Energy-Efficient Neural Networks using Approximate Computation Reuse

Computation of the linear Schrodinger Energy levels by Sinc method

Computation of the Schrodinger equation energy levels is very important in physics. For example we can use these levels to calculate the absorption coefficient and light refraction in a material as well as calculation of the interband and intersubband transition energies. Density of states of the system can also be obtained by using the energy levels. Thereafter we can determine that the system...

A Multithreaded CGRA for Convolutional Neural Network Processing

Convolutional neural network (CNN) is an essential model to achieve high accuracy in various machine learning applications, such as image recognition and natural language processing. One of the important issues for CNN acceleration with high energy efficiency and processing performance is efficient data reuse by exploiting the inherent data locality. In this paper, we propose a novel CGRA (Coar...

A Comparative Approximate Economic Behavior Analysis Of Support Vector Machines And Neural Networks Models

Escort: Efficient Sparse Convolutional Neural Networks on GPUs

Deep neural networks have achieved remarkable accuracy in many artificial intelligence applications, e.g. computer vision, at the cost of a large number of parameters and high computational complexity. Weight pruning can compress DNN models by removing redundant parameters in the networks, but it brings sparsity in the weight matrix, and therefore makes the computation inefficient on GPUs. Alth...

Approximate Computation using Neuralized FPU

Neural networks can be used as function approximators to improve the energy efficiency, performance, and fault-tolerance of traditional computer architectures. To maximize these improvements the granularity of the function must be as large as possible. This work-inprogress abstract explores the lower limits of neural network function approximation by replacing individual floating point multipli...