Exploring new frontiers
2019年4月9-11日 法国,巴黎,Marriott Conference Center

Thursday 11 April Morning AI NET Day TWO Track 3

    Conference Room Auditorium Level -1

  • Registration and welcome coffee from 07.30
  • Start of the Conference 08.30
  • Exhibition open from 08.00 to 19.30
  • Seated Lunch: 12.30
  • End of Conference: 16.30

Tuesday 09 April 2019

AI Net Tutorial
Auditorium Level -1

Thursday 11 April 2019

AI net Conference
Auditorium Level -1


AI net Conference

Auditorium Level -1

Jean-Marc Uze,
Network Data Scientist, AIforNet
09.00 Use Cases Session Part 2
Discussing Acumos Benefits
Frameworks like Acumos can be used to speed up the deployment of AI models.
Recalling all the problematics that Data Scientist are facing to create or update AI models.
Presenting Acumos and their benefits.

Philippe Dooze, Data Analyst, Orange Labs

Philippe Dooze is graduated from Lille 1 University and holds a Master's degree in telecommunication. He started working at Orange in 1999 as a project manager on measurement tools of mobile access network for 3 years in Paris. Afterwards, he worked in the French mobile monitoring center during 8 years as the responsible of quality performance and mobile monitoring tools in Lyon.   He joined Orange Labs, the Research and Development department of Orange, in Lannion, France, in 2010 as a research engineer. His research interests include mobile VoIP architecture, QoS prediction, Big Data and Machine Learning.   Since April 2018 he is fully involved as a project leader in a Linux Foundation Deep Learning project called Acumos"

AI in Networks Today: Pragmatic Use Cases
Resolving performance issues with insights from past and present behaviours.
Preemptive protection, acting before it is too late.
Multi-layer optimization, combining predictive analytics with the power of what-if simulations.
Predictive RAN x-haul, boosting the quality of experience for mobile users.

Niloufar Tayebi, Director, Global Consulting Enterprise & Cloud Services, Ciena

Niloufar Tayebi is Director, Global Consulting Enterprise and Cloud Services, at Ciena. She specializes in managed services and is adept in services strategies, enterprise and wholesale market analysis and business case modeling.   Niloufar has more than 20 years of experience in the telecommunications starting her career as a network architecture, has held leading roles in 4G wireless networking and carrier core product marketing and planning.   In her role in Ciena she is responsible as a global consultant for helping service providers to create new services and drive new business models leveraging Software Defined Networking (SDN) and Network Function Virtualization (NFV) with Ciena's Blue Planet network virtualization, orchestration, and management software.   Niloufar holds a Master's degree in Electrical Engineering from University of Ottawa, Canada. She lives in Ottawa, Ontario.

Exploring New Ways to Monitor France‑IX Network

Simon Muyal, CTO, France‑IX
Coffee Break / Exhibition / Interop Event
11.00 Machine Learning Session
Applying Machine Learning to Networks: Challenges & New Paradigms
Giving an overview of ML innovation, that has been developed using production data from some of the largest networks in the world, and how these solutions help automate operational intent.

Rahul Aggarwal, Founder & CEO, Augtera Networks
Applying AI to Encrypted Traffic Classification
Describing a method using AI to analyze some of the visible extracted features and detect patterns generated by specific applications, enabling us to identify key applications using encrypted traffic as input.

Nir Halachmi, Network Research Product Management, Huawei

Nir Halachmi is leading Network Research Product Management at Huawei European Research Center (ERC).   Nir is a subject matter expert for innovative 5G, SDN and NFV solutions, carriers and cloud technologies as well as Service Providers enterprise services and mobile backhaul (LTE 5G and small cells).   In his current role, Nir is focusing on innovation around SDN, NFV and 5G specifically focusing on 5G transport network slicing, Network Analytics and Next Generation Video / AR / VR.   Nir is also part of the OPNFV Marketing committee, as part of Huawei's commitment to open source.   Nir had spent the past 18 years developing and managing telecommunications products within both the wired and the wireless industries, and has worked across various technologies including Carrier Ethernet, Circuit Emulation, MPLS, IP Networking, Wi-Fi and WiMAX, Cloud and Edge Computing, SDN and NFV.   Nir holds a Master's Degree in Computer Science from the Inter-Disciplinary Center (IDC) in Israel.

Machine-Learning driven Network Planning & Operations
Walking through the emerging use of machine-learning techniques in network planning and day-to-day operations.

Benoit Lourdelet, Product Management Director, Extreme Networks
Seated Lunch
Thursday 11 April Afternoon AI NET Day TWO Track 3

    Conference Room Auditorium Level -1

  • Exhibition open from 08.00 to 19.30
  • End of Conference: 16.30

14.00 Deep Learning Session
Model-Driven Artificial Intelligence for Online Network Optimization
Proposing the framework of Online Network Optimization (ONO), which seeks to maintain both agile and efficient control over time, using an arsenal of data-driven, adaptive, and AI-based techniques.

Merouane Debbah, Director of the Mathematical and Algorithmic Sciences Lab, Huawei
Avoiding Over-Fitting Problem in Applying Artificial Neural Network to Intrusion Detection System
Anomaly-based IDS (Intrusion Detection System) monitors activities of computer and network systems and classifies them as either normal or anomalous based on heuristics or rules. Artificial neural network can be employed for anomaly-based IDS.

Kohei Shiomoto, Professor, Tokyo City University

Kohei Shiomoto is a Professor, Tokyo City University, where he is engaged in Research and Education in Network Management for the Internet, Mobile, and Cloud. Before joining Tokyo City University as Full Professor, he spent 28 years in NTT laboratories and was engaged in advanced research on SDN/NFV and Network Analytics, Communication Traffic & Service Quality, Traffic Engineering, IP and Optical Networking, (network architecture, IETF standardization, multi-layer traffic engineering), architecture design for high-speed IP/MPLS label switching router, IP router design, routing algorithm, and IETF GMPLS standardization, development of commercial ATM switching systems, research of high-speed networking technologies including ATM traffic control, measurement-based admission control, and ATM switch design.   From 1996 to 1997, he was on leave from NTT to join Department of Computer Science and Engineering, Washington University in St. Louis, MO, USA as Visiting Researcher and was engaged in research of high-speed networking technologies including dynamic flow switching and soft-state ATM switching.   He received the B.E., M.E., and Ph.D degrees in information and computer sciences from Osaka University, Osaka in 1987 1989, and 1998, respectively.

Coffee Break / Exhibition / Interop Event
AI - from Deterministic to Instinctive Networking
Predicting the barriers to accepting emerging AI technology and outlining an implementation strategy for stepwise building of confidence. Use cases show how value creation catalyzes the acceptance process.

Ulrich Kohn,
Director Technical Marketing, ADVA Optical Networking

Ulrich is Director of technical marketing at ADVA Optical Networking with responsibility for the companie`s One Network Edge program.  With over 25 years of experience in fixed and mobile networks, Ulrich is familiar with the challenges and pain points of today's networks and is able to show how the latest technology provides answers and an economic, future-proof path forward.   Before joining ADVA Optical Networking in April 2013, he worked for Ericsson and Marconi Communications in management positions with Business Development, Network Strategy, Product Marketing and Technical Sales.

Context and Dependency Awareness of Data and Control Plane Relationships
Outlining the mappings, discussing the methodology involved in creating them, and providing examples of known behaviors that taken together, may enable fully automated remediation and optimization systems. And for those interested in working directly on AI capabilities, showing how to access fully documented training data sets.

Drew Pletcher,
Principal Engineer, Cisco
End of the Conference