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. 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. 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. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. 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.

/pdf/imagenet-classification-with-deep-convolutional-neural-1190x9a6b9.pdf

ImageNet Classification with Deep Convolutional Neural Networks

In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. 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. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. 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.

Very Deep Convolutional Networks for Large-Scale Image Recognition

The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images and multimedia data. But exactly how such data can be harnessed and organized remains a critical problem. We introduce here a new database called “ImageNet”, a large-scale ontology of images built upon the backbone of the WordNet structure. ImageNet aims to populate the majority of the 80,000 synsets of WordNet with an average of 500-1000 clean and full resolution images. This will result in tens of millions of annotated images organized by the semantic hierarchy of WordNet. This paper offers a detailed analysis of ImageNet in its current state: 12 subtrees with 5247 synsets and 3.2 million images in total. We show that ImageNet is much larger in scale and diversity and much more accurate than the current image datasets. Constructing such a large-scale database is a challenging task. We describe the data collection scheme with Amazon Mechanical Turk. Lastly, we illustrate the usefulness of ImageNet through three simple applications in object recognition, image classification and automatic object clustering. We hope that the scale, accuracy, diversity and hierarchical structure of ImageNet can offer unparalleled opportunities to researchers in the computer vision community and beyond.

/pdf/imagenet-a-large-scale-hierarchical-image-database-1e8f663s1h.pdf

ImageNet: A large-scale hierarchical image database

We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. 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.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

Lie derivable maps at unit operator on nest algebras

A Novel Engine and Battery Coupled Thermal Management Strategy for Connected Hevs Based on Switched Model Predictive Control Under Low Temperature

Nowadays, there is a large number of web services with similar functions, from which users choose the best according to the quality of service (QoS). Hence, QoS prediction is a primary challenge in service recommendation. Most existing approaches model the user-service interaction relationship. However, the low-dimensional linear and the high-dimensional nonlinear relationships between users and services are seldom considered simultaneously. In addition, although location information, including the local location information of users and services, is incorporated to overcome data sparsity in most approaches. The global location information is seldom considered. Aiming at the above shortcomings, we propose a new QoS prediction model that fuses local and global location information of users and services in the interaction layer of the model. The proposed model uses a multilayer perceptron (MLP) to acquire high-dimensional nonlinear relationships of users and services, where the dot product is employed in complementing the learning of low-dimensional linear relationships. Experimental results on the real world dataset WS-Dream validate the prediction performance of the proposed model. 

Location-Aware Web Service QoS Prediction via Deep Collaborative Filtering

Acupuncture can regulate the functions of human body and improve the cognition of brain. However, the mechanism of acupuncture manipulations remains unclear. Here, we hypothesis that the frontal cortex plays a gating role in information routing of brain network under acupuncture. To that end, the gating effect of frontal cortex under acupuncture is analyzed in combination with EEG data of acupuncture at Zusanli acupoints. In addition, recurrent neural network (RNN) is used to reproduce the dynamics of frontal cortex under normal state and acupuncture state. From low-dimensional view, it is shown that the brain networks under acupuncture state can show stable attractor cycle dynamics, which may explain the regulation effect of acupuncture. Comparing with different manipulations, we find that the attractor of low-dimensional trajectory varies under different frequencies of acupuncture. Besides, a strip gated band of neural dynamics is found by changing the frequency of stimulation and excitatory-inhibitory balance of network. This reverse engineering of brain network indicates that the differences among acupuncture manipulations are caused by interaction and separation in the neural activity space between attractors that encode acupuncture function. Consequently, our results may provide help for quantitative analysis of acupuncture, and benefit for the clinical guidance of acupuncture clinicians.

Gating Attractor Dynamics of Frontal Cortex Under Acupuncture via Recurrent Neural Network

This work presents an online adaptive tracking control for a 4-wheel skid-steering mobile robot (SSMR). The objective is to develop an online kinematic model parameter estimation for an equivalent differential drive kinematic model, enabling motion control on the various terrains’ conditions. Combined with an equivalent differential drive kinematic model, the angular velocity of robot motion analyzed by the inertial measurement unit (IMU) sensor is used as the observation quantity, and the steering efficiency parameters in the kinematic model are automatically adjusted by a proportional derivative (PD) controller to improve the desired motion tracking control performance for the robot in the face of different terrains. The execution of tracking control is achieved by the SSMR with torque-adjusted 4-wheel independent velocity control. The proposed strategy is validated experimentally, where the SSMR performs the desired motion tracking in 10 sets with four types of terrains with different levels of flatness. The results demonstrate the high potential in overground navigation settings, due to its fast adaptation and motionfollowing capacity.

Kai Li

Papers

Lie derivable maps at unit operator on nest algebras

A Novel Engine and Battery Coupled Thermal Management Strategy for Connected Hevs Based on Switched Model Predictive Control Under Low Temperature

Location-Aware Web Service QoS Prediction via Deep Collaborative Filtering

Gating Attractor Dynamics of Frontal Cortex Under Acupuncture via Recurrent Neural Network

IMU-based Online Kinematic Model Parameter Estimation for Four-Wheeled Skid-Steering Mobile Robot Desired Motion Tracking on Different Terrains