scholarly journals Ego-Motion Estimation Using Recurrent Convolutional Neural Networks through Optical Flow Learning

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 222
Author(s):  
Baigan Zhao ◽  
Yingping Huang ◽  
Hongjian Wei ◽  
Xing Hu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Motion Estimation ◽  
Optical Flow ◽  
Feature Representation ◽  
Sequential Learning ◽  
Navigation Systems ◽  
Motion State ◽  
Training Schemes ◽  
Sequential Images

Visual odometry (VO) refers to incremental estimation of the motion state of an agent (e.g., vehicle and robot) by using image information, and is a key component of modern localization and navigation systems. Addressing the monocular VO problem, this paper presents a novel end-to-end network for estimation of camera ego-motion. The network learns the latent subspace of optical flow (OF) and models sequential dynamics so that the motion estimation is constrained by the relations between sequential images. We compute the OF field of consecutive images and extract the latent OF representation in a self-encoding manner. A Recurrent Neural Network is then followed to examine the OF changes, i.e., to conduct sequential learning. The extracted sequential OF subspace is used to compute the regression of the 6-dimensional pose vector. We derive three models with different network structures and different training schemes: LS-CNN-VO, LS-AE-VO, and LS-RCNN-VO. Particularly, we separately train the encoder in an unsupervised manner. By this means, we avoid non-convergence during the training of the whole network and allow more generalized and effective feature representation. Substantial experiments have been conducted on KITTI and Malaga datasets, and the results demonstrate that our LS-RCNN-VO outperforms the existing learning-based VO approaches.

Local Learning Algorithms for Sequential Tasks in Neural Networks

1998 ◽  
Vol 2 (6) ◽  
pp. 221-227 ◽  
Author(s):  
Anthony Robins ◽  
◽  
Marcus Frean ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Learning Algorithms ◽  
Learning Task ◽  
Sequential Learning ◽  
Local Learning ◽  
Neural Network Learning ◽  
Network Learning ◽  
Sequential Task ◽  
Global And Local

In this paper, we explore the concept of sequential learning and the efficacy of global and local neural network learning algorithms on a sequential learning task. Pseudorehearsal, a method developed by Robins19) to solve the catastrophic forgetting problem which arises from the excessive plasticity of neural networks, is significantly more effective than other local learning algorithms for the sequential task. We further consider the concept of local learning and suggest that pseudorehearsal is so effective because it works directly at the level of the learned function, and not indirectly on the representation of the function within the network. We also briefly explore the effect of local learning on generalization within the task.

scholarly journals All-Chalcogenide Programmable All-Optical Deep Neural Networks

2021 ◽  
Author(s):  
Ting Yu ◽  
Xiaoxuan Ma ◽  
Ernest Pastor ◽  
Jonathan George ◽  
Simon Wall ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Autonomous Vehicles ◽  
Structural Phase ◽  
Activation Function ◽  
Navigation Systems ◽  
Optical Neural Networks ◽  
Electro Optic ◽  
All Optical ◽  
On Chip

Abstract Deeplearning algorithms are revolutionising many aspects of modern life. Typically, they are implemented in CMOS-based hardware with severely limited memory access times and inefficient data-routing. All-optical neural networks without any electro-optic conversions could alleviate these shortcomings. However, an all-optical nonlinear activation function, which is a vital building block for optical neural networks, needs to be developed efficiently on-chip. Here, we introduce and demonstrate both optical synapse weighting and all-optical nonlinear thresholding using two different effects in one single chalcogenide material. We show how the structural phase transitions in a wide-bandgap phase-change material enables storing the neural network weights via non-volatile photonic memory, whilst resonant bond destabilisation is used as a nonlinear activation threshold without changing the material. These two different transitions within chalcogenides enable programmable neural networks with near-zero static power consumption once trained, in addition to picosecond delays performing inference tasks not limited by wire charging that limit electrical circuits; for instance, we show that nanosecond-order weight programming and near-instantaneous weight updates enable accurate inference tasks within 20 picoseconds in a 3-layer all-optical neural network. Optical neural networks that bypass electro-optic conversion altogether hold promise for network-edge machine learning applications where decision-making in real-time are critical, such as for autonomous vehicles or navigation systems such as signal pre-processing of LIDAR systems.

scholarly journals Sparsity-Inducing Binarized Neural Networks

2020 ◽  
Vol 34 (07) ◽  
pp. 12192-12199 ◽  
Author(s):  
Peisong Wang ◽  
Xiangyu He ◽  
Gang Li ◽  
Tianli Zhao ◽  
Jian Cheng
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
High Efficiency ◽  
State Of The Art ◽  
Feature Representation ◽  
Binary Representation ◽  
Performance Gap ◽  
Sign Function ◽  
Current State ◽  
The Arts

