Essays about: "end-to-end learning"

Showing result 1 - 5 of 22 essays containing the words end-to-end learning.

  1. 1. Deep learning navigation for UGVs on forests paths

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Linus Lind; [2018]
    Keywords : ;

    Abstract : Artificial intelligence and machine learning have seen great progress in recent years. In this work, we will look at the application of machine learning in visual navigational systems for unmanned vehicles in natural environments. READ MORE

  2. 2. 3D YOLO: End-to-End 3D Object Detection Using Point Clouds

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Ezeddin Al Hakim; [2018]
    Keywords : Computer vision; Machine Learning; Autonomous Vehicles; Autonomous Cars; Lider; Point Cloud; Deep Learning; Object Detection; YOLO;

    Abstract : For safe and reliable driving, it is essential that an autonomous vehicle can accurately perceive the surrounding environment. Modern sensor technologies used for perception, such as LiDAR and RADAR, deliver a large set of 3D measurement points known as a point cloud. READ MORE

  3. 3. Mobile Object Detection using TensorFlow Lite and Transfer Learning

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Oscar Alsing; [2018]
    Keywords : cnn; convolutional neural networks; transfer learning; mobile object detection;

    Abstract : With the advancement in deep learning in the past few years, we are able to create complex machine learning models for detecting objects in images, regardless of the characteristics of the objects to be detected. This development has enabled engineers to replace existing heuristics-based systems in favour of machine learning models with superior performance. READ MORE

  4. 4. Artificial Neural Networks in Swedish Speech Synthesis

    University essay from KTH/Tal-kommunikation

    Author : Per Näslund; [2018]
    Keywords : Speech Synthesis; neural; LSTM; Speech Technology; Tacotron; Attention; CNN; Neural Networks; RNN;

    Abstract : Text-to-speech (TTS) systems have entered our daily lives in the form of smart assistants and many other applications. Contemporary re- search applies machine learning and artificial neural networks (ANNs) to synthesize speech. It has been shown that these systems outperform the older concatenative and parametric methods. READ MORE

  5. 5. 3D Shape Detection for Augmented Reality

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Hector Anadon Leon; [2018]
    Keywords : 3D Machine Learning; object detection; computer vision; shape; point cloud;

    Abstract : In previous work, 2D object recognition has shown exceptional results. However, it is not possible to sense the environment spatial information, where the objects are and what they are. READ MORE