The recent advances in single-cell technologies have enabled us to profile genomic features at unprecedented resolution and data sets from multiple domains are available, including data sets that profile different types of genomic features and data sets that profile the same type of genomic features across different species. These data sets typically have different powers in identifying the unknown cell types through clustering, and data integration can potentially lead to a better performance of clustering algorithms. In this work, we formulate the problem in an unsupervised transfer learning framework, which utilizes knowledge learned from auxiliary data set to improve the clustering performance of target data set. The degree of shared information among the target and auxiliary data sets can vary, and their distributions can also be different. To address these challenges, we propose an elastic coupled co-clustering based transfer learning algorithm, by elastically propagating clustering knowledge obtained from the auxiliary data set to the target data set. Implementation on single-cell genomic data sets shows that our algorithm greatly improves clustering performance over the traditional learning algorithms. The source code and data sets are available at https://github.com/cuhklinlab/elasticC3.

This paper considers the problem of multi-agent distributed optimization. In this problem, there are multiple agents in the system, and each agent only knows its local cost function. The objective for the agents is to collectively compute a common minimum of the aggregate of all their local cost functions. In principle, this problem is solvable using a distributed variant of the traditional gradient-descent method, which is an iterative method. However, the speed of convergence of the traditional gradient-descent method is highly influenced by the conditioning of the optimization problem being solved. Specifically, the method requires a large number of iterations to converge to a solution if the optimization problem is ill-conditioned. In this paper, we propose an iterative pre-conditioning approach that can significantly attenuate the influence of the problem's conditioning on the convergence-speed of the gradient-descent method. The proposed pre-conditioning approach can be easily implemented in distributed systems and has minimal computation and communication overhead. For now, we only consider a specific distributed optimization problem wherein the individual local cost functions of the agents are quadratic. Besides the theoretical guarantees, the improved convergence speed of our approach is demonstrated through experiments on a real data-set.

As traffic congestion continues growing in urban areas, more and more cities have realized that investment priority should be given to public transport modes, such as bus transit systems (BRT) instead of personal vehicles. Simply put, in congested cities, public transport modes are more efficient than personal vehicles in terms of carrying and moving people around. As city populations grow and as their economic bases shift and evolve, their housing sector adjusts, even more vehicles are expected to enter the roads each day, creating more traffic congestion. The 2012 Urban Mobility Report states that, the lack of public transportation services would have cost commuters an additional 865 million hours of delay. With growing urban population numbers, this number undoubtedly stands higher today (National Express). On average, expanding and optimizing transit services produced an economic benefit of roughly $45 million a year by connecting urban areas in the US. There is no doubt that expanding public transportation use is key to reducing traffic congestion.

This paper addresses a lot-sizing and scheduling problem variant arising from the study of the curing process of a tire factory. The aim is to find the minimum makespan needed for producing enough tires to meet the demand requirements on time, considering the availability and compatibility of different resources involved. To solve this problem, we suggest a hybrid approach that consists in first applying a heuristic to obtain an estimated value of the makespan and then solving a mathematical model to determine the minimum value. We note that the size of the model (number of variables and constraints) depends significantly on the estimated makespan. Extensive numerical experiments over different instances based on real data are presented to evaluate the effectiveness of the hybrid procedure proposed. From the results obtained we can note that the hybrid approach is able to achieve the optimal makespan for many of the instances, even large ones, since the results provided by the heuristic allow to reduce significantly the size of the mathematical model.

Commonsense reasoning has long been considered as one of the holy grails of artificial intelligence. Most of the recent progress in the field has been achieved by novel machine learning algorithms for natural language processing. However, without incorporating logical reasoning, these algorithms remain arguably shallow. With some notable exceptions, developers of practical automated logic-based reasoners have mostly avoided focusing on the problem. The paper argues that the methods and algorithms used by existing automated reasoners for classical first-order logic can be extended towards commonsense reasoning. Instead of devising new specialized logics we propose a framework of extensions to the mainstream resolution-based search methods to make these capable of performing search tasks for practical commonsense reasoning with reasonable efficiency. The proposed extensions mostly rely on operating on ordinary proof trees and are devised to handle commonsense knowledge bases containing inconsistencies, default rules, taxonomies, topics, relevance, confidence and similarity measures. We claim that machine learning is best suited for the construction of commonsense knowledge bases while the extended logic-based methods would be well-suited for actually answering queries from these knowledge bases.

