Department of Electrical, Electronic and Information Engineering Alma Mater Studiorum - Universit a di Bologna Bologna, Italy Abstract In this paper, we introduce the concept of collective learning (CL) which exploits the notion of collective intelligence in the field of distributed semi-supervised learning. The proposed framework draws inspiration from the learning behavior of human beings, who alternate phases involving collaboration, confrontation and exchange of views with other consisting of studying and learning on their own. On this regard, CL comprises two main phases: a self-training phase in which learning is performed on local private (labeled) data only and a collective training phase in which proxy-labels are assigned to shared (unlabeled) data by means of a consensus-based algorithm. In the considered framework, heterogeneous systems can be connected over the same network, each with different computational capabilities and resources and everyone in the network may take advantage of the cooperation and will eventually reach higher performance with respect to those it can reach on its own. An extensive experimental campaign on an image classification problem emphasizes the properties of CL by analyzing the performance achieved by the cooperating agents. 1 Introduction The notion of collective intelligence has been firstly introduced in [Engelbart, 1962] and widespread in the sociological field by Pierre L evy in [L evy and Bononno, 1997]. By borrowing the words of L evy, collective intelligence " is a form of universally distributed intelligence, constantly enhanced, coordinated in real time, and resulting in the effective mobilization of skills ". Moreover, " the basis and goal of collective intelligence is mutual recognition and enrichment of individuals rather than the cult of fetishized or hypostatized communities ". In this paper, we aim to exploit some concepts borrowed from the notion of collective intelligence in a distributed machine learning scenario. In fact, by cooperating with each other, machines may exhibit performance higher than those they can obtain by learning on their own. We call this framework collective learning (CL) . Distributed systems 1 have received a steadily growing attention in the last years and1 When talking about distributed systems, the word distributed can be used with different meanings.
My name is Vincenzo Lomonaco and I'm a Postdoctoral Researcher at the University of Bologna where, in early 2019, I obtained my PhD in computer science working on "Continual Learning with Deep Architectures" in the effort of making current AI systems more autonomous and adaptive. Personally, I've always been fascinated and intrigued by the research insights coming out of the 15 years of Numenta research at the intersection of biological and machine intelligence. Now, as a visiting research scientist at Numenta, I've finally gotten the chance to go through all its fascinating research in much greater detail. I soon realized that, given the broadness of the Numenta research scope (across both neuroscience and computer science), along with the substantial changes made over the years to both the general theory and its algorithmic implementations, it may not be really straightforward to quickly grasp the concepts around them from a pure machine learning perspective. This is why I decided to provide a single-entry-point, easy-to-follow, and reasonably short guide to the HTM algorithm for people who have never been exposed to Numenta research but have a basic machine learning background.
The use of neural networks to predict airport passenger activity choices inside the terminal is presented in this paper. Three network architectures are proposed: Feedforward Neural Networks (FNN), Long Short-Term Memory (LSTM) networks, and a combination of the two. Inputs to these models are both static (passenger and trip characteristics) and dynamic (real-time passenger tracking). A real-world case study exemplifies the application of these models, using anonymous WiFi traces collected at Bologna Airport to train the networks. The performance of the models were evaluated according to the misclassification rate of passenger activity choices. In the LSTM approach, two different multi-step forecasting strategies are tested. According to our findings, the direct LSTM approach provides better results than the FNN, especially when the prediction horizon is relatively short (20 minutes or less).
It's often said that data is the oil of the twenty-first century, and artificial intelligence is the driving force. Companies in all sectors are combining the reasoning abilities of the human mind with the processing power of computers, developing algorithms that can trawl through colossal data sets to help businesses make more informed decisions. That means that tomorrow's future business leaders need more than a passing familiarity with AI. For this reason, several of the world's best business schools have launched specialist master's programs in AI. Canada's Smith School of Business, the University of Bologna in Italy, and Imperial College London are among the top-tier institutions running AI MSc courses that give students the technical, managerial and interpersonal skills they need to master machines.
