SPERT-II: A Vector Microprocessor System and its Application to Large Problems in Backpropagation Training

نویسندگان

  • John Wawrzynek
  • Krste Asanovic
  • Brian Kingsbury
  • James Beck
  • David Johnson
  • Nelson Morgan
چکیده

We report on our development of a high-performance system for neural network and other signal processing applications. We have designed and implemented a vector microprocessor and packaged it as an attached processor for a conventional workstation. We present performance comparisons with commercial workstations on neural network backpropagation training. The SPERT-II system demonstrates significant speedups over extensively handoptimization code running on the workstations.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Fast Kohonen Net Implementation for Spert-II

We present an implementation of Kohonen Self-Organizing Feature Maps for the Spert-II vector microprocessor system. The implementation supports arbitrary neural map topologies and arbitrary neighborhood functions. For small networks, as used in real-world tasks, a single Spert-II board is measured to run Kohonen net classiication at up to 208 million connections per second (MCPS). On a speech c...

متن کامل

Simulation of Reduced Precision Arithmetic for Digital Neural Networks Using the RAP Machine

This paper describes some of our recent work in the development of computer architectures for eecient execution of artiicial neural network algorithms. Our earlier system, the Ring Array Processor (RAP), was a multiprocessor based on commercial DSPs with a low-latency ring interconnection scheme. We have used the RAP to simulate variable precision arithmetic and guide us in the design of higher...

متن کامل

Using simulations of reduced precision arithmetic to design a neuro-microprocessor

This article describes some of our recent work in the development of computer architectures for efficient execution of artificial neural network algorithms. Our earlier system, the Ring Array Processor (RAP), was a multiprocessor based on commercial DSPs with a low-latency ring interconnection scheme. We have used the RAP to simulate variable precision arithmetic to guide us in the design of ar...

متن کامل

Spert-II: A Vector Microprocessor System

March 1996 79 Many algorithms used in human-machine interface applications—such as speech, image, and handwriting recognition— require extensive computation. The burgeoning area of multimedia processing also requires high-performance computing. Processing elements for use in these areas must provide high performance at low cost, as they probably will appear in a variety of consumer products. Th...

متن کامل

A MULTI-OBJECTIVE EVOLUTIONARY ALGORITHM USING DECOMPOSITION (MOEA/D) AND ITS APPLICATION IN MULTIPURPOSE MULTI-RESERVOIR OPERATIONS

This paper presents a Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D) for the optimal operation of a complex multipurpose and multi-reservoir system. Firstly, MOEA/D decomposes a multi-objective optimization problem into a number of scalar optimization sub-problems and optimizes them simultaneously. It uses information of its several neighboring sub-problems for optimizin...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1995