellingtone
 
OutSystems ONE 2025-recap presentation.pptx
bymostafaothman27
 
Session 4 - Agentic Testing with UiPath Agents
byDianaGray10
 
Q8 DIGITAL IDENTITY HUB - WSO2 Oxygenate Italy 2025
byProfesia Srl, Lynx Group
 
Wrapping up unowned UTF8 C strings: CStringView
byIgalia
 
RR B.Ed. educational trust. Ashish Tiwari
byat386834
 
Transform Your Online Store with AltiusNxt AI Enriched data
byAltiusNxt Technologies
 
Exclusive Hands-On Workshop: Agentic Automation with UiPath (First Edition)
byanabulhac
 
Revolutionizing SQL Database Design for the Modern Era.pdf
bySQL DBM
 
GenAI GraphTalk - Kuala Lumpur - 4 Nov 2025
bygourisachdeva2
 
Manage Local Users and Groups - RHCSA (RH124)
byLinuxCert Guru
 
Transparency Exchange API: How Do You Find the SBOM for a Smart Light Bulb?
byPavel Shukhman
 
Dr. Robert Krug - Specializes In Predictive Modeling
byDr. Robert Krug
 
Q3'25 Financial Results and Earnings Presentation
byDropbox
 
Private Governance: How Decentralized Mechanisms Can Regulate the Crypto Economy
byFederico Ast
 
"Visual Guide to DSA: Big O Notation, Data Structures, and Algorithms Fundame...
byNusrat Gulbarga
 

IIBMP2019 講演資料「オープンソースで始める深層学習」