Palczewski / Lee / Mookiah Production-Ready Applied Deep Learning

Learn how to construct and deploy complex models in PyTorch and TensorFlow deep learning frameworks
1. Auflage 2022
ISBN: 978-1-80323-805-0
Verlag: De Gruyter
Format: EPUB
Kopierschutz: 0 - No protection

E-Book, Englisch, 322 Seiten

No detailed description available for "Production-Ready Applied Deep Learning".

Autoren/Hrsg.

Palczewski, Tomasz

Lee, Jaejun (Brandon)

Mookiah, Lenin

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Mensch-Maschine-Interaktion Informationsarchitektur
• Mathematik | Informatik EDV | Informatik Technische Informatik
• Mathematik | Informatik EDV | Informatik Daten / Datenbanken Datenbankdesign & Datenbanktheorie
• Mathematik | Informatik EDV | Informatik Informatik Mensch-Maschine-Interaktion Informationsvisualisierung

Inhaltsverzeichnis

Table of Contents - Effective Planning of Deep Learning-Driven Projects
- Data Preparation for Deep Learning Projects

- Developing a Powerful Deep Learning Model

- Experiment Tracking, Model Management, and Dataset Versioning
- Data Preparation in the Cloud
- Efficient Model Training
- Revealing the Secret of Deep Learning Models
- Simplifying Deep Learning Model Deployment
- Scaling a Deep Learning Pipeline
- Improving Inference Efficiency
- Deep Learning on Mobile Devices
- Monitoring Deep Learning Endpoints in Production
- Reviewing the Completed Deep Learning Project

Über Autor(innen)

Palczewski Tomasz:

Tomasz Palczewski is currently working as a staff software engineer at Samsung Research America. He has a Ph.D. in physics and an eMBA degree from Quantic. His zeal for getting insights out of large datasets using cutting-edge techniques led him to work across the globe at CERN (Switzerland), LBNL (Italy), J-PARC (Japan), University of Alabama (US), and University of California (US). In 2016, he was deployed to the South Pole to calibrate the world's largest neutrino telescope. Later, he decided to pivot his career and focus on applying his skills in industry. Currently, he works on modeling user behavior and creating value for advertising and marketing verticals by deploying machine learning (ML), deep learning, and statistical models at scale.Lee Jaejun (Brandon):

Jaejun (Brandon) Lee is currently working as an AI research lead at RoboEye.ai, integrating cutting-edge algorithms in computer vision and AI into industrial automation solutions. He has obtained his master's degree from the University of Waterloo with research focused on natural language processing (NLP), specifically speech recognition. He has spent many years developing a fully productionized yet open source wake word detection toolkit with a web browser deployment target, Howl. Luckily, his effort has been picked up by Mozilla's Firefox Voice and it is actively providing a completely hands-free experience to many users all over the world.Mookiah Lenin:

Lenin Mookiah is a machine learning engineer who has worked with reputed tech companies – Samsung Research America, eBay Inc., and Adobe R&D. He has worked in the technology industry for over 11 years in various domains: banking, retail, eDiscovery, and media. He has played various roles in the end-to-end productization of large-scale machine learning systems. He mainly employs the big data ecosystem to build reliable feature pipelines that data scientists consume. Apart from his industrial experience, he researched anomaly detection in his Ph.D. at Tennessee Tech University (US) using a novel graph-based approach. He studied entity resolution on social networks during his master's at Tsinghua University, China.