Goto

Collaborating Authors

ASCENT Village International Mining and Resources Conference

#artificialintelligence

ARE YOU A TECH STARTUP OR SCALE UP LOOKING TO COMMERCIALISE? Raise your profile in the global mining sector by putting your innovations in front of 7000 attendees including leading tech investors and some of the most influential people in Mining Tech. IMARC are offering 20 startups or scaleups the opportunity to raise their profile with global mining leaders within the ASCENT Village. If you are chosen for ASCENT the Investment is $1,000 AUD GST. You will be notified by email if your application has been successful.


A Network-Specific Markov Random Field Approach to Community Detection

AAAI Conferences

Markov Random Field (MRF) is a powerful framework for developing probabilistic models of complex problems. MRF models possess rich structures to represent properties and constraints of a problem. It has been successful on many application problems, particularly those of computer vision and image processing, where data are structured, e.g., pixels are organized on grids. The problem of identifying communities in networks, which is essential for network analysis, is in principle analogous to finding objects in images. It is surprising that MRF has not yet been explored for network community detection. It is challenging to apply MRF to network analysis problems where data are organized on graphs with irregular structures. Here we present a network-specific MRF approach to community detection. The new method effectively encodes the structural properties of an irregular network in an energy function (the core of an MRF model) so that the minimization of the function gives rise to the best community structures. We analyzed the new MRF-based method on several synthetic benchmarks and real-world networks, showing its superior performance over the state-of-the-art methods for community identification.


On the Value of Bandit Feedback for Offline Recommender System Evaluation

arXiv.org Machine Learning

In academic literature, recommender systems are often evaluated on the task of next-item prediction. The procedure aims to give an answer to the question: "Given the natural sequence of user-item interactions up to time t, can we predict which item the user will interact with at time t+1?". Evaluation results obtained through said methodology are then used as a proxy to predict which system will perform better in an online setting. The online setting, however, poses a subtly different question: "Given the natural sequence of user-item interactions up to time t, can we get the user to interact with a recommended item at time t+1?". From a causal perspective, the system performs an intervention, and we want to measure its effect. Next-item prediction is often used as a fall-back objective when information about interventions and their effects (shown recommendations and whether they received a click) is unavailable. When this type of data is available, however, it can provide great value for reliably estimating online recommender system performance. Through a series of simulated experiments with the RecoGym environment, we show where traditional offline evaluation schemes fall short. Additionally, we show how so-called bandit feedback can be exploited for effective offline evaluation that more accurately reflects online performance.


8th Edition of International Conference on Big Data & Data Science

#artificialintelligence

The EuroSciCon is glad to announce the "8th Edition of International Conference on Big Data & Data Science" to be held during October 04-05, 2018 at London, UK. The Big Data conference focuses on the topics Big Data Analytics, Big Data Algorithms, Big data in Bioinformatics, Data Mining with Big Data, Visualization in Big data, Big data in Neural Network for Deep Learning, High Performance Computing for Big data, Machine Learning in Data Science, Open science in Big data, Hadoop map reduce for analyzing information, regression in Data Science and Big data applications. Theme: Exploring Future Technologies for Data Mining & Analysis By bringing together interdisciplinary researchers working in a variety of application areas this Big Data 2018 would lay a platform for all the Academicians, eminent Researchers, Young and enthusiastic developers in computer science, Data Analysts and Industrial Members to interact and intend their advanced and upcoming new advancements in the field of Modern computer technology & data mining with global eminent researchers and accelerate progress in this area.


DF-SLAM: A Deep-Learning Enhanced Visual SLAM System based on Deep Local Features

arXiv.org Artificial Intelligence

As the foundation of driverless vehicle and intelligent robots, Simultaneous Localization and Mapping(SLAM) has attracted much attention these days. However, non-geometric modules of traditional SLAM algorithms are limited by data association tasks and have become a bottleneck preventing the development of SLAM. To deal with such problems, many researchers seek to Deep Learning for help. But most of these studies are limited to virtual datasets or specific environments, and even sacrifice efficiency for accuracy. Thus, they are not practical enough. We propose DF-SLAM system that uses deep local feature descriptors obtained by the neural network as a substitute for traditional hand-made features. Experimental results demonstrate its improvements in efficiency and stability. DF-SLAM outperforms popular traditional SLAM systems in various scenes, including challenging scenes with intense illumination changes. Its versatility and mobility fit well into the need for exploring new environments. Since we adopt a shallow network to extract local descriptors and remain others the same as original SLAM systems, our DF-SLAM can still run in real-time on GPU.