scholarly journals An LSTM Based Generative Adversarial Architecture for Robotic Calligraphy Learning System

2020 ◽  
Vol 12 (21) ◽  
pp. 9092
Author(s):  
Fei Chao ◽  
Gan Lin ◽  
Ling Zheng ◽  
Xiang Chang ◽  
Chih-Min Lin ◽  
...  
Keyword(s):  
Chinese Character ◽  
Learning System ◽  
Training Data ◽  
Gradient Algorithm ◽  
Learning Ability ◽  
Sequence Information ◽  
Generation Process ◽  
Training Set ◽  
Trajectory Point ◽  
Lstm Network

Robotic calligraphy is a very challenging task for the robotic manipulators, which can sustain industrial manufacturing. The active mechanism of writing robots require a large sized training set including sequence information of the writing trajectory. However, manual labelling work on those training data may cause the time wasting for researchers. This paper proposes a machine calligraphy learning system using a Long Short-Term Memory (LSTM) network and a generative adversarial network (GAN), which enables the robots to learn and generate the sequences of Chinese character stroke (i.e., writing trajectory). In order to reduce the size of the training set, a generative adversarial architecture combining an LSTM network and a discrimination network is established for a robotic manipulator to learn the Chinese calligraphy regarding its strokes. In particular, this learning system converts Chinese character stroke image into the trajectory sequences in the absence of the stroke trajectory writing sequence information. Due to its powerful learning ability in handling motion sequences, the LSTM network is used to explore the trajectory point writing sequences. Each generation process of the generative adversarial architecture contains a number of loops of LSTM. In each loop, the robot continues to write by following a new trajectory point, which is generated by LSTM according to the previously written strokes. The written stroke in an image format is taken as input to the next loop of the LSTM network until the complete stroke is finally written. Then, the final output of the LSTM network is evaluated by the discriminative network. In addition, a policy gradient algorithm based on reinforcement learning is employed to aid the robot to find the best policy. The experimental results show that the proposed learning system can effectively produce a variety of high-quality Chinese stroke writing.

Using problem-based learning in a Chinese character class design: A case study of Korean learners of Chinese

2019 ◽  
Vol 3 (2) ◽  
pp. 129-138
Author(s):  
Eun Young Jang ◽  
Heung Soo Park ◽  
Yeon Sil Jeong
Keyword(s):  
Character Education ◽  
Chinese Character ◽  
Chinese Language ◽  
Problem Based Learning ◽  
Learning Ability ◽  
Self Directed Learning ◽  
Learning Abilities ◽  
Learning Attitudes ◽  
Teaching Learning ◽  
Korean Learners

This study attempted to try out Chinese-character education centering on experience and learners away from existing lecture-centered, teacher-centered education. For this purpose, problem-based learning (PBL) was proposed as one of the Chinese-language ability-enhancement measures for Korean learners of the Chinese language, and in order to examine the effect, we attempt to use the PBL tasks in the ‘Chinese-language reading’ class at a university for basic Chinese-language learners and analyze the results. PBL is a teaching-learning method in which learners focus on learning by using problems. In this study, we attempted to use PBL for the group work format. In this way, we can confirm that the class using the PBL has many advantages, such as improving learning ability and problem-solving ability, and strengthening cooperation. In addition, it was found that PBL is worthwhile to try because it is effective in inducing learning motivation, improving attention and interest in Chinese-character learning, improving learning attitudes of learners, and developing self-directed learning abilities.

scholarly journals BLAINDER—A Blender AI Add-On for Generation of Semantically Labeled Depth-Sensing Data

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2144
Author(s):  
Stefan Reitmann ◽  
Lorenzo Neumann ◽  
Bernhard Jung
Keyword(s):  
Point Clouds ◽  
Training Data ◽  
Sensor Data ◽  
Generation Process ◽  
Data Generation ◽  
Depth Sensor ◽  
Depth Sensing ◽  
Depth Sensors ◽  
3D Point Clouds ◽  
Wide Range

Common Machine-Learning (ML) approaches for scene classification require a large amount of training data. However, for classification of depth sensor data, in contrast to image data, relatively few databases are publicly available and manual generation of semantically labeled 3D point clouds is an even more time-consuming task. To simplify the training data generation process for a wide range of domains, we have developed the BLAINDER add-on package for the open-source 3D modeling software Blender, which enables a largely automated generation of semantically annotated point-cloud data in virtual 3D environments. In this paper, we focus on classical depth-sensing techniques Light Detection and Ranging (LiDAR) and Sound Navigation and Ranging (Sonar). Within the BLAINDER add-on, different depth sensors can be loaded from presets, customized sensors can be implemented and different environmental conditions (e.g., influence of rain, dust) can be simulated. The semantically labeled data can be exported to various 2D and 3D formats and are thus optimized for different ML applications and visualizations. In addition, semantically labeled images can be exported using the rendering functionalities of Blender.

scholarly journals Effects of Training Set Size on Supervised Machine-Learning Land-Cover Classification of Large-Area High-Resolution Remotely Sensed Data

2021 ◽  
Vol 13 (3) ◽  
pp. 368
Author(s):  
Christopher A. Ramezan ◽  
Timothy A. Warner ◽  
Aaron E. Maxwell ◽  
Bradley S. Price
Keyword(s):  
Machine Learning ◽  
Sample Size ◽  
Remotely Sensed ◽  
Training Data ◽  
Supervised Machine Learning ◽  
Sample Sizes ◽  
Remotely Sensed Data ◽  
Large Area ◽  
Training Set ◽  
Set Size

