Resource-Efficient Artificial Intelligence - Probabilistic Machine Learning on Ultra-Low-Power Systems

For all autonomous devices the development of resource-aware machine learning techniques is required to reduce the tremendous resource consumption. This work provides theoretical and practical building blocks to bring full-fledged machine learning pipelines to systems with very low computational power or highly restricted energy supply. The presentation of theoretical methods is accompanied by actual learning results on ultra-low-power hardware.

Über den Autor / die Autorin

Dr. Nico Piatkowski
, Fraunhofer Institute IAIS, Sankt Augustin, Germany.

Zusammenfassung

For all autonomous devices the development of resource-aware machine learning techniques is required to reduce the tremendous resource consumption. This work provides theoretical and practical building blocks to bring full-fledged machine learning pipelines to systems with very low computational power or highly restricted energy supply. The presentation of theoretical methods is accompanied by actual learning results on ultra-low-power hardware.

Produktdetails

• Autoren: Nico Piatkowski
• Verlag: De Gruyter
• Sprache: Englisch
• Produktform: Taschenbuch
• Erschienen: 20.01.2024
• EAN: 9783110721058
• ISBN: 978-3-11-072105-8
• Seiten: 350
• Illustration: 100 col. ill.
• Serie: de Gruyter Textbook
• Themen: Naturwissenschaften, Medizin, Informatik, Technik > Informatik, EDV > Informatik; Informatik, Künstliche Intelligenz, machine learning, Maschinelles Lernen, Artificial Intelligence, Textbook, computer science, Wahrscheinlichkeitsmodelle, Algorithms & data structures, Information technology: general issues, Computer networking & communications, COM000000 COMPUTERS / General, TEC009000 Technology & Engineering / Engineering (General), COM032000 COMPUTERS / Information Technology, TEC008000 Technology & Engineering / Electronics / General, Power utilization & applications, COM051300 COMPUTERS / Programming / Algorithms, Speichergrenzen, Storage limits, Probability Models