scholarly journals Leveraging Deep Learning for Visual Odometry Using Optical Flow

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1313
Author(s):  
Tejas Pandey ◽  
Dexmont Pena ◽  
Jonathan Byrne ◽  
David Moloney
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Optical Flow ◽  
Recurrent Neural Networks ◽  
Deep Neural Networks ◽  
Visual Odometry ◽  
Camera Motion ◽  
Learning Approaches ◽  
Outlier Rejection ◽  
Entire Trajectory

In this paper, we study deep learning approaches for monocular visual odometry (VO). Deep learning solutions have shown to be effective in VO applications, replacing the need for highly engineered steps, such as feature extraction and outlier rejection in a traditional pipeline. We propose a new architecture combining ego-motion estimation and sequence-based learning using deep neural networks. We estimate camera motion from optical flow using Convolutional Neural Networks (CNNs) and model the motion dynamics using Recurrent Neural Networks (RNNs). The network outputs the relative 6-DOF camera poses for a sequence, and implicitly learns the absolute scale without the need for camera intrinsics. The entire trajectory is then integrated without any post-calibration. We evaluate the proposed method on the KITTI dataset and compare it with traditional and other deep learning approaches in the literature.

scholarly journals Image Compression Based on Deep Learning: A Review

2021 ◽  
pp. 62-76
Author(s):  
Hajar Maseeh Yasin ◽  
Adnan Mohsin Abdulazeez
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Image Compression ◽  
Recurrent Neural Networks ◽  
Deep Neural Networks ◽  
Review Paper ◽  
High Accuracy ◽  
Machine Learning Methods ◽  
Digital Era ◽  
Different Types

Image compression is an essential technology for encoding and improving various forms of images in the digital era. The inventors have extended the principle of deep learning to the different states of neural networks as one of the most exciting machine learning methods to show that it is the most versatile way to analyze, classify, and compress images. Many neural networks are required for image compressions, such as deep neural networks, artificial neural networks, recurrent neural networks, and convolution neural networks. Therefore, this review paper discussed how to apply the rule of deep learning to various neural networks to obtain better compression in the image with high accuracy and minimize loss and superior visibility of the image. Therefore, deep learning and its application to different types of images in a justified manner with distinct analysis to obtain these things need deep learning.

scholarly journals Deep Learning for the classification of quenched jets

2021 ◽  
Vol 2021 (11) ◽  
Author(s):  
L. Apolinário ◽  
N. F. Castro ◽  
M. Crispim Romão ◽  
J. G. Milhano ◽  
R. Pedro ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Quark Gluon Plasma ◽  
Recurrent Neural Networks ◽  
Heavy Ions ◽  
Deep Neural Networks ◽  
Gluon Plasma ◽  
Jet Quenching ◽  
Learning Techniques

Abstract An important aspect of the study of Quark-Gluon Plasma (QGP) in ultrarelativistic collisions of heavy ions is the ability to identify, in experimental data, a subset of the jets that were strongly modified by the interaction with the QGP. In this work, we propose studying Deep Learning techniques for this purpose. Samples of Z+jet events were simulated in vacuum (pp collisions) and medium (PbPb collisions) and used to train Deep Neural Networks with the objective of discriminating between medium- and vacuum-like jets within the medium (PbPb) sample. Dedicated Convolutional Neural Networks, Dense Neural Networks and Recurrent Neural Networks were developed and trained, and their performance was studied. Our results show the potential of these techniques for the identification of jet quenching effects induced by the presence of the QGP.

scholarly journals Deep Sparse Learning for Automatic Modulation Classification Using Recurrent Neural Networks

Sensors ◽  
2021 ◽  
Vol 21 (19) ◽  
pp. 6410
Author(s):  
Ke Zang ◽  
Wenqi Wu ◽  
Wei Luo
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Deep Neural Networks ◽  
Learning Algorithm ◽  
Model Performance ◽  
Sparse Learning ◽  
Modulation Classification ◽  
Learning Models ◽  
Automatic Modulation Classification

