Name: Secure AI models deployment at the edge with OpenVINO™ on Ubuntu containers
Start: 2021-11-17T17:00:00Z
End: 2021-11-17T17:00:47.000Z
Location: BrightTALK
Rating: 4.3

Get the most in depth information about the Ubuntu technology and services from Canonical. 

Learn why Ubuntu is the preferred Linux platform and how Canonical can help you make the most out of your Ubuntu environment.

Introduction to Ubuntu Core 24

Join us for a deep dive into the role of vector databases in generative AI applications. Vector databases facilitate efficient data representation, retrieval and manipulation, enabling AI systems to generate high-fidelity outputs across various domains, from natural language processing to image synthesis.

This webinar will discuss various concepts, such as generative AI, retrieval augmented generation (RAG), the importance of search engines, and efficient open source tooling that enables developers and enthusiasts to build their generative AI applications.

Vector databases for generative AI applications

Developing solutions with open source software provides rapid time-to-market and extensive community support, empowering businesses to deliver innovative products swiftly by leveraging the collective expertise and diverse support of developers and users. Despite these advantages, open source software is susceptible to security vulnerabilities, and addressing a Common Vulnerabilities and Exposures (CVE) issue within your solution can be time-consuming and costly, potentially disrupting development cycles and impacting your bottom line. Google and Canonical have a decade-long partnership based on the belief that software and infrastructure can be seamless and versatile without compromising scale, security, compliance, or reliability.

Join our webinar to discover how you can enhance the security of your complete software supply chain using Ubuntu Pro on Google Cloud. Explore the extensive coverage provided by the Ubuntu Universe, ensuring security for diverse workloads such as MongoDB, Apache Spark, Redis, Kafka, MySQL, NGINX, PostgreSQL, and language ecosystems including Python, Java, Ruby, and JavaScript/Node.js. 

In this webinar, you’ll learn:
-How to host your fully secured software supply chain on Google Cloud
-How Google Cloud provides the secure, open source, scalable infrastructure that enables organizations to run workloads on premises, in Google Cloud, or in any other public or private cloud.
-How Ubuntu Pro’s vulnerability patching process reduces the average CVE exposure time from 98 days to 1 day
-How Ubuntu Pro serves as a single trusted source for security patching for over 30,000 software packages
-How to easily upgrade from Ubuntu to Ubuntu Pro on GCP

Secure your supply chain on Google Cloud with Ubuntu Pro

In this webinar, we’ll share how confidential computing can bring hardware-level security to your sensitive AI workloads, both on-prem and on the public cloud.

Secure your AI workloads with Confidential VMs

As organisations increasingly look to take advantage of AI technologies, there are several critical considerations that they must contend with, including intellectual property, data security and costs related to computing infrastructure. Private cloud solutions are ideally suited to solving these challenges. Canonical Openstack, for instance, is a great example of a cloud platform that can be used to build and deploy machine learning applications securely and cost-effectively.

Why consider a private cloud for AI?
Private clouds are a handy solution for enterprises when it comes to AI/ML since they deliver many of the key capabilities that organisations report as important, including:
1) Cost optimisation: Private clouds enable businesses to optimise their costs by always running their workloads where it makes more sense from an economic standpoint.
2) Digital sovereignty: Private clouds offer a safe environment for data and applications by ensuring that the organisation owns access and controls the level of sharing amongst the different teams using the cloud.
3) Performance acceleration: Private clouds offer GPU virtualisation and other capabilities to improve performance and therefore project delivery, confidentiality, efficiency and time to setup as required by sophisticated AI/ML workloads. 

Learn more about AI on the private cloud in this webinar:
Join the webinar on 30 April 2024, where Tytus Kurek, OpenStack Product Manager, and Andreea Munteanu, AI Product Manager, will talk more about private clouds for AI projects. The presentation will cover:
1) Key considerations when building a private cloud for AI projects
2) Performance acceleration options for private cloud
3) Guidance for Kubernetes on OpenStack for AI initiatives
And more…

[APAC] AI on Private Cloud: why is it relevant in the hyperscalers era?

A real time kernel is designed to serve extreme latency-dependent use cases and to provide deterministic response times to service events.

In this webinar we will cover when and how you can deploy a real time kernel, giving examples of applications in healthcare, industrial, automotive, robotics, and more. We will talk about kernel preemption and preemption modes, with a deep dive on PREEMPT_RT (the out-of-tree patch for x86 and Arm architectures) and real time Ubuntu.

