The model is a convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards. Volodymyr Mnih, et al., "Playing Atari with Deep Reinforcement Lea…

We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. Volodymyr Mnih, et al., "Playing Atari with Deep Reinforcement Learning" https://arx…

One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection. Christian Szegedy, et al., "Going Deeper with Co…

To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. Christian Szegedy, et al., "Going Deeper with Convolutions" https://arxiv.org/abs/1409.4842 2014年のILSVRCで1…

This was achieved by a carefully crafted design that allows for increasing the depth and width of the network while keeping the computational budget constant. Christian Szegedy, et al., "Going Deeper with Convolutions" https://arxiv.org/ab…

The main hallmark of this architecture is the improved utilization of the computing resources inside the network. Christian Szegedy, et al., "Going Deeper with Convolutions" https://arxiv.org/abs/1409.4842 2014年のILSVRCで1位になったディー…

We propose a deep convolutional neural network architecture codenamed Inception, which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILS…

Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation. Kaiming He, et al.…

Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Kaiming He, et al., "Deep Residual Learning for Image Recognition" https://arxiv.org/abs/1512.03385 2015年のILSVRC…

The depth of representations is of central importance for many visual recognition tasks. Kaiming He, et al., "Deep Residual Learning for Image Recognition" https://arxiv.org/abs/1512.03385 2015年のILSVRCで1位になったディープラーニングモデ…

We also present analysis on CIFAR-10 with 100 and 1000 layers. Kaiming He, et al., "Deep Residual Learning for Image Recognition" https://arxiv.org/abs/1512.03385 2015年のILSVRCで1位になったディープラーニングモデルであるResNetの論文の"Deep…

This result won the 1st place on the ILSVRC 2015 classification task. Kaiming He, et al., "Deep Residual Learning for Image Recognition" https://arxiv.org/abs/1512.03385 2015年のILSVRCで1位になったディープラーニングモデルであるResNetの論文…

An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. Kaiming He, et al., "Deep Residual Learning for Image Recognition" https://arxiv.org/abs/1512.03385 2015年のILSVRCで1位になったディープラーニングモデルである…

On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets but still having lower complexity. Kaiming He, et al., "Deep Residual Learning for Image Recognition" https://arxiv.org/abs/1512.033…

We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. Kaiming He, et al., "Deep Residual Learning for Image Recognition" https://ar…

Frame of Reference(F.o.R.)とは、英語リーディング教本という本で紹介されている英語構文を考えるための判断枠組みです。 個人的には、文系よりも理系向きの英文読解方法だと思います。 本ブログではFrame of Reference(F.o.R.)の内容自体は説明いたしませ…

We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. Kaiming He, et al., "Deep Residual Learning for Image Recognition" https://arxiv.org/abs/15…

We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. Kaiming He, et al., "Deep Residual Learning for Image Recognition" https://arxiv.org/abs/1512.03385 2015年…

Deeper neural networks are more difficult to train. Kaiming He, et al., "Deep Residual Learning for Image Recognition" https://arxiv.org/abs/1512.03385 2015年のILSVRCで1位になったディープラーニングモデルであるResNetの論文の"Deep Residual L…

We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision. Karen Simonyan, et al., "Very Deep Convolutional Networks for Large-Scale I…

We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. Karen Simonyan, et al., "Very Deep Convolutional Networks for Large-Scale Image Recognition" https://arxiv.org/abs/1409.1…

These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. Karen Simonyan, et al., "Very Deep Convolutional Ne…

Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3 × 3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by…

In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Karen Simonyan, et al., "Very Deep Convolutional Networks for Large-Scale Image Recognition" https://ar…

We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry. Alex Krizhevsky, et al., "ImageNet Classification with Deep …

To reduce overfitting in the fully-connected layers we employed a recently-developed regularization method called “dropout” that proved to be very effective. Alex Krizhevsky, et al., "ImageNet Classification with Deep Convolutional Neural …

To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. Alex Krizhevsky, et al., "ImageNet Classification with Deep Convolutional Neural Networks" https://papers.nips.cc…

The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. Alex Krizhevs…

On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. Alex Krizhevsky, et al., "ImageNet Classification with Deep Convolutional Neural Networks" https:…

We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. Alex Krizhevsky, et al., "ImageNet Classification with Deep Convol…