Abstract-- It is well recognized that the project productivity is a key driver in estimating software project effort from Use Case Point size metric at early software development stages. Although, there are few proposed models for predicting productivity, there is no consistent conclusion regarding which model is the superior. Therefore, instead of building a new productivity prediction model, this paper presents a new ensemble construction mechanism applied for software project productivity prediction. Ensemble is an effective technique when performance of base models is poor. We proposed a weighted mean method to aggregate predicted productivities based on average of errors produced by training model. The obtained results show that the using ensemble is a good alternative approach when accuracies of base models are not consistently accurate over different datasets, and when models behave diversely.

Recently, deep neural networks (DNNs) have been widely applied in mobile intelligent applications. The inference for the DNNs is usually performed in the cloud. However, it leads to a large overhead of transmitting data via wireless network. In this paper, we demonstrate the advantages of the cloud-edge collaborative inference with quantization. By analyzing the characteristics of layers in DNNs, an auto-tuning neural network quantization framework for collaborative inference is proposed. We study the effectiveness of mixed-precision collaborative inference of state-of-the-art DNNs by using ImageNet dataset. The experimental results show that our framework can generate reasonable network partitions and reduce the storage on mobile devices with trivial loss of accuracy.

Knowledge Graph (KG) embedding is a fundamental problem in data mining research with many real-world applications. It aims to encode the entities and relations in the graph into low dimensional vector space, which can be used for subsequent algorithms. Negative sampling, which samples negative triplets from non-observed ones in the training data, is an important step in KG embedding. Recently, generative adversarial network (GAN), has been introduced in negative sampling. By sampling negative triplets with large scores, these methods avoid the problem of vanishing gradient and thus obtain better performance. However, using GAN makes the original model more complex and hard to train, where reinforcement learning must be used. In this paper, motivated by the observation that negative triplets with large scores are important but rare, we propose to directly keep track of them with the cache. However, how to sample from and update the cache are two important questions. We carefully design the solutions, which are not only efficient but also achieve a good balance between exploration and exploitation. In this way, our method acts as a "distilled" version of previous GA-based methods, which does not waste training time on additional parameters to fit the full distribution of negative triplets. The extensive experiments show that our method can gain significant improvement in various KG embedding models, and outperform the state-of-the-art negative sampling methods based on GAN.

Apple has found a way to circumvent a Chinese court ban preventing it from selling iPhones in the country, the firm said. US chip maker Qualcomm claims Apple violated two of its patents, which resulted in two preliminary injunctions in China earlier this week that force Apple to stop selling a wide range of iPhones there. The ban accounts for almost every smartphone Apple has made in the last three years, including the iPhone 6s, iPhone 6s Plus, iPhone 7, iPhone 7 Plus, iPhone 8, iPhone 8 Plus and iPhone X. In order to get around the ban, Apple said in a statement it would carry out software updates next week that will "address any possible concern" about the company's compliance with the order. The alleged intellectual property infringement relates to features allowing iPhone users to adjust pictures and manage applications.

ULTI-task learning[3], [23] is a subfield of machine learning, particularly transfer learning [17], [22], [24], [25], which uses auxiliary data or knowledge from related/similar tasks to facilitate the learning in a new task. As a result, a learning model for the new task can be built with much less task-specific training data. Or, in other words, with the same amount of task-specific data, a much better model could be trained. In multi-task learning, multiple related learning tasks are performed simultaneously using a (partially) shared model representation. As a result, the common information contained in these related tasks can be exploited to improve the learning efficiency and generalization performance of each task-specific model. Multi-task optimization (MTO) [6], [12], [16], [19] applies multi-task learning to optimization to study how to effectively and efficiently tackle multiple optimization problems simultaneously. Evolutionarymulti-tasking [16], or multifactorial optimization (MFO)[12], is an emerging subfield of MTO, which integrates evolutionary computation and multi-task learning.

