Filip De Turck

Bio: Filip De Turck is an academic researcher from Ghent University. The author has contributed to research in topics: Cloud computing & Scalability. The author has an hindex of 42, co-authored 588 publications receiving 10495 citations.

Network Function Virtualization: State-of-the-Art and Research Challenges

Abstract: Network function virtualization (NFV) has drawn significant attention from both industry and academia as an important shift in telecommunication service provisioning. By decoupling network functions (NFs) from the physical devices on which they run, NFV has the potential to lead to significant reductions in operating expenses (OPEX) and capital expenses (CAPEX) and facilitate the deployment of new services with increased agility and faster time-to-value. The NFV paradigm is still in its infancy and there is a large spectrum of opportunities for the research community to develop new architectures, systems and applications, and to evaluate alternatives and trade-offs in developing technologies for its successful deployment. In this paper, after discussing NFV and its relationship with complementary fields of software defined networking (SDN) and cloud computing, we survey the state-of-the-art in NFV, and identify promising research directions in this area. We also overview key NFV projects, standardization efforts, early implementations, use cases, and commercial products.

VNF-P: A model for efficient placement of virtualized network functions

Abstract: Network Functions Virtualization (NFV) is an upcoming paradigm where network functionality is virtualized and split up into multiple building blocks that can be chained together to provide the required functionality. This approach increases network flexibility and scalability as these building blocks can be allocated and reallocated at runtime depending on demand. The success of this approach depends on the existence and performance of algorithms that determine where, and how these building blocks are instantiated. In this paper, we present and evaluate a formal model for resource allocation of virtualized network functions within NFV environments, a problem we refer to as Virtual Network Function Placement (VNF-P). We focus on a hybrid scenario where part of the services may be provided by dedicated physical hardware, and where part of the services are provided using virtualized service instances. We evaluate the VNF-P model using a small service provider scenario and two types of service chains, and evaluate its execution speed. We find that the algorithms finish in 16 seconds or less for a small service provider scenario, making it feasible to react quickly to changing demand.

VIME: Variational Information Maximizing Exploration

Abstract: Scalable and effective exploration remains a key challenge in reinforcement learning (RL). While there are methods with optimality guarantees in the setting of discrete state and action spaces, these methods cannot be applied in high-dimensional deep RL scenarios. As such, most contemporary RL relies on simple heuristics such as epsilon-greedy exploration or adding Gaussian noise to the controls. This paper introduces Variational Information Maximizing Exploration (VIME), an exploration strategy based on maximization of information gain about the agent's belief of environment dynamics. We propose a practical implementation, using variational inference in Bayesian neural networks which efficiently handles continuous state and action spaces. VIME modifies the MDP reward function, and can be applied with several different underlying RL algorithms. We demonstrate that VIME achieves significantly better performance compared to heuristic exploration methods across a variety of continuous control tasks and algorithms, including tasks with very sparse rewards.

#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning

Abstract: Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov decision processes (MDPs). It is generally thought that count-based methods cannot be applied in high-dimensional state spaces, since most states will only occur once. Recent deep RL exploration strategies are able to deal with high-dimensional continuous state spaces through complex heuristics, often relying on optimism in the face of uncertainty or intrinsic motivation. In this work, we describe a surprising finding: a simple generalization of the classic count-based approach can reach near state-of-the-art performance on various high-dimensional and/or continuous deep RL benchmarks. States are mapped to hash codes, which allows to count their occurrences with a hash table. These counts are then used to compute a reward bonus according to the classic count-based exploration theory. We find that simple hash functions can achieve surprisingly good results on many challenging tasks. Furthermore, we show that a domain-dependent learned hash code may further improve these results. Detailed analysis reveals important aspects of a good hash function: 1) having appropriate granularity and 2) encoding information relevant to solving the MDP. This exploration strategy achieves near state-of-the-art performance on both continuous control tasks and Atari 2600 games, hence providing a simple yet powerful baseline for solving MDPs that require considerable exploration.

Cloudlets: bringing the cloud to the mobile user

Abstract: Although mobile devices are gaining more and more capabilities (i.e. CPU power, memory, connectivity, ...), they still fall short to execute complex rich media and data analysis applications. Offloading to the cloud is not always a solution, because of the high WAN latencies, especially for applications with real-time constraints such as augmented reality. Therefore the cloud has to be moved closer to the mobile user in the form of cloudlets. Instead of moving a complete virtual machine from the cloud to the cloudlet, we propose a more fine grained cloudlet concept that manages applications on a component level. Cloudlets do not have to be fixed infrastructure close to the wireless access point, but can be formed in a dynamic way with any device in the LAN network with available resources. We present a cloudlet architecture together with a prototype implementation, showing the advantages and capabilities for a mobile real-time augmented reality application.

Machine learning

Abstract: Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Acute Kidney Injury Network: report of an initiative to improve outcomes in acute kidney injury

Abstract: Acute kidney injury (AKI) is a complex disorder for which currently there is no accepted definition. Having a uniform standard for diagnosing and classifying AKI would enhance our ability to manage these patients. Future clinical and translational research in AKI will require collaborative networks of investigators drawn from various disciplines, dissemination of information via multidisciplinary joint conferences and publications, and improved translation of knowledge from pre-clinical research. We describe an initiative to develop uniform standards for defining and classifying AKI and to establish a forum for multidisciplinary interaction to improve care for patients with or at risk for AKI. Members representing key societies in critical care and nephrology along with additional experts in adult and pediatric AKI participated in a two day conference in Amsterdam, The Netherlands, in September 2005 and were assigned to one of three workgroups. Each group's discussions formed the basis for draft recommendations that were later refined and improved during discussion with the larger group. Dissenting opinions were also noted. The final draft recommendations were circulated to all participants and subsequently agreed upon as the consensus recommendations for this report. Participating societies endorsed the recommendations and agreed to help disseminate the results. The term AKI is proposed to represent the entire spectrum of acute renal failure. Diagnostic criteria for AKI are proposed based on acute alterations in serum creatinine or urine output. A staging system for AKI which reflects quantitative changes in serum creatinine and urine output has been developed. We describe the formation of a multidisciplinary collaborative network focused on AKI. We have proposed uniform standards for diagnosing and classifying AKI which will need to be validated in future studies. The Acute Kidney Injury Network offers a mechanism for proceeding with efforts to improve patient outcomes.

The European commission

Abstract: 2 1 The innovative transport systems and the CityMobil project 10 1.1 The research questions 10 2 The state of art in the field of automatic transport systems 12 2.1 Case studies and demand studies for innovative transport systems 12 3 The design and implementation of surveys 14 3.1 Definition of experimental design 14 3.2 Questionnaire design and delivery 16 3.3 First analyses on the collected sample 18 4 Calibration of Logit Multionomial demand models 21 4.1 Methodology 21 4.2 Calibration of the “full” model. 22 4.3 Calibration of the “final” model 24 4.4 The demand analysis through the final Multinomial Logit model 25 5 The analysis of interaction between the demand and socioeconomic attributes 31 5.1 Methodology 31 5.2 Application of Mixed Logit models to the demand 31 5.3 Analysis of the interactions between demand and socioeconomic attributes through Mixed Logit models 32 5.4 Mixed Logit model and interaction between age and the demand for the CTS 38 5.5 Demand analysis with Mixed Logit model 39 6 Final analyses and conclusions 45 6.1 Comparison between the results of the analyses 45 6.2 Conclusions 48 6.3 Answers to the research questions and future developments 52