Deep learning models, especially recurrent neural networks (RNNs), have been successfully applied to automatic modulation classification (AMC) problems recently. However, deep neural networks are usually overparameterized, i.e., most of the connections between neurons are redundant. The large model size hinders the deployment of deep neural networks in applications such as Internet-of-Things (IoT) networks. Therefore, reducing parameters without compromising the network performance via sparse learning is often desirable since it can alleviates the computational and storage burdens of deep learning models. In this paper, we propose a sparse learning algorithm that can directly train a sparsely connected neural network based on the statistics of weight magnitude and gradient momentum. We first used the MNIST and CIFAR10 datasets to demonstrate the effectiveness of this method. Subsequently, we applied it to RNNs with different pruning strategies on recurrent and non-recurrent connections for AMC problems. Experimental results demonstrated that the proposed method can effectively reduce the parameters of the neural networks while maintaining model performance. Moreover, we show that appropriate sparsity can further improve network generalization ability.

End-to-end, sequence-to-sequence probabilistic visual odometry through deep neural networks

2017 ◽  
Vol 37 (4-5) ◽  
pp. 513-542 ◽  
Author(s):  
Sen Wang ◽  
Ronald Clark ◽  
Hongkai Wen ◽  
Niki Trigoni
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Visual Odometry ◽  
Feature Representation ◽  
Geometric Information ◽  
Geometric Problem ◽  
End To End

This paper studies visual odometry (VO) from the perspective of deep learning. After tremendous efforts in the robotics and computer vision communities over the past few decades, state-of-the-art VO algorithms have demonstrated incredible performance. However, since the VO problem is typically formulated as a pure geometric problem, one of the key features still missing from current VO systems is the capability to automatically gain knowledge and improve performance through learning. In this paper, we investigate whether deep neural networks can be effective and beneficial to the VO problem. An end-to-end, sequence-to-sequence probabilistic visual odometry (ESP-VO) framework is proposed for the monocular VO based on deep recurrent convolutional neural networks. It is trained and deployed in an end-to-end manner, that is, directly inferring poses and uncertainties from a sequence of raw images (video) without adopting any modules from the conventional VO pipeline. It can not only automatically learn effective feature representation encapsulating geometric information through convolutional neural networks, but also implicitly model sequential dynamics and relation for VO using deep recurrent neural networks. Uncertainty is also derived along with the VO estimation without introducing much extra computation. Extensive experiments on several datasets representing driving, flying and walking scenarios show competitive performance of the proposed ESP-VO to the state-of-the-art methods, demonstrating a promising potential of the deep learning technique for VO and verifying that it can be a viable complement to current VO systems.

Recent Progresses of Deep Learning in Drug Discovery

2021 ◽  
Vol 27 ◽  
Author(s):  
Feng Wang ◽  
XiaoMin Diao ◽  
Shan Chang ◽  
Lei Xu
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Drug Discovery ◽  
Deep Neural Networks ◽  
De Novo ◽  
De Novo Design ◽  
Learning Approaches ◽  
Property Prediction ◽  
Design Property ◽  
Future Direction

: Deep learning, an emerging field of artificial intelligence based on neural network in machine learning, has been applied in various fields and is highly valued. Herein we mainly review several mainstream architectures in deep learning, including deep neural networks, convolutional neural networks and recurrent neural networks in the field of drug discovery. The applications of several architectures in molecular de novo design, property prediction, biomedical imaging and synthetic planning have also been explored. We also discuss the future direction of the deep learning approaches and the main challenges we need to address.