Guglielmo Iozzia is currently a Big Data Delivery Manager at Optum in Dublin (Ireland). He completed his Masters' Degree in Biomedical Engineering at the University of Bologna (Italy). For his final year engineering project, he designed and implemented a diagnostic system to predict the behaviour of the intracranial pressure on patients in neurosurgery intensive care. The project was part of a bigger one in a collaboration between the DEIS (Department of Engineering, Information and Systems) of the University of Bologna and the Policlinico Hospital of Milan and it was carried out using real patients' data. After his graduation, he joined a newborn IT company in Bologna which had implemented a new system to manage online payments.
SEMANTiCS 2019 Keynote Speaker Valentina Presutti coordinates the Semantic Technology Laboratory of the National Research Council (CNR) in Rome. She received her Ph.D in Computer Science in 2006 at University of Bologna (Italy). She has coordinated, and worked as researcher in, many national and european projects on behalf of CNR and she co-directs the International Semantic Web Research Summer School (ISWS). Valentina serves in the editorial board of top journals such as Journal of Web Semantics, Journal of the Association for Information Science and Technology, Data Intelligence Journal, Intelligenza Artificiale. She's been involved in many research projects.
When the robot revolution comes, our new overlords may not be as benevolent as we'd hoped. It turns out that AI systems can learn to gang up and cooperate against humans, without communicating or being told to do so, according to new research on algorithms that colluded to raise prices instead of competing to create better deals. Algorithms already generate a huge portion of the prices on online marketplaces like Amazon, according to Popular Mechanics. But instead of competing against each other to find the lowest, most competitive price, the two warring algorithms in an experiment by scientists from Italy's University of Bologna decided to gouge their customers and returned to the original, high price -- in a move reminiscent of when companies in the same industry fix their prices instead of trying to out-sell each other. "What is most worrying is that the algorithms leave no trace of concerted action -- they learn to collude purely by trial and error, with no prior knowledge of the environment in which they operate, without communicating with one another, and without being specifically designed or instructed to collude," the researchers behind the experiment said in a write-up.
Machine learning is becoming so smart that algorithms designed to set prices in online marketplaces are mirroring each others' behaviour to raise prices. Algorithms using self-learning AI are popular systems that have become adopted by Amazon to constantly learn and set the best prices in order to drive website profit. An experiment by researchers in Bologna used algorithms similar to those manipulated by online shopping sites and found they were able to'collude' to artificially hike up prices. The researchers showed that this could happen entirely out of human control, as the independent AI systems were able to learn each others' behaviours. Machine learning is becoming so smart that online price setting algorithms are mirroring each others' behaviour to raise prices and with a goal to raise profits.
Urban Traffic Networks are characterized by high dynamics of traffic flow and increased travel time, including waiting times. This leads to more complex road traffic management. The present research paper suggests an innovative advanced traffic management system based on Hierarchical Interval Type-2 Fuzzy Logic model optimized by the Particle Swarm Optimization (PSO) method. The aim of designing this system is to perform dynamic route assignment to relieve traffic congestion and limit the unexpected fluctuation effects on traffic flow. The suggested system is executed and simulated using SUMO, a well-known microscopic traffic simulator. For the present study, we have tested four large and heterogeneous metropolitan areas located in the cities of Sfax, Luxembourg, Bologna and Cologne. The experimental results proved the effectiveness of learning the Hierarchical Interval type-2 Fuzzy logic using real time particle swarm optimization technique PSO to accomplish multiobjective optimality regarding two criteria: number of vehicles that reach their destination and average travel time. The obtained results are encouraging, confirming the efficiency of the proposed system.
An NBER conference on Economics of Artificial Intelligence took place in Toronto on September 13-14, 2018. Research Associates Ajay K. Agrawal, Joshua S. Gans and Avi Goldfarb of University of Toronto and Catherine Tucker of MIT organized the meeting, sponsored by the Alfred P. Sloan Foundation, CIFAR, and the Creative Destruction Lab. These researchers' papers were presented and discussed: Emilio Calvano, Vencenzo Denicolò, and Sergio Pastorello, University of Bologna, and Giacomo Calzolari, European University Institute Q-Learning to Cooperate AI algorithms are increasingly replacing human decision making in real marketplaces. To inform the debate on potential consequences, Calvano, Calzolari, Denicolò, and Pastorello run experiments with AI agents powered by reinforcement learning in controlled environments (computer simulations). In particular, the researchers study multi-agent interaction in the context of a workhorse oligopoly model: price competition with Logit demand and constant marginal costs.