This webinar is designed for:
- Embedded software engineers
- Solutions/systems architects
- Developers
- IoT business developers
- Product managers

Real time kernel: use cases and deployment strategies with Ubuntu

You’ve probably heard of Linux, but maybe you’re not quite sure what it is, what you can do with it, and, more importantly, whether you can trust it to run your next project!

In this webinar, Canonical’s Ijlal Loutfi and Henry Coggill discuss the security of Linux and Ubuntu. We’ll start with the basics of why the operating system is important and how it underpins the integrity of any applications running on top. We will provide background information as to what Linux is, for those who might be unfamiliar with its history, and discuss how open-source software is developed and bundled into distributions.

We will discuss how the open-source ecosystem deals with security vulnerabilities, how they are discovered and fixed, and how end users react to this perpetual dance. Then we will go deeper into the range of security technology built into Ubuntu and what this means for protection against unknown threats. Finally, we will explore how Canonical’s enterprise-grade support delivers a comprehensive platform for secure open-source adoption.

Is Linux secure?

What can PostgreSQL do for AI application?

PostgreSQL is capable of efficiently storing and retrieving large amounts of data, such as training data for your models. Its wide support of the SQL standard, including SQL/MED, makes inspecting and querying that data a breeze. Moreover, PostgreSQL comes with similarity search capabilities, providing convenient index structures (GIST, GIN...) and built-in extensions (fuzzystrmatch, pg_trgm...).

Yet, there is more to PostgreSQL's ecosystem than the database server. There are more than 1000 extensions for PostgreSQL, many of which can be useful for AI developers and users, for example pgvector and PostgresML. 


The Role of PostgreSQL in MLOps

MLOps projects such as Kubeflow rely on relational databases for storing different artefacts, and choosing which relational database to use for MLOps is a common dilemma. We approached a similar topic in our recent webinar “PostgreSQL vs MySQL”, where we explored how, despite looking similar on the surface, the two databases are actually very different. The significant structural differences between databases can have a tremendous influence on the performance of any ML project, so understanding the possible impact is critical for both the enterprises who use these platforms and the engineers who develop them.


So how do we use PostgreSQL for machine learning?

Join the live discussion to learn more about using PostgreSQL for AI projects. The webinar will cover:
- An overview of the PostgreSQL ecosystem for AI projects
- Benefits of PostgreSQL for AI projects
- Use cases where PostgreSQL should be used for AI projects

Using PostgreSQL to power your AI applications

What does it mean to be a smarter enterprise, powered by artificial intelligence (AI) and big data? The possibilities reach far beyond today’s chatbots, self-driving cars, and product recommendation engines.

MicroCloud is the newest addition to Canonical’s cloud infrastructure portfolio. It is a low-touch, open-source cloud solution purpose-built for scalable clusters and edge deployments for all types of enterprises. With simplicity, security, and automation at its core, MicroCloud minimises the time and effort required to deploy and maintain a production-grade cloud infrastructure.

Join us as we delve into the features and benefits of MicroCloud, including its suitability for on-premise clouds and edge deployments at remote locations. Learn how MicroCloud caters to distributed environments, offering a simpler, more prescriptive cloud experience that makes zero-ops a reality for many industries.

Furthermore, discover how MicroCloud's lightweight architecture enables cost-effective deployments on both commodity and high-end hardware, with several options to further reduce its footprint depending on workload needs. Take advantage of this opportunity to explore Canonical MicroCloud and learn how it can transform your cloud infrastructure.

In this webinar, we will cover:
1) What is MicroCloud?
2) What are the challenges in today’s cloud infrastructure ecosystem and how does MicroCloud address them?
3) What are the use cases for MicroCloud?
4) How can you deploy your own MicroCloud?
5) What’s coming in the next release? 

Tune in live on April 16th, at 18:00 CET or watch on demand at your convenience.

MicroCloud: a low-touch open source cloud for all

Move to the cloud, they said. It will be fun, they said.

So you decided to do so, but now you’re facing an eternal dilemma: use one of the existing public cloud platforms or build your own? You ask yourself more questions: Which option is more convenient for your use case? Which one is more cost-effective? How do you preserve digital sovereignty regardless of the choice?

These are all good questions. We will cover them in this webinar. However, what you’re really searching for is more elementary. It is about how you can make use of available cloud technologies to meet your organisations’ needs. In other words, how you can do computing, your way?

During this webinar we will show you a “do it yourself” approach to cloud infrastructure implementation. By using mature open source technologies we will demonstrate the path towards your own production-grade cloud, preserving digital sovereignty and ensuring cost-effectiveness, while maintaining the versatility provided by global tech giants.