New Trends of Deep Learning in Clinical Cardiology

2020 ◽  
Vol 15 ◽  
Author(s):  
Zichao Chen ◽  
Qi Zhou ◽  
Aziz Khan Turlandi ◽  
Jordan Jill ◽  
Rixin Xiong ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Deep Neural Networks ◽  
Disease Symptoms ◽  
Clinical Cardiology ◽  
Pros And Cons ◽  
Ultrasonic Analysis ◽  
Multi Level

: Deep Learning (DL) is a novel type of Machine Learning (ML) model. It is showing increasing promise in medicine, study and treatment of diseases and injuries, to assist in data classification, novel disease symptoms and complicated decision making. Deep learning is the form of machine learning typically implemented via multi-level neural networks. This work discuss the pros and cons of using DL in clinical cardiology that also apply in medicine in general, while proposing certain directions as the more viable for clinical use. DL models called deep neural networks (DNNs), recurrent neural networks (RNNs) and convolutional neural networks (CNNs) have been applied to arrhythmias, electrocardiogram, ultrasonic analysis, genomes and endomyocardial biopsy. Convincingly, the rusults of trained model are good, demonstrating the power of more expressive deep learning algorithms for clinical predictive modeling. In the future, more novel deep learning methods are expected to make a difference in the field of clinical medicines.

scholarly journals Examining Attention Mechanisms in Deep Learning Models for Sentiment Analysis

2021 ◽  
Vol 11 (9) ◽  
pp. 3883
Author(s):  
Spyridon Kardakis ◽  
Isidoros Perikos ◽  
Foteini Grivokostopoulou ◽  
Ioannis Hatzilygeroudis
Keyword(s):  
Neural Networks ◽  
Experimental Study ◽  
Deep Learning ◽  
Comparative Analysis ◽  
Sentiment Analysis ◽  
Recurrent Neural Networks ◽  
Deep Neural Networks ◽  
Training Methods ◽  
Learning Models ◽  
Neural Models

Attention-based methods for deep neural networks constitute a technique that has attracted increased interest in recent years. Attention mechanisms can focus on important parts of a sequence and, as a result, enhance the performance of neural networks in a variety of tasks, including sentiment analysis, emotion recognition, machine translation and speech recognition. In this work, we study attention-based models built on recurrent neural networks (RNNs) and examine their performance in various contexts of sentiment analysis. Self-attention, global-attention and hierarchical-attention methods are examined under various deep neural models, training methods and hyperparameters. Even though attention mechanisms are a powerful recent concept in the field of deep learning, their exact effectiveness in sentiment analysis is yet to be thoroughly assessed. A comparative analysis is performed in a text sentiment classification task where baseline models are compared with and without the use of attention for every experiment. The experimental study additionally examines the proposed models’ ability in recognizing opinions and emotions in movie reviews. The results indicate that attention-based models lead to great improvements in the performance of deep neural models showcasing up to a 3.5% improvement in their accuracy.

scholarly journals Deep Learning: Implications for Human Learning and Memory

2020 ◽  
Author(s):  
James Lloyd McClelland ◽  
Matthew M. Botvinick
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Learning And Memory ◽  
Deep Neural Networks ◽  
Human Learning ◽  
Machine Intelligence ◽  
Learning Approaches ◽  
Human Capabilities ◽  
Wide Range ◽  
Learning Research

