Sökning: "Iterative Pruning"

Hittade 4 uppsatser innehållade orden Iterative Pruning.

  1. 1. Pruning a Single-Shot Detector for Faster Inference : A Comparison of Two Pruning Approaches

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Karl Beckman; [2022]
    Nyckelord :Computer Vision; Object Detection; Single-Shot Detector; SSD-MobileNetV2; Iterative Pruning; Datorseende; Objektdetektering; Enstegsdetektor; SDD-MobileNet-V2; Iterativ Beskärning;

    Sammanfattning : Modern state-of-the-art object detection models are based on convolutional neural networks and can be divided into single-shot detectors and two-stage detectors. Two-stage detectors exhibit impressive detection performance but their complex pipelines make them slow. LÄS MER

  3. 2. A collision framework for rigid and deformable body simulation

    Master-uppsats, Linköpings universitet/Medie- och Informationsteknik; Linköpings universitet/Tekniska högskolan

    Författare :Rasmus Haapaoja; [2016]
    Nyckelord :collision detection; collision response; physically-based simulation;

    Sammanfattning : This thesis describes methods for collision detection and collision response, implemented in a complete collision framework for both rigid and deformable bodies. The framework is intended to act as a base for new technologies regarding muscle and facial simulation for feature film production, at the visual effects studio MPC. LÄS MER

  4. 3. A Multi-Agent System for playing the board game Risk

    Magister-uppsats, Blekinge Tekniska Högskola/Avdelningen för programvarusystem

    Författare :Fredrik Olsson; [2005]
    Nyckelord :Multi-Agent System; Board Games; Distributed Problem Solving; Risk;

    Sammanfattning : Risk is a game in which traditional Artificial-Intelligence methods such as for example iterative deepening and Alpha-Beta pruning can not successfully be applied due to the size of the search space. Distributed problem solving in the form of a multi-agent system might be the solution. LÄS MER

  5. 4. A Multi-Agent System for playing the board game Risk

    Magister-uppsats, Blekinge Tekniska Högskola/Avdelningen för programvarusystem

    Författare :Fredrik Olsson; [2005]
    Nyckelord :Multi-Agent System; Board Games; Distributed Problem Solving; Risk;

    Sammanfattning : Risk is a game in which traditional Artificial-Intelligence methods such as for example iterative deepening and Alpha-Beta pruning can not successfully be applied due to the size of the search space. Distributed problem solving in the form of a multi-agent system might be the solution. LÄS MER