Activation functions are essential for deep learning methods to learn and perform complex tasks such as image classification. Rectified Linear Unit (ReLU) has been widely used and become the default activation function across the deep learning community since 2012. Although ReLU has been popular, however, the hard zero property of the ReLU has heavily hindered the negative values from propagating through the network. Consequently, the deep neural network has not been benefited from the negative representations. In this work, an activation function called Flatten-T Swish (FTS) that leverage the benefit of the negative values is proposed. To verify its performance, this study evaluates FTS with ReLU and several recent activation functions. Each activation function is trained using MNIST dataset on five different deep fully connected neural networks (DFNNs) with depth vary from five to eight layers. For a fair evaluation, all DFNNs are using the same configuration settings. Based on the experimental results, FTS with a threshold value, T=-0.20 has the best overall performance. As compared with ReLU, FTS (T=-0.20) improves MNIST classification accuracy by 0.13%, 0.70%, 0.67%, 1.07% and 1.15% on wider 5 layers, slimmer 5 layers, 6 layers, 7 layers and 8 layers DFNNs respectively. Apart from this, the study also noticed that FTS converges twice as fast as ReLU. Although there are other existing activation functions are also evaluated, this study elects ReLU as the baseline activation function.

This paper proposes a push and pull search method in the framework of differential evolution (PPS-DE) to solve constrained single-objective optimization problems (CSOPs). More specifically, two sub-populations, including the top and bottom sub-populations, are collaborated with each other to search global optimal solutions efficiently. The top sub-population adopts the pull and pull search (PPS) mechanism to deal with constraints, while the bottom sub-population use the superiority of feasible solutions (SF) technique to deal with constraints. In the top sub-population, the search process is divided into two different stages --- push and pull stages.An adaptive DE variant with three trial vector generation strategies is employed in the proposed PPS-DE. In the top sub-population, all the three trial vector generation strategies are used to generate offsprings, just like in CoDE. In the bottom sub-population, a strategy adaptation, in which the trial vector generation strategies are periodically self-adapted by learning from their experiences in generating promising solutions in the top sub-population, is used to choose a suitable trial vector generation strategy to generate one offspring. Furthermore, a parameter adaptation strategy from LSHADE44 is employed in both sup-populations to generate scale factor $F$ and crossover rate $CR$ for each trial vector generation strategy. Twenty-eight CSOPs with 10-, 30-, and 50-dimensional decision variables provided in the CEC2018 competition on real parameter single objective optimization are optimized by the proposed PPS-DE. The experimental results demonstrate that the proposed PPS-DE has the best performance compared with the other seven state-of-the-art algorithms, including AGA-PPS, LSHADE44, LSHADE44+IDE, UDE, IUDE, $\epsilon$MAg-ES and C$^2$oDE.

Chinese tech giant Tencent's first attempt in AI healthcare was the Miying platform, which has been a point of pride for CEO Huateng Ma since its 2017 launch. Supported by AI-powered medical imaging technologies, Miying assists doctors with the screening of esophageal cancer, pulmonary nodules, cervical cancer, etc. The platform has been well received in the AI and medical communities, with a fast-expanding market in Chinese top-tier AAA hospitals. At the recent International Congress of Parkinson's Disease and Movement Disorders in Hong Kong, Tencent unveiled its second layout in AI healthcare: Medical AI Lab. The lab team includes experts in machine learning, computational vision, video analytics, augmented reality (AR), natural language understanding (NLU), etc. Tencent Medical AI Lab is the latest in the company's continuing efforts on AI to Business marketing.

China has several advantages when it comes to the artificial intelligence field, but chief among them is Chinese companies' access to troves of data. "(China has) done a fantastic job of moving its economy to cashless and when you can pay with everything with your phone, you amass a huge amount of data," author and columnist Thomas Friedman told CNBC. "When you can get these giant data sets, and then apply artificial intelligence to them," he said. "You're going to see better and better and more deep insight patterns than anyone else and I think it'll be a great advantage for China." On top of that, China doesn't have the same restrictive privacy laws as many other countries, making it easier for companies to collect data.

The popular narrative around artificial intelligence research is that it's mainly a war between China and the United States. Not so fast, says Europe. New data released today (Dec. The data was assembled from Scopus, a citation database owned by scientific publishing company Elsevier. If the current trend continues, China will soon overtake Europe in the number of papers published.