September 19, 2022 – The challenges associated with getting AI models into production are well known. What developers need now are ways to address those challenges.
It’s the topic Ramtin Davanlou, AI & Analytics Principal Director at Accenture, discussed during his presentation at the oneAPI DevSummit for AI 2022, specifically focusing on how developers can get their models into production and do it more quickly.
Key takeaways:
- Moving through the AI development-to-deployment cycle requires a combination of hardware acceleration and software optimization, the latter which is provided by oneAPI.
- Intel, in conjunction with Accenture, has created AI reference kits to help developers streamline and expedite the development and deployment of AI models for key business domains—healthcare, manufacturing, retail, and more.
- The first four kits are available now.
Watch [24:05] and learn how to accelerate AI development cycles by using the tools and framework optimizations that are part of Intel’s AI software portfolio.
AI Reference Kits Overview
Each is optimized with Intel® AI Tools powered by oneAPI—specifically Intel® AI Analytics Toolkit and Intel® Distribution of OpenVINO™ toolkit—for faster training and inferencing performance using less compute resources.
The kits include:
- Solution Brief: An overview of the value proposition, describing the problem, solution, and impact.
- Developer Guide: Recommendations for frameworks, algorithms, data processing techniques, hyper-tuning, quantization, and deployment, including showing how to build the ML pipeline.
- Code Repository: GitHub code snippets, configurations, datasets, and libraries before and after optimization.
- Platform Architecture: A guide for setting up the best performing compute architecture.
- Benchmarking Results: Performance gains and metrics showing impact of oneAPI optimizations.
How to Get Them
The following are available now, with more on tap every quarter:
- Predictive Asset Maintenance: Predict the probability of failure and proactively maintain assets to avoid outages, downtimes and operational costs.
- Visual Quality Inspection: Use computer vision to detect defects and reduce quality inspection time and costs.
- Customer Care Agent Intent Enablement: Enable virtual agents to understand user intents in automated conversations using Natural Language Understanding (NLU).
- Intelligent Document Indexing: Reduce human capital costs and manual intervention for classifying massive volumes of incoming documents ingested into the organization.
Learn more about these new, trained AI reference kits, including the opportunity to get notified when new kits are available.
About our expert
As a part of Accenture’s Applied Intelligence group, Ramtin Davanlou leads the development of global offering and solutions in analytics and artificial intelligence. His key responsibility is to drive growth in AI through innovation and thought leadership. He works with ecosystem partners and provides optimized solutions and technology architecture recommendations to clients in various industries.
See Related Content
On-Demand Webinars & Podcasts
- Scale AI with Optimized, Domain-Specific Reference Kits
- Intel, Databricks, and HEAVY.AI Streamline End-to-End AI Pipelines
- GE Healthcare Solutions Accelerated by Intel® oneAPI Toolkits
Tech Articles
- Optimize Distributed AI Training using Intel® oneAPI Toolkits
- Getting Started with Habana® Gaudi® for Deep Learning Training
- A Scale-Out Training Solution for Deep Learning Recommender Systems
- Superior Machine Learning Performance on Intel® Xeon® Processors
Podcasts
Get the Software
Intel® oneAPI AI Analytics Toolkit
Accelerate end-to-end machine learning and data science pipelines with optimized deep learning frameworks and high-performing Python* libraries.
Get It Now
See All Tools