Binarization of feature representation is critical for Binarized Neural Networks (BNNs). Currently, sign function is the commonly used method for feature binarization. Although it works well on small datasets, the performance on ImageNet remains unsatisfied. Previous methods mainly focus on minimizing quantization error, improving the training strategies and decomposing each convolution layer into several binary convolution modules. However, whether sign is the only option for binarization has been largely overlooked. In this work, we propose the Sparsity-inducing Binarized Neural Network (Si-BNN), to quantize the activations to be either 0 or +1, which introduces sparsity into binary representation. We further introduce trainable thresholds into the backward function of binarization to guide the gradient propagation. Our method dramatically outperforms current state-of-the-arts, lowering the performance gap between full-precision networks and BNNs on mainstream architectures, achieving the new state-of-the-art on binarized AlexNet (Top-1 50.5%), ResNet-18 (Top-1 59.7%), and VGG-Net (Top-1 63.2%). At inference time, Si-BNN still enjoys the high efficiency of exclusive-not-or (xnor) operations.

scholarly journals High-Resolution Radar Echo Prediction with Machine Learning

2021 ◽  
Author(s):  
Matej Choma ◽  
Jakub Bartel ◽  
Petr Šimánek ◽  
Vojtěch Rybář
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Optical Flow ◽  
Recurrent Neural Network ◽  
Short Term Memory ◽  
Mean Squared Error ◽  
Geographical Area ◽  
Weather Radar ◽  
Radar Echo ◽  
Data Driven Approach

<p>The standard for weather radar nowcasting in the Central Europe region is the COTREC extrapolation method. We propose a recurrent neural network based on the PredRNN architecture, which outperforms the COTREC 60 minutes predictions by a significant margin.</p><p>Nowcasting, as a complement to numerical weather predictions, is a well-known concept. However, the increasing speed of information flow in our society today creates an opportunity for its effective implementation. Methods currently used for these predictions are primarily based on the optical flow and are struggling in the prediction of the development of the echo shape and intensity.</p><p>In this work, we are benefiting from a data-driven approach and building on the advances in the capabilities of neural networks for computer vision. We define the prediction task as an extrapolation of sequences of the latest weather radar echo measurements. To capture the spatiotemporal behaviour of rainfall and storms correctly, we propose the use of a recurrent neural network using a combination of long short term memory (LSTM) techniques with convolutional neural networks (CNN). Our approach is applicable to any geographical area, radar network resolution and refresh rate.</p><p>We conducted the experiments comparing predictions for 10 to 60 minutes into the future with the Critical Success Index, which evaluates the spatial accuracy of the predicted echo and Mean Squared Error. Our neural network model has been trained with three years of rainfall data captured by weather radars over the Czech Republic. Results for our bordered testing domain show that our method achieves comparable or better scores than both COTREC and optical flow extrapolation methods available in the open-source pySTEPS and rainymotion libraries.</p><p>With our work, we aim to contribute to the nowcasting research in general and create another source of short-time predictions for both experts and the general public.</p>

scholarly journals Learning to Localise Automated Vehicles in Challenging Environments Using Inertial Navigation Systems (INS)

2021 ◽  
Vol 11 (3) ◽  
pp. 1270
Author(s):  
Uche Onyekpe ◽  
Vasile Palade ◽  
Stratis Kanarachos
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Autonomous Vehicles ◽  
Short Term Memory ◽  
Inertial Navigation ◽  
Satellite System ◽  
Navigation Systems ◽  
Inertial Navigation Systems ◽  
Displacement Estimation ◽  
Global Navigation Satellite

An approach based on Artificial Neural Networks is proposed in this paper to improve the localisation accuracy of Inertial Navigation Systems (INS)/Global Navigation Satellite System (GNSS) based aided navigation during the absence of GNSS signals. The INS can be used to continuously position autonomous vehicles during GNSS signal losses around urban canyons, bridges, tunnels and trees, however, it suffers from unbounded exponential error drifts cascaded over time during the multiple integrations of the accelerometer and gyroscope measurements to position. More so, the error drift is characterised by a pattern dependent on time. This paper proposes several efficient neural network-based solutions to estimate the error drifts using Recurrent Neural Networks, such as the Input Delay Neural Network (IDNN), Long Short-Term Memory (LSTM), Vanilla Recurrent Neural Network (vRNN), and Gated Recurrent Unit (GRU). In contrast to previous papers published in literature, which focused on travel routes that do not take complex driving scenarios into consideration, this paper investigates the performance of the proposed methods on challenging scenarios, such as hard brake, roundabouts, sharp cornering, successive left and right turns and quick changes in vehicular acceleration across numerous test sequences. The results obtained show that the Neural Network-based approaches are able to provide up to 89.55% improvement on the INS displacement estimation and 93.35% on the INS orientation rate estimation.