Recent years have seen an explosion of interest in deep learning and deep neural networks. Deep learning lies at the heart of unprecedented feats of machine intelligence as well as software people use every day. Systems built on deep learning have surpassed human capabilities in complex strategy games like go and chess, and we use them for speech recognition, image captioning, and a wide range of other applications. A consideration of deep learning is crucial for a Handbook of Human Memory, since human brains are deep neural networks, and an understanding of artificial deep learning systems may contribute to our understanding of how humans and animals learn and remember. Deep neural networks are complex, structured systems that process information in a parallel, distributed, and context sensitive fashion, and deep learning is the effort to use these systems to acquire capabilities we associate with intelligence through an experience dependent learning process. Within the field of Artificial Intelligence, work in deep learning is typically directed toward the goal of creating and understanding intelligence using all available tools and resources without consideration of their biological plausibility. Many of the ideas, however, at the heart of deep learning draw their inspiration from the brain and from characteristics of human intelligence we believe are best captured by these brain-inspired systems (Rumelhart, McClelland, and the PDP Research Group, 1986). Furthermore, ideas emerging from deep learning research can help inform us about memory and learning in humans and animals. Thus, deep learning research can be seen as fertile ground for engagement between researchers who work on related issues with implications for both biological and machine intelligence.We begin by introducing the basic constructs employed in deep learning and then consider several of the widely used learning paradigms and architectures used in these systems. We then turn to a consideration of how the constructs of deep learning relate to traditional constructs in the psychological literature on learning and memory. Next, we consider recent developments in the field of reinforcement learning that have broad implications for human learning and memory. We conclude with a consideration of areas where human capabilities still far exceed current deep learning approaches, and describe possible future directions toward understanding how these abilities might best be captured.

Levenshtein Augmentation Improves Performance of SMILES Based Deep-Learning Synthesis Prediction

2020 ◽  
Author(s):  
Dean Sumner ◽  
Jiazhen He ◽  
Amol Thakkar ◽  
Ola Engkvist ◽  
Esben Jannik Bjerrum
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Sequence Similarity ◽  
Learning Models ◽  
Underlying Network

<p>SMILES randomization, a form of data augmentation, has previously been shown to increase the performance of deep learning models compared to non-augmented baselines. Here, we propose a novel data augmentation method we call “Levenshtein augmentation” which considers local SMILES sub-sequence similarity between reactants and their respective products when creating training pairs. The performance of Levenshtein augmentation was tested using two state of the art models - transformer and sequence-to-sequence based recurrent neural networks with attention. Levenshtein augmentation demonstrated an increase performance over non-augmented, and conventionally SMILES randomization augmented data when used for training of baseline models. Furthermore, Levenshtein augmentation seemingly results in what we define as <i>attentional gain </i>– an enhancement in the pattern recognition capabilities of the underlying network to molecular motifs.</p>

scholarly journals Deep convolutional neural networks for cardiovascular vulnerable plaque detection

2019 ◽  
Vol 277 ◽  
pp. 02024 ◽  
Author(s):  
Lincan Li ◽  
Tong Jia ◽  
Tianqi Meng ◽  
Yizhe Liu
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Vulnerable Plaque ◽  
Recall Rate ◽  
Superior Performance ◽  
Learning Approaches ◽  
Deep Convolutional Neural Networks ◽  
Vulnerable Plaques ◽  
Plaque Detection

In this paper, an accurate two-stage deep learning method is proposed to detect vulnerable plaques in ultrasonic images of cardiovascular. Firstly, a Fully Convonutional Neural Network (FCN) named U-Net is used to segment the original Intravascular Optical Coherence Tomography (IVOCT) cardiovascular images. We experiment on different threshold values to find the best threshold for removing noise and background in the original images. Secondly, a modified Faster RCNN is adopted to do precise detection. The modified Faster R-CNN utilize six-scale anchors (122,162,322,642,1282,2562) instead of the conventional one scale or three scale approaches. First, we present three problems in cardiovascular vulnerable plaque diagnosis, then we demonstrate how our method solve these problems. The proposed method in this paper apply deep convolutional neural networks to the whole diagnostic procedure. Test results show the Recall rate, Precision rate, IoU (Intersection-over-Union) rate and Total score are 0.94, 0.885, 0.913 and 0.913 respectively, higher than the 1st team of CCCV2017 Cardiovascular OCT Vulnerable Plaque Detection Challenge. AP of the designed Faster RCNN is 83.4%, higher than conventional approaches which use one-scale or three-scale anchors. These results demonstrate the superior performance of our proposed method and the power of deep learning approaches in diagnose cardiovascular vulnerable plaques.

Sign in / Sign up

Export Citation Format

Share Document