Premiere
summary
Pipeline automations show how to cut months of cross-team work to deployment by wiring AWS step-based ML pipelines into CI/CD; a drone case study benchmarks CNNs versus transformers for object detection with accuracy and latency numbers; practical demos include SageMaker BlazingText on entire Wikipedia for word embeddings, ONNX model export and deploy to embed models in apps, TensorRT + DeepStream low-latency pipeline for real-time inference, and an open-source vVate vector DB for semantic search — clear tools, datasets, and measured results.
AI-written summary · about
chapters (25)
- 0:00Preamble
- 0:44Antje Barth - Amazon Web Services
- 1:17Tempest van Schaik - Microsoft
- 1:47Milecia McGregor
- 2:06Gajendra Deshpande
- 2:40Madalina Burci
- 3:17Suraj Muraleedharan
- 3:35Hila Fox
- 3:56Eduardo Dixo
- 4:25Karl Weinmeister
- 4:47Asif Mujawar
- 5:18Nidal Albeiruti
- 5:59Pawel Skrzypek & Anna Warno
- 6:38Ron Lyle Dagdag
- 7:06Laura Ham
- 7:35Aditya Lohia
- 8:12Matteo Gabrielli
- 8:44Nicola Pietroluongo
- 9:10Mofizur Rahman
- 9:30Dinesh Subramani
- 10:24Marianna Diachuk
- 10:57Nicolas Metallo
- 11:24Tim Spann
- 11:49Joshua Arvin Lat
- 12:00Thank you!
related talks
17mAI/ML demo derby
08mPremiere
33mDeploying and Scaling Spark ML and Tensorflow AI Models
09mPremiere
54mDeep learning on AWS with NVIDIA: From training to deployment
12mLeveraging AWS and Kubernetes for Scalable AI/ML Workloads in the Cloud
40mVertex AI: Pipelines for your MLOps workflows
21mPremiere - Conf42 Python 2024