Multi-agent reinforcement learning is a standard framework for modeling multi-agent interactions applied in real-world scenarios. Inspired by experience sharing in human groups, learning knowledge parallel reusing between agents can potentially promote team learning performance, especially in multi-task environments. When all agents interact with the environment and learn simultaneously, how each independent agent selectively learns from other agents' behavior knowledge is a problem that we need to solve. This paper proposes a novel knowledge transfer framework in MARL, PAT (Parallel Attentional Transfer). We design two acting modes in PAT, student mode and self-learning mode. Each agent in our approach trains a decentralized student actor-critic to determine its acting mode at each time step. When agents are unfamiliar with the environment, the shared attention mechanism in student mode effectively selects learning knowledge from other agents to decide agents' actions. PAT outperforms state-of-the-art empirical evaluation results against the prior advising approaches. Our approach not only significantly improves team learning rate and global performance, but also is flexible and transferable to be applied in various multi-agent systems.

With widespread applications of artificial intelligence (AI), the capabilities of the perception, understanding, decision-making and control for autonomous systems have improved significantly in the past years. When autonomous systems consider the performance of accuracy and transferability simultaneously, several AI methods, like adversarial learning, reinforcement learning (RL) and meta-learning, show their powerful performance. Here, we review the learning-based approaches in autonomous systems from the perspectives of accuracy and transferability. Accuracy means that a well-trained model shows good results during the testing phase, in which the testing set shares a same task or a data distribution with the training set. Transferability means that when an trained model is transferred to other testing domains, the accuracy is still good. Firstly, we introduce some basic concepts of transfer learning and then present some preliminaries of adversarial learning, RL and meta-learning. Secondly, we focus on reviewing the accuracy and transferability to show the advantages of adversarial learning, like generative adversarial networks (GANs), in typical computer vision tasks in autonomous systems, including image style transfer, image super-resolution, image deblurring/dehazing/rain removal, semantic segmentation, depth estimation and person re-identification. Then, we further review the performance of RL and meta-learning from the aspects of accuracy and transferability in autonomous systems, involving robot navigation and robotic manipulation. Finally, we discuss several challenges and future topics for using adversarial learning, RL and meta-learning in autonomous systems.

Knowledge Graphs (KG) are a rich source of structured knowledge that can be leveraged to solve important AI tasks such as question answering [3], relation extraction [25], recommender systems [30]. Consequently, the past decade has witnessed the development of large-scale knowledge graphs like Freebase[1], Wordnet[13], Yago[20], DBpedia[9], NELL[4] that store billions of facts about the world. Typically, a knowledge graph stores knowledge in the form of triples (h, r, t) where r is the relation between entity h and t. Even though knowledge graphs are extremely large and are growing with each day, they are still incomplete with important links missing between entities. This problem of predicting missing links between known entities is known as Knowledge Graph Completion (KBC).

With more board configurations than there are atoms in the universe, the ancient Chinese game of Go has long been considered a grand challenge for artificial intelligence. On March 9, 2016, the worlds of Go and artificial intelligence collided in South Korea for an extraordinary best-of-five-game competition, coined The DeepMind Challenge Match. Hundreds of millions of people around the world watched as a legendary Go master took on an unproven AI challenger for the first time in history. Directed by Greg Kohs with an original score by Academy Award nominee, Hauschka, AlphaGo chronicles a journey from the halls of Oxford, through the backstreets of Bordeaux, past the coding terminals of DeepMind in London, and ultimately, to the seven-day tournament in Seoul. As the drama unfolds, more questions emerge: What can artificial intelligence reveal about a 3000-year-old game?

IPVM also points out that it's unusual for a surveillance tech company to be selling high-end thermal cameras and software via an e-commerce site with a "shopping cart," which Athena continues to do. Athena CEO Lisa Falzone told Fast Company they took that approach so that customers wouldn't have to wait for weeks to get the technology. IPVM demonstrated that the price of Athena's "Coronavirus Detection System" shown on the website has risen from $3,900 as of March 17 to $8,900 on March 23. Athena CTO Chris Ciabarra says the price of the software-hardware solution can fluctuate with the prices and availability of the thermal cameras used. With the U.S. lagging other countries in the distribution of coronavirus testing kits, health authorities have had to look to other means of detection, like the infrared ear thermometers used in some countries.