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

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

We will review some of the major results in random graphs and some of the more challenging open problems. We will cover algorithmic and structural questions. We will touch on newer models, including those related to the WWW.

Random graphs

There are a huge number of features which are said to improve Convolutional Neural Network (CNN) accuracy. Practical testing of combinations of such features on large datasets, and theoretical justification of the result, is required. Some features operate on certain models exclusively and for certain problems exclusively, or only for small-scale datasets; while some features, such as batch-normalization and residual-connections, are applicable to the majority of models, tasks, and datasets. We assume that such universal features include Weighted-Residual-Connections (WRC), Cross-Stage-Partial-connections (CSP), Cross mini-Batch Normalization (CmBN), Self-adversarial-training (SAT) and Mish-activation. We use new features: WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, CmBN, DropBlock regularization, and CIoU loss, and combine some of them to achieve state-of-the-art results: 43.5% AP (65.7% AP50) for the MS COCO dataset at a realtime speed of ~65 FPS on Tesla V100. Source code is at this https URL

YOLOv4: Optimal Speed and Accuracy of Object Detection

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

SFHN: Spatial-Frequency Domain Hybrid Network for Image Super-Resolution

N-heterocyclic carbene Copper complex catalyzed Chan-Evans-Lam reactions of arylboronic acids with azoles and amines

The development of visible light-responsive semiconductor photocatalysts has inspired extensive interest, but its number is very limited for the quantum dots (QDs)-based ones. Herein, an emerging mono-elemental material, violet phosphorus...

Violet Phosphorus Quantum Dots as an Emerging Visible light-responsive Photocatalyst for Efficient Hydrogen Evolution Reaction

Blue Luminescence of Lead-Free Cs2cucl4 Glass Ceramics with Long-Term Water-Resistance Stability

The solar-assisted electric boiler water heating systems adopted in student apartments at universities have some shortcomings, such as unsuitable system designs, unstable water supply temperature, and excessive power consumption. As discussed in this paper, the hot water supply system was reformed, and two apartments with the same building area, same solar collector area, and similar water consumption were selected to be used in comparative experiments. The auxiliary heat source for one of the apartments was changed from an electric boiler to three air source heat pumps, and a constant temperature water tank was added to form a double-tank water supply system. In addition, the operation strategy was adjusted. The other apartment was not modified. The energy consumption, solar fraction, water supply quality and economy of the two systems were analyzed and compared. The results showed that the transformation plan is reasonable and feasible. The solar fraction of the reformed system was significantly improved. The water supply temperature of the original system ranged from 35 °C to 60 °C, but it was shown to stabilize between 40 °C and 50 °C after the transformation. The average power saving rate of the reformed system reached 72.70%, and this economic benefit is highly significant. Additionally, the TRNSYS simulation software was used to model and optimize the control of the system.

/pdf/study-on-the-energy-efficiency-improvement-and-operation-2p94mm3f.pdf

Chang Xu

Papers

SFHN: Spatial-Frequency Domain Hybrid Network for Image Super-Resolution

N-heterocyclic carbene Copper complex catalyzed Chan-Evans-Lam reactions of arylboronic acids with azoles and amines

Violet Phosphorus Quantum Dots as an Emerging Visible light-responsive Photocatalyst for Efficient Hydrogen Evolution Reaction

Blue Luminescence of Lead-Free Cs2cucl4 Glass Ceramics with Long-Term Water-Resistance Stability

Study on the Energy Efficiency Improvement and Operation Optimization of a Solar Water Heating System