Join this moderated roundtable discussion group of 10-20 attendees focusing on efficient edge ML inference.

There will be several moderators per topic area to allow for multiple tables and questions will be prepared in advance. Each group will be multidisciplinary with representation from across the tech stack. Attendees who have registered for the event will be able to sign up for the roundtable discussion groups closer to the event, or via an AI Hardware & Edge AI Summit sales representative.

The subtopics to be discussed will include:

- Efficient edge-based inference on low-power devices: hardware and software optimizations
- Challenges of handling high-dimensional data at the edge for efficient inference
- Adapting machine learning models for low-power edge devices: balancing model accuracy and computational complexity
- Designing efficient edge-to-cloud communication protocols to minimize latency and optimize bandwidth usage

Join this moderated roundtable discussion group of 10-20 attendees focusing on efficient cloud based ML inference.

There will be several moderators per topic area to allow for multiple tables and questions will be prepared in advance. Each group will be multidisciplinary with representation from across the tech stack. Attendees who have registered for the event will be able to sign up for the roundtable discussion groups closer to the event, or via an AI Hardware & Edge AI Summit sales representative.

The subtopics to be discussed will include:

- Optimizing hardware for efficient inference: balancing cost and performance
- Latency and throughput challenges in cloud-based machine learning inference
- Designing distributed systems for scalable and reliable inference

Join this moderated roundtable discussion group of 10-20 attendees focusing on challenges in deploying machine learning into production.

There will be several moderators per topic area to allow for multiple tables and questions will be prepared in advance. Each group will be multidisciplinary with representation from across the tech stack. Attendees who have registered for the event will be able to sign up for the roundtable discussion groups closer to the event, or via an AI Hardware & Edge AI Summit sales representative.

The subtopics to be discussed will include:

- Mitigating challenges from changes between training and production infrastructure
- MLOps workflows for shortening time-to-value
- Navigating compatability, scalability and availabilty of hardware during deployment

Join this moderated roundtable discussion group of 10-20 attendees focusing on novel training and learning paradigms for ML. 

There will be several moderators per topic area to allow for multiple tables and questions will be prepared in advance. Each group will be multidisciplinary with representation from across the tech stack. Attendees who have registered for the event will be able to sign up for the roundtable discussion groups closer to the event, or via an AI Hardware & Edge AI Summit sales representative.

The subtopics to be discussed will include:

- Limitations of current training architectures and paradigms
- Use cases and challenges for distributed learning (i.e. federated learning)
- Data centric AI + few & low shot learning methods for efficient training
- Datasets for ML training - Open Source options

Join this moderated roundtable discussion group of 10-20 attendees focusing on novel training and learning paradigms for ML. 

There will be several moderators per topic area to allow for multiple tables and questions will be prepared in advance. Each group will be multidisciplinary with representation from across the tech stack. Attendees who have registered for the event will be able to sign up for the roundtable discussion groups closer to the event, or via an AI Hardware & Edge AI Summit sales representative.

The subtopics to be discussed will include:

- Limitations of current training architectures and paradigms
- Use cases and challenges for distributed learning (i.e. federated learning)
- Data centric AI + few & low shot learning methods for efficient training
- Datasets for ML training - Open Source options

Real-time personalized recommendations (RTPRec) have become increasingly prevalent in the digital realm, particularly as more users have become accustomed to using mobile apps and consuming larger amounts of digital data, videos, and engaging in e-commerce activities online following the Covid-19 pandemic.

DL-based recommender is known for its superior accuracy in handling unstructured data, often referred to as embeddings. This characteristic makes them ideal candidates for personalized recommendations. However, it's important to note that DL-based models can involve an extensive number of parameters, ranging into the billions or even trillions, which can pose significant challenges when real-time processing is crucial.

To address this challenge, various strategies such as inference optimization, model compression, and the utilization of hardware accelerators have been introduced to enhance performance and meet the stringent latency requirements of real-time applications. Additionally, this session will delve into accelerator-based distributed systems, offering insights into memory management and performance scalability from an infrastructure perspective.