OpenStack is the world's most popular open source cloud platform and its adoption continues to grow exponentially every year. It serves as an extension or a reasonable alternative to hyperscalers, effectively addressing cloud cost optimisation concerns. But at the same time, OpenStack adoption has always been a challenge. Hence through this webinar, we want to help you get started with OpenStack.

In this webinar we will:
1) Discuss the current status of the cloud computing market
2) Delve into the world of OpenStack - the most popular open source cloud platform
3) Walk you through OpenStack’s high-level architecture, its services and their functions
4) Teach you how to get started and break the ice with OpenStack immediately

What is OpenStack and why does it matter?

AI is at the heart of a revolution in the technology space. From oil & gas to public sector, from telco to retail, all departments from all industries are looking for ways to put AI to work. Once organisations have finalised use case assessment, their next question is typically related to the environment they will use to develop and deploy their AI initiatives. 

They often prefer the public clouds as an initial environment, because of the computing power and ability to scale as projects mature. In addition to the infrastructure, enterprises need software where they can develop and deploy the machine learning models. Open source tools such as Jupyter Notebooks or MLflow are a great starting point and enable you to have a consistent experience on any cloud for your ML workloads. When scaling projects, the need for MLOps platforms such as Charmed Kubeflow is absolutely obvious.

Join our webinar to learn more about open source tooling for AI on public cloud. Led by Aaron Whitehouse, Senior Public Cloud Enablement Director, and Andreea Munteanu, AI Product Manager, the webinar will cover:

Scenarios in which open source tooling on public cloud solves a problem for AI initiatives
Main benefits of using open source tooling on the public cloud for AI projects
Use cases from our customers 
Hybrid cloud and multi cloud opportunities for AI projects

AI on public cloud with open source

Deploying a PostgreSQL instance on Ubuntu is as simple as running a single command (i.e. sudo apt install postgresql-<version>). Yet, running a single instance of PostgreSQL is a recipe for downtime and reputation damage to your company.

To run a highly available PostgreSQL deployment you need to leverage several techniques such as replication, automatic failovers, failure isolation and backups. 

In this webinar, we will examine advanced techniques to implement fail-safe replication and automatic fail-overs. We will cover the following:
Replication techniques
Automatic fail-over techniques on client and server side
Demo

A deep dive into PostgreSQL replication and automatic failover techniques

Recent changes at VMware have compelled existing customers to consider alternatives. Many have turned their eyes to open source. If you’re considering options to remove vendor lock-in, lower total cost of ownership (TCO) and advance innovation, this webinar is for you. 

In this webinar, we present open-source solutions as an alternative to VMware software. We show that adopting open source brings many benefits, including cost savings, increased flexibility and higher quality. We demonstrate how to build a fully functional cloud infrastructure on Ubuntu while ensuring feature parity with VMware solutions. Finally, we discuss how to perform a hassle-free migration.

This webinar includes an overview of:
1) The most common migration paths
2) Ubuntu-based infrastructure
3) Canonical’s commercial services

From VMware to Open Source

In database management, MongoDB stands as the unrivalled leader for document databases.
This session will explore how organisations tackle data challenges and harness MongoDB to modernise their data management strategies, gaining a competitive edge in the process.

In this webinar, you will learn about:
the unique data management challenges faced by small, medium, and large enterprises,
insights into specific use cases where MongoDB proves to be an ideal database choice,
tailored database solutions for industry-specific domains and diverse enterprise needs,
charmed MongoDB, an enhanced, and fully-compatible drop-in replacement for MongoDB Community Edition with advanced MongoDB enterprise features.

MongoDB for modern data management

Join us for a webinar featuring industry experts as they delve into the future of automotive. We’ll be focusing on software-defined vehicles (SDVs) and the innovative high-performance computing (HPC) solutions provided by EB corbos Linux – built on Ubuntu, leveraging the partnership between Canonical and Elektrobit.

In this session, Bertrand Boisseau, Automotive Sector Lead at Canonical, will be joined by guests Jens Petersohn, Head of HPC OS Product Group, Elektrobit, and Loïc Minier, Director of Partner Engineering Architecture from Canonical. These experts will provide insight into the trends shaping SDVs, the challenges they present, and the critical role of cybersecurity in this evolving landscape.

During the webinar, we will explore what SDVs are and their implications, examining the paradigm shift in the automotive industry towards software-driven vehicles.
 
We will address key topics such as the need for cybersecurity mandates, the evolving E/E architecture of SDVs, the importance of maintaining software integrity, meeting regulatory requirements, and delivering innovative features to enhance the user experience.

