img Leseprobe Leseprobe

Number Systems for Deep Neural Network Architectures

Thanos Stouraitis, Ghada Alsuhli, Hani Saleh, et al.

PDF
ca. 53,49

Springer Nature Switzerland img Link Publisher

Naturwissenschaften, Medizin, Informatik, Technik / Elektronik, Elektrotechnik, Nachrichtentechnik

Beschreibung

This book provides readers a comprehensive introduction to alternative number systems for more efficient representations of Deep Neural Network (DNN) data. Various number systems (conventional/unconventional) exploited for DNNs are discussed, including Floating Point (FP), Fixed Point (FXP), Logarithmic Number System (LNS), Residue Number System (RNS), Block Floating Point Number System (BFP), Dynamic Fixed-Point Number System (DFXP) and Posit Number System (PNS). The authors explore the impact of these number systems on the performance and hardware design of DNNs, highlighting the challenges associated with each number system and various solutions that are proposed for addressing them.

Weitere Titel in dieser Kategorie
Cover Vacuum Tubes
Amelia Khatri
Cover Birth of Radio
Eleanor Hawking

Kundenbewertungen

Schlagwörter

deep neural network number representation, deep neural network architectures, deep neural network hardware implementation, number systems for deep neural network hardware implementation, deep neural network accelerators