Essays about: "semantic memory"

Showing result 1 - 5 of 37 essays containing the words semantic memory.

  1. 1. Improving 3D Point Cloud Segmentation Using Multimodal Fusion of Projected 2D Imagery Data : Improving 3D Point Cloud Segmentation Using Multimodal Fusion of Projected 2D Imagery Data

    University essay from Linköpings universitet/Datorseende

    Author : Linbo He; [2019]
    Keywords : deep learning; multimodal fusion; multimodality; semantic segmentation; point cloud segmentation;

    Abstract : Semantic segmentation is a key approach to comprehensive image data analysis. It can be applied to analyze 2D images, videos, and even point clouds that contain 3D data points. READ MORE

  2. 2. Memory Efficient Semantic Segmentation for Embedded Systems

    University essay from Lunds universitet/Institutionen för datavetenskap

    Author : Haochen Liu; Erik Olsson; [2019]
    Keywords : Neural networks; Semantic segmentation; Pruning; Quantization; Tiling; Memory allocation; DeepLab; MobileNet; Technology and Engineering;

    Abstract : Convolutional neural networks (CNNs) have made rapid progress in the last years and in fields, such as computer vision, they are considered state-of-the-art. However, CNNs are very computationally intensive. This makes them challenging to use in embedded devices such as smartphones, security cameras and cars. READ MORE

  3. 3. A Detailed Analysis of Semantic Dependency Parsing with Deep Neural Networks

    University essay from Linköpings universitet/Interaktiva och kognitiva system

    Author : Daniel Roxbo; [2019]
    Keywords : Semantic Dependency Parsing; LSTM;

    Abstract : The use of Long Short Term Memory (LSTM) networks continues to yield better results in natural language processing tasks. One area which recently has seen significant improvements is semantic dependency parsing, where the current state-of-the-art model uses a multilayer LSTM combined with an attention-based scoring function to predict the dependencies. READ MORE

  4. 4. Experimenting with picture-based methods for semantic fieldwork: A case study on quantity superlatives in Persian

    University essay from Göteborgs universitet/Institutionen för filosofi, lingvistikoch vetenskapsteori

    Author : Golsa Nouri-Hosseini; [2018-11-14]
    Keywords : picture-based methods; semantic fieldwork; superlatives; Persian;

    Abstract : This work (a) presents a novel questionnaire for eliciting comparatives and superlatives of quality and quantity; (b) suggests guidelines for creating visual elicitation stimuli, as well as practical implications for semantic fieldworkers; (c) reports on a case study comparing two visual elicitation methods in semantic fieldwork, storyboards and picture-aided translation, showing that picture-aided translation might work better than storyboards for some purposes; (d) reports the results of comparing two different stories (the ‘What Matters’ story, developed in the project, and the ‘Bake-off’ story from Totem Field Storyboards) in semantic fieldwork; and (e) presents results of studying the morphosyntactic strategies for expressing superlatives of quantity and quality, comparatives, definiteness, and absolute, relative and proportional readings in Persian.Storyboards are a series of pictures which tell a story, and the participants are invited to tell the story in their native language, based on the pictures. READ MORE

  5. 5. Localising and Reconstructing Drill Holes in 3D Objects using Machine Learning

    University essay from Uppsala universitet/Institutionen för informationsteknologi

    Author : Viktor Ståhl; [2018]
    Keywords : ;

    Abstract : To move towards an increasingly automated future, machines are becoming smarter and can now solve tasks only humans could before. In this thesis project, the possibility to find, classify and reconstruct holes in three dimensional objects using machine learning is explored. READ MORE