Join us to hear about:
- The challenges of integrating advanced software functionalities while ensuring safety and security throughout the vehicle's lifecycle.
- The partnership between Canonical and Elektrobit, highlighting the synergy between Ubuntu's open-source expertise and Elektrobit's automotive software solutions. 
- The specifics of EB Corbos Linux, showcasing its secure, scalable, and customizable platform tailored for SDV development.

Don't miss this opportunity to gain valuable insights into the future of automotive technology and learn how EB corbos Linux – built on Ubuntu, is paving the way for the next generation of software-defined vehicles. 

Register now and join us as we explore the intersection of innovation, security, and sustainability in the automotive industry.

Unlocking software-defined vehicles: a deep dive into automotive software

Across the world, the application of Artificial Intelligence and Machine Learning (AI/ML) to business challenges is a hot topic. But, what does it mean for storage systems, and how can open source storage answer those needs?  Without data, and speedy access to it, AI solutions might not deliver the results as quickly as expected, delaying insights and innovation.  Canonical Ceph is a great example of a highly scalable open source storage solution that can be used to back modern AI/ML workflows and unlock the full potential of your AI ecosystem.
In this webinar we will explore typical use cases for external storage for AI systems, the workflows, the impact AI has on storage systems, and also the impact that storage systems can have on your AI jobs.

AI storage with Ceph

Many entities mistakenly consider ML models as the only significant challenge in an AI project. In reality, one of the most essential considerations for a successful AI/ML initiative is the infrastructure on which models are deployed, tested, and rolled out. This in itself creates the need for AI infrastructure specialists, which can be both difficult and costly to find. There is, however, another option: outsourcing your AI infrastructure to a multi-cloud managed service provider. 

Choosing an open-sourced managed infrastructure solution can help you accelerate your time to production, easily and cost-effectively cover some essential skill gaps in your ML journey, and even increase your budget’s predictability. In this webinar, product managers Adrian Matei and Andreea Munteanu explore the implications and benefits of adopting a Managed AI solution like Canonical’s. Join us and find out more!

Topics covered include: 
- Managed AI infrastructure overview & processes 
- Products & platforms
- Pre-deployment considerations
- Benefits of adopting the solution 
and more!

Managed AI infrastructure: demystifying AI’s most underrated challenge

Building a secure software supply chain is the challenge facing developers of tomorrow's applications. Deep learning models in frameworks like PyTorch and TensorFlow require complex pipelines, composing from abundant resources. From training the models to testing, optimising, and deploying them on OCI images with OpenVINO™. This webinar will focus on the deployment on containers phase, building on the work done by Intel and Canonical to provide not only developer-friendly yet also secure and stable container images. By combining Ubuntu containers with the OpenVINO™ Model Server, developers can deploy and manage inference-as-a-service on a range of Intel® platforms using Kubernetes – from the edge to the cloud.

Secure AI models deployment at the edge with OpenVINO™ on Ubuntu containers

Artificial Intelligence

Containers

edge

Security

Cloud computing has exploded over the past few years, delivering a previously unimagined level of workplace mobility and flexibility. The cloud computing community on BrightTALK is made up of thousands of engaged professionals learning from the latest cloud computing research and resources. Join the community to expand your cloud computing knowledge and have your questions answered in live sessions with industry experts and vendor representatives.

Cloud Computing

The application development community features top thought leadership focusing on optimal practices in software development, SDLC methodology, mobile app development and application development platforms and tools. Join top software engineers and coders as they cover emerging trends in everything from enterprise app development to developing for mobile platforms such as Android and iOS.

Application Development

Enterprise applications have become a crucial piece of infrastructure for many businesses. The enterprise applications community on BrightTALK features the latest insights in enterprise application integration, enterprise application architecture and EAS software. Join the community to gain access to thousands of videos and webinars presented by recognized enterprise information systems experts and arm yourself with the knowledge you need to succeed.

Enterprise Applications

Join thousands of engaged IT professionals in the application management community on BrightTALK. Interact with your peers in relevant webinars and videos on the latest trends and best practices for application lifecycle management, application performance management and application development.

Application Management

Get powerful end user computing insights from influential EUC experts. Connect with thought leaders and colleagues to get the most up-to-date knowledge on effective approaches to get non-programmers to create working applications.

End User Computing

As an IT professional, many of the problems you face are multifaceted, complex and don’t lend themselves to simple solutions. The information technology community features useful and free information technology resources. Join to browse thousands of videos and webinars on ITIL best practices, IT security strategy and more presented by leading CTOs, CIOs and other technology experts.

Secure AI models deployment at the edge with OpenVINO™ on Ubuntu containers

Presented by

About this talk

More from this channel