Image classification is a difficult machine learning task, where Convolutional Neural Networks (CNNs) have been applied for over 20 years in order to solve the problem. In recent years, instead of the traditional way of only connecting the current layer with its next layer, shortcut connections have been proposed to connect the current layer with its forward layers apart from its next layer, which has been proved to be able to facilitate the training process of deep CNNs. However, there are various ways to build the shortcut connections, it is hard to manually design the best shortcut connections when solving a particular problem, especially given the design of the network architecture is already very challenging. In this paper, a hybrid evolutionary computation (EC) method is proposed to \textit{automatically} evolve both the architecture of deep CNNs and the shortcut connections. Three major contributions of this work are: Firstly, a new encoding strategy is proposed to encode a CNN, where the architecture and the shortcut connections are encoded separately; Secondly, a hybrid two-level EC method, which combines particle swarm optimisation and genetic algorithms, is developed to search for the optimal CNNs; Lastly, an adjustable learning rate is introduced for the fitness evaluations, which provides a better learning rate for the training process given a fixed number of epochs. The proposed algorithm is evaluated on three widely used benchmark datasets of image classification and compared with 12 peer Non-EC based competitors and one EC based competitor. The experimental results demonstrate that the proposed method outperforms all of the peer competitors in terms of classification accuracy.

Stochastic partition models divide a multi-dimensional space into a number of rectangular regions, such that the data within each region exhibit certain types of homogeneity. Due to the nature of their partition strategy, existing partition models may create many unnecessary divisions in sparse regions when trying to describe data in dense regions. To avoid this problem we introduce a new parsimonious partition model -- the Rectangular Bounding Process (RBP) -- to efficiently partition multi-dimensional spaces, by employing a bounding strategy to enclose data points within rectangular bounding boxes. Unlike existing approaches, the RBP possesses several attractive theoretical properties that make it a powerful nonparametric partition prior on a hypercube. In particular, the RBP is self-consistent and as such can be directly extended from a finite hypercube to infinite (unbounded) space. We apply the RBP to regression trees and relational models as a flexible partition prior. The experimental results validate the merit of the RBP {in rich yet parsimonious expressiveness} compared to the state-of-the-art methods.

With the rapid growth of the data volume and the fast increasing of the computational model complexity in the scenario of cloud computing, it becomes an important topic that how to handle users' requests by scheduling computational jobs and assigning the resources in data center. In order to have a better perception of the computing jobs and their requests of resources, we analyze its characteristics and focus on the prediction and classification of the computing jobs with some machine learning approaches. Specifically, we apply LSTM neural network to predict the arrival of the jobs and the aggregated requests for computing resources. Then we evaluate it on Google Cluster dataset and it shows that the accuracy has been improved compared to the current existing methods. Additionally, to have a better understanding of the computing jobs, we use an unsupervised hierarchical clustering algorithm, BIRCH, to make classification and get some interpretability of our results in the computing centers.

Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We'll also be posting a weekly calendar of upcoming robotics events for the next few months; here's what we have so far (send us your events!): Let us know if you have suggestions for next week, and enjoy today's videos. Whether free and flexible movements or defined sequences, thanks to its modular design, the pneumatic lightweight robot can be used for numerous applications. In combination with various adaptive grippers, it can pick up and handle a wide variety of objects and shapes.

Facial recognition technology, traditionally both marketed and feared as a way to exponentially enhance surveillance capabilities, may one day become integral for producing pork. According to a report from the New York Times, major Chinese tech companies like Alibaba and JD.com are developing artificial intelligence tools to detect disease and keep track of individual pigs using facial recognition. China hopes the technology will make large farms more manageable, allowing it to consolidate and close smaller facilities. The government claims that the move would cut down on pollution. Pig facial recognition would be invaluable to precision livestock farming, an animal husbandry practice most common in European countries and China that uses tracking technologies to maximize efficiency.

Every sibling relationship has its clichés. In the Microsoft family of social-learning chatbots, the contrasts between Tay, the infamous, sex-crazed neo-Nazi, and her younger sister Zo, your teenage BFF with #friendgoals, are downright Shakespearean. When Microsoft released Tay on Twitter in 2016, an organized trolling effort took advantage of her social-learning abilities and immediately flooded the bot with alt-right slurs and slogans. Tay copied their messages and spewed them back out, forcing Microsoft to take her offline after only 16 hours and apologize. A few months after Tay's disastrous debut, Microsoft quietly released Zo, a second English-language chatbot available on Messenger, Kik, Skype, Twitter, and Groupme.

The new range of Samsung Galaxy S10 smartphones are finally on sale, two weeks after the technology giant unveiled its latest flagship device. Alongside Samsung's standard Galaxy S10 is the entry-level Galaxy S10e and the premium Galaxy S10 – with several UK networks competing to offer the best deal for each. EE, Sky Mobile, BT Mobile and Virgin Mobile have offers ranging from around £30 to £65, depending on the model and contract type. We'll tell you what's true. You can form your own view.

Artificial intelligence has become an essential part of our everyday lives. It is used in financial processes, medical examinations, logistics, publishing, and in a wide range of other fast-rising industries. According to The AI Index 2018 Annual Report by Stanford University, active AI startups in the US increased 2.1x from 2015 to 2018, while venture capital funding for US AI startups increased 4.5x from 2013 to 2017. Today, there are so many AI development companies on the market that it is becoming more and more difficult to choose the one. Based on my experience in IT market research, I've compiled a list of best AI providers.

Not that I'm a big fan of such titles, but when I look at what 5G will bring, it's clear most businesses will feel the impact. Most technologies have a slow adoption curve. This change of speed is going to catch most companies unaware. The technological improvements of better connectivity are apparent, but their consequences aren't. There are two big groups of problems that 5G's lower latency and high bandwidth will impact. On one side, we have those problems that we can solve with low computation and real-time responses. Think of any remote controller. There is minor computation needs on the controller side but needs fast reactions on the remoter actuator.

Tensions between the warring parties have heightened in recent weeks over a stalled United Nations-led peace deal in the port of Hodeidah. The U.N. is trying to arrange a withdrawal of both sides from Hodeidah, the main entry point for most of Yemen's imports.