A Novel Approach for Simplifying Neural Networks by Identifying Decoupling Inputs

2004 ◽  
pp. 754-765
Author(s):  
Sanggil Kang ◽  
Wonil Kim
Keyword(s):  
Neural Networks ◽  
Novel Approach

A Novel Approach for Image Super Resolution Problems with Convolution Neural Networks

2017 ◽  
Vol 6 (4) ◽  
pp. 15
Author(s):  
JANARDHAN CHIDADALA ◽  
RAMANAIAH K.V. ◽  
BABULU K ◽  
◽  
◽  
...  
Keyword(s):  
Neural Networks ◽  
Super Resolution ◽  
Convolution Neural Networks ◽  
Novel Approach ◽  
Image Super Resolution

scholarly journals Autonomous flight cycles and extreme landings of airliners beyond the current limits and capabilities using artificial neural networks

2021 ◽  
Author(s):  
Haitham Baomar ◽  
Peter J. Bentley
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Weather Conditions ◽  
Extreme Weather ◽  
Training Data ◽  
Aviation Industry ◽  
Control Models ◽  
Novel Approach ◽  
Network Modules ◽  
Artificial Neural

AbstractWe describe the Intelligent Autopilot System (IAS), a fully autonomous autopilot capable of piloting large jets such as airliners by learning from experienced human pilots using Artificial Neural Networks. The IAS is capable of autonomously executing the required piloting tasks and handling the different flight phases to fly an aircraft from one airport to another including takeoff, climb, cruise, navigate, descent, approach, and land in simulation. In addition, the IAS is capable of autonomously landing large jets in the presence of extreme weather conditions including severe crosswind, gust, wind shear, and turbulence. The IAS is a potential solution to the limitations and robustness problems of modern autopilots such as the inability to execute complete flights, the inability to handle extreme weather conditions especially during approach and landing where the aircraft’s speed is relatively low, and the uncertainty factor is high, and the pilots shortage problem compared to the increasing aircraft demand. In this paper, we present the work done by collaborating with the aviation industry to provide training data for the IAS to learn from. The training data is used by Artificial Neural Networks to generate control models automatically. The control models imitate the skills of the human pilot when executing all the piloting tasks required to pilot an aircraft between two airports. In addition, we introduce new ANNs trained to control the aircraft’s elevators, elevators’ trim, throttle, flaps, and new ailerons and rudder ANNs to counter the effects of extreme weather conditions and land safely. Experiments show that small datasets containing single demonstrations are sufficient to train the IAS and achieve excellent performance by using clearly separable and traceable neural network modules which eliminate the black-box problem of large Artificial Intelligence methods such as Deep Learning. In addition, experiments show that the IAS can handle landing in extreme weather conditions beyond the capabilities of modern autopilots and even experienced human pilots. The proposed IAS is a novel approach towards achieving full control autonomy of large jets using ANN models that match the skills and abilities of experienced human pilots and beyond.

Mining discriminative patches for script identification in natural scene images

2021 ◽  
Vol 40 (1) ◽  
pp. 551-563
Author(s):  
Liqiong Lu ◽  
Dong Wu ◽  
Ziwei Tang ◽  
Yaohua Yi ◽  
Faliang Huang
Keyword(s):  
Neural Networks ◽  
Experimental Results ◽  
The Other ◽  
Natural Scene ◽  
Fixed Size ◽  
Script Identification ◽  
Aspect Ratios ◽  
Novel Approach ◽  
Public Datasets ◽  
Natural Scene Images

This paper focuses on script identification in natural scene images. Traditional CNNs (Convolution Neural Networks) cannot solve this problem perfectly for two reasons: one is the arbitrary aspect ratios of scene images which bring much difficulty to traditional CNNs with a fixed size image as the input. And the other is that some scripts with minor differences are easily confused because they share a subset of characters with the same shapes. We propose a novel approach combing Score CNN, Attention CNN and patches. Attention CNN is utilized to determine whether a patch is a discriminative patch and calculate the contribution weight of the discriminative patch to script identification of the whole image. Score CNN uses a discriminative patch as input and predict the score of each script type. Firstly patches with the same size are extracted from the scene images. Secondly these patches are used as inputs to Score CNN and Attention CNN to train two patch-level classifiers. Finally, the results of multiple discriminative patches extracted from the same image via the above two classifiers are fused to obtain the script type of this image. Using patches with the same size as inputs to CNN can avoid the problems caused by arbitrary aspect ratios of scene images. The trained classifiers can mine discriminative patches to accurately identify some confusing scripts. The experimental results show the good performance of our approach on four public datasets.

scholarly journals Explaining Neural Networks Using Attentive Knowledge Distillation

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1280
Author(s):  
Hyeonseok Lee ◽  
Sungchan Kim
Keyword(s):  
Neural Networks ◽  
Model Prediction ◽  
Saliency Map ◽  
Model Parameters ◽  
Learning Capability ◽  
Fine Grained ◽  
Network Layers ◽  
Saliency Maps ◽  
Novel Approach ◽  
Knowledge Distillation

Explaining the prediction of deep neural networks makes the networks more understandable and trusted, leading to their use in various mission critical tasks. Recent progress in the learning capability of networks has primarily been due to the enormous number of model parameters, so that it is usually hard to interpret their operations, as opposed to classical white-box models. For this purpose, generating saliency maps is a popular approach to identify the important input features used for the model prediction. Existing explanation methods typically only use the output of the last convolution layer of the model to generate a saliency map, lacking the information included in intermediate layers. Thus, the corresponding explanations are coarse and result in limited accuracy. Although the accuracy can be improved by iteratively developing a saliency map, this is too time-consuming and is thus impractical. To address these problems, we proposed a novel approach to explain the model prediction by developing an attentive surrogate network using the knowledge distillation. The surrogate network aims to generate a fine-grained saliency map corresponding to the model prediction using meaningful regional information presented over all network layers. Experiments demonstrated that the saliency maps are the result of spatially attentive features learned from the distillation. Thus, they are useful for fine-grained classification tasks. Moreover, the proposed method runs at the rate of 24.3 frames per second, which is much faster than the existing methods by orders of magnitude.

Sign in / Sign up

Export Citation Format

Share Document