SCORING MODELING BASED ON NEURAL NETWORKS FOR DETERMINING A BANK BORROWER'S RATING

2020 ◽  
Vol 2020 (10) ◽  
pp. 54-62
Author(s):  
Oleksii VASYLIEV ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Statistical Data ◽  
Activation Function ◽  
Decision Making Process ◽  
Neural Network Architecture ◽  
Acceptable Accuracy ◽  
The Neural Network ◽  
Sigmoid Activation Function

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

Color Space Transformation using Neural Networks

2019 ◽  
Vol 2019 (1) ◽  
pp. 153-158
Author(s):  
Lindsay MacDonald
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Color Space ◽  
Reflectance Spectra ◽  
Network Architectures ◽  
Color Spaces ◽  
Natural Materials ◽  
Space Transformation ◽  
Color Space Transformation

We investigated how well a multilayer neural network could implement the mapping between two trichromatic color spaces, specifically from camera R,G,B to tristimulus X,Y,Z. For training the network, a set of 800,000 synthetic reflectance spectra was generated. For testing the network, a set of 8,714 real reflectance spectra was collated from instrumental measurements on textiles, paints and natural materials. Various network architectures were tested, with both linear and sigmoidal activations. Results show that over 85% of all test samples had color errors of less than 1.0 ΔE2000 units, much more accurate than could be achieved by regression.

Estimating Pigment Concentrations from Spectral Images Using an Encoder‐Decoder Neural Network

2020 ◽  
Vol 64 (3) ◽  
pp. 30502-1-30502-15
Author(s):  
Kensuke Fukumoto ◽  
Norimichi Tsumura ◽  
Roy Berns
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Absorption Coefficient ◽  
Spectral Data ◽  
High Accuracy ◽  
Pigment Concentration ◽  
Scattering Coefficient ◽  
A Value ◽  
Input And Output ◽  
Pigment Concentrations

Abstract A method is proposed to estimate the concentration of pigments mixed in a painting, using the encoder‐decoder model of neural networks. The model is trained to output a value that is the same as its input, and its middle output extracts a certain feature as compressed information about the input. In this instance, the input and output are spectral data of a painting. The model is trained with pigment concentration as the middle output. A dataset containing the scattering coefficient and absorption coefficient of each of 19 pigments was used. The Kubelka‐Munk theory was applied to the coefficients to obtain many patterns of synthetic spectral data, which were used for training. The proposed method was tested using spectral images of 33 paintings, which showed that the method estimates, with high accuracy, the concentrations that have a similar spectrum of the target pigments.

Neural Network Techniques for Time Series Prediction: A Review

2019 ◽  
Vol 3 (3) ◽  
Author(s):  
Muhammad Faheem Mushtaq ◽  
Urooj Akram ◽  
Muhammad Aamir ◽  
Haseeb Ali ◽  
Muhammad Zulqarnain
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Series ◽  
Time Series Data ◽  
Weather Prediction ◽  
Time Series Prediction ◽  
Series Data ◽  
Prediction Problem ◽  
Neural Network Models ◽  
Physical Time

It is important to predict a time series because many problems that are related to prediction such as health prediction problem, climate change prediction problem and weather prediction problem include a time component. To solve the time series prediction problem various techniques have been developed over many years to enhance the accuracy of forecasting. This paper presents a review of the prediction of physical time series applications using the neural network models. Neural Networks (NN) have appeared as an effective tool for forecasting of time series.  Moreover, to resolve the problems related to time series data, there is a need of network with single layer trainable weights that is Higher Order Neural Network (HONN) which can perform nonlinearity mapping of input-output. So, the developers are focusing on HONN that has been recently considered to develop the input representation spaces broadly. The HONN model has the ability of functional mapping which determined through some time series problems and it shows the more benefits as compared to conventional Artificial Neural Networks (ANN). The goal of this research is to present the reader awareness about HONN for physical time series prediction, to highlight some benefits and challenges using HONN.

Sign in / Sign up

Export Citation Format

Share Document