GO DEEPER

カメラや写真やディープラーニングや人工知能のお話(2017年9月)

 

Google Research Blog

MatConvNet

HELLO CYBERNETICS

IoTニュース

========== Data Sets ==========

THE MNIST DATABASE of handwritten digits

CIFAR

ImageNet

The PASCAL Visual Object Classes Homepage

COCO - Common Objects in Context

========== Machine Learning ==========

機械学習をゼロから1ヶ月間勉強し続けた結果

Coursera - Machine Learning

機械学習を納品するのは、そんなに簡単な話じゃないから気をつけて

パターン認識と機械学習の学習

The Elements of Statistical Learning : Data Mining, Inference, and Prediction Second Edition

Statistical Learning with Sparsity : The Lasso and Generalizations

 

【Neural Network】

ニューラルネットワークの動物園:ニューラルネットワーク・アーキテクチャのチートシート(前編)

ニューラルネットワークの動物園:ニューラルネットワーク・アーキテクチャのチートシート(後編)

 

【CNN】

Res netと派生研究の紹介

Convolutional Neural Networksのトレンド

●Inception-v1 (GoogLeNet)
Going Deeper with Convolutions
References
-[1]Know your meme: We need to go deeper.
-[2]Provable Bounds for Learning Some Deep Representations
-[3]On Two-Dimensional Sparse Matrix Partitioning: Models, Methods, and a Recipe.
-[4]Large Scale Distributed Deep Networks
-[5]Scalable Object Detection using Deep Neural Networks
-[6]Rich feature hierarchies for accurate object detection and semantic segmentation(R-CNN)
-[7]Improving neural networks by preventing co-adaptation of feature detectors
-[8]Some Improvements on Deep Convolutional Neural Network Based Image Classification
-[9]ImageNet Classification with Deep Convolutional Neural Networks (AlexNet)
-[10]Backpropagation Applied to Handwritten Zip Code Recognition
-[11]Gradient-Based Learning Applied to Document Recognition
-[12]Network in Network
-[13]Acceleration of Stochastic Approximation by Averaging
-[14]OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
-[15]Robust Object Recognition with Cortex-Like Mechanisms
-[16]Scaling Up Matrix Computations on Shared-Memory Manycore Systems with 1000 CPU Cores
-[17]On the importance of initialization and momentum in deep Learning
-[18]Deep Neural Networks for Object Detection
-[19]DeepPose: Human Pose Estimation via Deep Neural Networks
-[20]Segmentation as Selective Search for Object Recognition
-[21]Visualizing and Understanding Convolutional Networks

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

[Survey]Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

●Residual Network (ResNet)
Deep Residual Learning for Image Recognition
References
-[1]
-[2]

Residual Network(ResNet)の理解とチューニングのベストプラクティス

●Xception
Xception: Deep Learning with Depthwise Separable Convolutions
References
-[1]
-[2]

[DL輪読会]Xception: Deep Learning with Depthwise Separable Convolutions

●VGG-VD
Very Deep Convolutional Networks for Large-Scalse Image Recognition
References
-[1]
-[2]

●VGG-S,M,F
Return of the Devil in the Details: Delving Deep into Convolutional Nets
References
-[1]
-[2]

●AlexNet
ImageNet Classification with Deep Convolutional Neural Networks
References
-[1]
-[2]

●SENet
Squeeze-and-Excitation Networks
References
-[1]
-[2]

●NASNet
Leaning Transferable Architectures for Scalable Image Recognition
References
-[1]
-[2]
-[70]Neural Architecture Search with Reinforcement Learning

●AutoML
Neural Architecture Search with Reinforcement Learning
Large-Scale Evolution of Image Classifier

 

●R-CNN
Rich feature hierarchies for accurate object detection and semantic segmentation
References
-[1]
-[2]

EdgeBoxes: Locating Object Proposals from Edges

●Fast R-CNN
Fast R-CNN
References
-[1]
-[2]

●Faster R-CNN
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
References
-[1]
-[2]

●Single Shot Multibox Detector
SSD: Single Shot MultiBox Detector
References
-[1]
-[2]

YOLO & YOLOv2

 

 

【RNN】

わかるLSTM 〜 最近の動向と共に

LSTMネットワークの概要

【GAN】

はじめてのGAN

 

【VAE】

 

【SAE】

 

【Deep Q-Network】

最近のDQN

【Deep Boltzmann Machines】

Deep Boltzmann Machines

 

【正則化】

【SVM】

サポートベクターマシン - 産総研 赤穂先生

SVM、ニューラルネットなどに共通する分類問題における考え方 - Hello Cybernetics

サポートベクターマシンの概要

【カーネル法】

カーネル法入門 1.カーネル法へのイントロダクション - 統数研 福水先生

 

【グラフィカルモデル】

【アンサンブル学習】

【強化学習】

ゼロからDeepまで学ぶ強化学習

 

【フレームワーク系】

TensorFlow

keras

Preferred Networks

 

【その他】

========== Computational Fluid Dynamics ==========

【界面追跡】

【界面捕獲】

【MPS】

【SPH】

【Lattice Boltzmann】

【Non-Newtonian Fluid】

公開日:
最終更新日:2017/12/07