Recent progresses of neural network unsupervised learning: II Real world applications

1999 ◽  
Author(s):  
Harold H. Szu
Keyword(s):  
Neural Network ◽  
Unsupervised Learning ◽  
Real World ◽  
Real World Applications

SpeeChin

2021 ◽  
Vol 5 (4) ◽  
pp. 1-23
Author(s):  
Ruidong Zhang ◽  
Mingyang Chen ◽  
Benjamin Steeper ◽  
Yaxuan Li ◽  
Zihan Yan ◽  
...  
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Real World ◽  
User Study ◽  
Imaging System ◽  
User Studies ◽  
Ir Imaging ◽  
Real World Applications ◽  
Challenges And Opportunities ◽  
Silent Speech

This paper presents SpeeChin, a smart necklace that can recognize 54 English and 44 Chinese silent speech commands. A customized infrared (IR) imaging system is mounted on a necklace to capture images of the neck and face from under the chin. These images are first pre-processed and then deep learned by an end-to-end deep convolutional-recurrent-neural-network (CRNN) model to infer different silent speech commands. A user study with 20 participants (10 participants for each language) showed that SpeeChin could recognize 54 English and 44 Chinese silent speech commands with average cross-session accuracies of 90.5% and 91.6%, respectively. To further investigate the potential of SpeeChin in recognizing other silent speech commands, we conducted another study with 10 participants distinguishing between 72 one-syllable nonwords. Based on the results from the user studies, we further discuss the challenges and opportunities of deploying SpeeChin in real-world applications.

scholarly journals Model Fast Tansfer Learning pada Jaringan Syaraf Tiruan Konvolusional untuk Klasifikasi Gender Berdasarkan Citra Wajah

2019 ◽  
Vol 18 (2) ◽  
pp. 211-221
Author(s):  
Bambang Krismono Triwijoyo
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Real World ◽  
Face Image ◽  
Gender Classification ◽  
Learning Method ◽  
Image Transfer ◽  
Real World Applications ◽  
The Face

The face is a challenging object to be recognized and analyzed automatically by a computer in many interesting applications such as facial gender classification. The large visual variations of faces, such as occlusions, pose changes, and extreme lightings, impose great challenge for these tasks in real world applications. This paper explained the fast transfer learning representations through use of convolutional neural network (CNN) model for gender classification from face image. Transfer learning aims to provide a framework to utilize previously-acquired knowledge to solve new but similar problems much more quickly and effectively. The experimental results showed that the transfer learning method have faster and higher accuracy than CNN network without transfer learning.

Q-Learning in Continuous State-Action Space with Noisy and Redundant Inputs by Using a Selective Desensitization Neural Network

2015 ◽  
Vol 19 (6) ◽  
pp. 825-832 ◽  
Author(s):  
Takaaki Kobayashi ◽  
◽  
Takeshi Shibuya ◽  
Masahiko Morita
Keyword(s):  
Neural Network ◽  
Real World ◽  
Value Function ◽  
Action Space ◽  
Sensor Noise ◽  
Q Learning ◽  
State Action ◽  
Continuous State ◽  
Real World Applications ◽  
Function Approximator

When applying reinforcement learning (RL) algorithms such as Q-learning to real-world applications, we must consider the influence of sensor noise. The simplest way to reduce such noise influence is to additionally use other types of sensors, but this may require more state space -- and probably increase redundancy. Conventional value-function approximators used to RL in continuous state-action space do not deal appropriately with such situations. The selective desensitization neural network (SDNN) has high generalization ability and robustness against noise and redundant input. We therefore propose an SDNN-based value-function approximator for Q-learning in continuous state-action space, and evaluate its performance in terms of robustness against redundant input and sensor noise. Results show that our proposal is strongly robust against noise and redundant input and enables the agent to take better actions by using additional inputs without degrading learning efficiency. These properties are eminently advantageous in real-world applications such as in robotic systems.

scholarly journals ResGCN: attention-based deep residual modeling for anomaly detection on attributed networks

2021 ◽  
Author(s):  
Yulong Pei ◽  
Tianjin Huang ◽  
Werner van Ipenburg ◽  
Mykola Pechenizkiy
Keyword(s):  
Neural Network ◽  
Adverse Effect ◽  
Intrusion Detection ◽  
Anomaly Detection ◽  
Real World ◽  
Deep Neural Network ◽  
Convolutional Network ◽  
Real World Applications ◽  
Residual Graph ◽  
Attributed Networks

AbstractEffectively detecting anomalous nodes in attributed networks is crucial for the success of many real-world applications such as fraud and intrusion detection. Existing approaches have difficulties with three major issues: sparsity and nonlinearity capturing, residual modeling, and network smoothing. We propose Residual Graph Convolutional Network (ResGCN), an attention-based deep residual modeling approach that can tackle these issues: modeling the attributed networks with GCN allows to capture the sparsity and nonlinearity, utilizing a deep neural network allows direct residual ing from the input, and a residual-based attention mechanism reduces the adverse effect from anomalous nodes and prevents over-smoothing. Extensive experiments on several real-world attributed networks demonstrate the effectiveness of ResGCN in detecting anomalies.

scholarly journals Crowd Counting using Deep Recurrent Spatial-Aware Network

2018 ◽  
Author(s):  
Lingbo Liu ◽  
Hongjun Wang ◽  
Guanbin Li ◽  
Wanli Ouyang ◽  
Liang Lin
Keyword(s):  
Neural Network ◽  
Real World ◽  
Local Refinement ◽  
Crowd Counting ◽  
Multi Scale ◽  
Residual Learning ◽  
Crowd Density ◽  
Real World Applications ◽  
Refinement Process ◽  
Density Map

Crowd counting from unconstrained scene images is a crucial task in many real-world applications like urban surveillance and management, but it is greatly challenged by the camera’s perspective that causes huge appearance variations in people’s scales and rotations. Conventional methods address such challenges by resorting to fixed multi-scale architectures that are often unable to cover the largely varied scales while ignoring the rotation variations. In this paper, we propose a unified neural network framework, named Deep Recurrent Spatial-Aware Network, which adaptively addresses the two issues in a learnable spatial transform module with a region-wise refinement process. Specifically, our framework incorporates a Recurrent Spatial-Aware Refinement (RSAR) module iteratively conducting two components: i) a Spatial Transformer Network that dynamically locates an attentional region from the crowd density map and transforms it to the suitable scale and rotation for optimal crowd estimation; ii) a Local Refinement Network that refines the density map of the attended region with residual learning. Extensive experiments on four challenging benchmarks show the effectiveness of our approach. Specifically, comparing with the existing best-performing methods, we achieve an improvement of 12\% on the largest dataset WorldExpo’10 and 22.8\% on the most challenging dataset UCF\_CC\_50

Sign in / Sign up

Export Citation Format

Share Document