Essays about: "Arithmetic Computation"
Showing result 1 - 5 of 9 essays containing the words Arithmetic Computation.
-
1. EMONAS : Evolutionary Multi-objective Neuron Architecture Search of Deep Neural Network
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Customized Deep Neural Network (DNN) accelerators have been increasingly popular in various applications, from autonomous driving and natural language processing to healthcare and finance, etc. However, deploying them directly on embedded system peripherals within real-time operating systems (RTOS) is not easy due to the paradox of the complexity of DNNs and the simplicity of embedded system devices. READ MORE
-
2. Leveraging Posits for the Conjugate Gradient Linear Solver on an Application-Level RISC-V Core
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Emerging floating-point arithmetics provide a way to optimize the execution of computationally-intensive algorithms. This is the case with scientific computational kernels such as the Conjugate Gradient (CG) linear solver. Exploring new arithmetics is of paramount importance to maximize the accuracy and timing performance of these algorithms. READ MORE
-
3. Representation and Efficient Computation of Sparse Matrix for Neural Networks in Customized Hardware
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Deep Neural Networks are widely applied to various kinds of fields nowadays. However, hundreds of thousands of neurons in each layer result in intensive memory storage requirement and a massive number of operations, making it difficult to employ deep neural networks on mobile devices where the hardware resources are limited. READ MORE
-
4. Effect of distance measures and feature representations on distance-based accessibility measures
University essay from Lunds universitet/Institutionen för naturgeografi och ekosystemvetenskapAbstract : Distance-based accessibility measures are often built using vector representations of origin and destination features, and Euclidean or network-based distances. There are few comparisons of how the choice of feature representations and distance types affects results. Existing comparisons often use Spearman’s rank correlation coefficients. READ MORE
-
5. Hardware Architectures for the Inverse Square Root and the Inverse Functions using Harmonized Parabolic Synthesis
University essay from Lunds universitet/Institutionen för elektro- och informationsteknikAbstract : This thesis presents a comparison between implementations of the inverse square root function, using two approximation algorithms; Harmonized Parabolic Synthesis and the Newton-Raphson Method. The input is a 15 bit fixed-point number, the range of which is selected so that the implementation is suitable for use as a block implementing the inverse square root for floating-point numbers, and the designs are constrained by the error, which must be < 2^(-15). READ MORE