The size of the training data set is a major determinant of classification accuracy. Nevertheless, the collection of a large training data set for supervised classifiers can be a challenge, especially for studies covering a large area, which may be typical of many real-world applied projects. This work investigates how variations in training set size, ranging from a large sample size (n = 10,000) to a very small sample size (n = 40), affect the performance of six supervised machine-learning algorithms applied to classify large-area high-spatial-resolution (HR) (1–5 m) remotely sensed data within the context of a geographic object-based image analysis (GEOBIA) approach. GEOBIA, in which adjacent similar pixels are grouped into image-objects that form the unit of the classification, offers the potential benefit of allowing multiple additional variables, such as measures of object geometry and texture, thus increasing the dimensionality of the classification input data. The six supervised machine-learning algorithms are support vector machines (SVM), random forests (RF), k-nearest neighbors (k-NN), single-layer perceptron neural networks (NEU), learning vector quantization (LVQ), and gradient-boosted trees (GBM). RF, the algorithm with the highest overall accuracy, was notable for its negligible decrease in overall accuracy, 1.0%, when training sample size decreased from 10,000 to 315 samples. GBM provided similar overall accuracy to RF; however, the algorithm was very expensive in terms of training time and computational resources, especially with large training sets. In contrast to RF and GBM, NEU, and SVM were particularly sensitive to decreasing sample size, with NEU classifications generally producing overall accuracies that were on average slightly higher than SVM classifications for larger sample sizes, but lower than SVM for the smallest sample sizes. NEU however required a longer processing time. The k-NN classifier saw less of a drop in overall accuracy than NEU and SVM as training set size decreased; however, the overall accuracies of k-NN were typically less than RF, NEU, and SVM classifiers. LVQ generally had the lowest overall accuracy of all six methods, but was relatively insensitive to sample size, down to the smallest sample sizes. Overall, due to its relatively high accuracy with small training sample sets, and minimal variations in overall accuracy between very large and small sample sets, as well as relatively short processing time, RF was a good classifier for large-area land-cover classifications of HR remotely sensed data, especially when training data are scarce. However, as performance of different supervised classifiers varies in response to training set size, investigating multiple classification algorithms is recommended to achieve optimal accuracy for a project.

New Supervised Learning Theory Applied to Cerebellar Modeling for Suppression of Variability of Saccade End Points

2013 ◽  
Vol 25 (6) ◽  
pp. 1440-1471 ◽  
Author(s):  
Masahiko Fujita
Keyword(s):  
Supervised Learning ◽  
Cerebellar Cortex ◽  
Learning Theory ◽  
Learning System ◽  
Learning Ability ◽  
Motor Center ◽  
End Points ◽  
Noise Effects ◽  
End Point ◽  
Control Scheme

A new supervised learning theory is proposed for a hierarchical neural network with a single hidden layer of threshold units, which can approximate any continuous transformation, and applied to a cerebellar function to suppress the end-point variability of saccades. In motor systems, feedback control can reduce noise effects if the noise is added in a pathway from a motor center to a peripheral effector; however, it cannot reduce noise effects if the noise is generated in the motor center itself: a new control scheme is necessary for such noise. The cerebellar cortex is well known as a supervised learning system, and a novel theory of cerebellar cortical function developed in this study can explain the capability of the cerebellum to feedforwardly reduce noise effects, such as end-point variability of saccades. This theory assumes that a Golgi-granule cell system can encode the strength of a mossy fiber input as the state of neuronal activity of parallel fibers. By combining these parallel fiber signals with appropriate connection weights to produce a Purkinje cell output, an arbitrary continuous input-output relationship can be obtained. By incorporating such flexible computation and learning ability in a process of saccadic gain adaptation, a new control scheme in which the cerebellar cortex feedforwardly suppresses the end-point variability when it detects a variation in saccadic commands can be devised. Computer simulation confirmed the efficiency of such learning and showed a reduction in the variability of saccadic end points, similar to results obtained from experimental data.

scholarly journals Mobile English Teaching System Based on Adaptive Algorithm

2018 ◽  
Vol 13 (08) ◽  
pp. 64 ◽  
Author(s):  
Xing Zhao
Keyword(s):  
Adaptive Algorithm ◽  
Learning System ◽  
Learning Ability ◽  
English Learning ◽  
Learning Space ◽  
Teaching System ◽  
English Teaching ◽  
Three Layer Architecture ◽  
Hypermedia Model ◽  
Feedback Module

To improve the students’ individualized and autonomous learning ability in English teaching, a mobile English learning system is designed on the basis of adaptive algorithm. The students’ need for the adaptive mobile English teaching system is analyzed through researches on students and questionnaires. According to the needs analysis, the main functional modules of the adaptive mobile English learning system are designed, including the creation module, personalized learning module, evaluation and feedback module, and management module. Then, the improved XAHM (XML adaptive hypermedia model) is applied to the mobile English learning system. The three-layer architecture of the English mobile learning system is revised into four layers of composition layer, data layer, business logic layer and presentation layer. At the same time, more attention is diverted to the terminal and the situation. Finally, the system is tested. The test results showed that the mobile English learning system realized the self-adaptive and intelligent navigation of learning space in the course of teaching. It is concluded that the new adaptive algorithm had a good performance for college English learning.

Study on Consistency Analysis in Text Categorization

2014 ◽  
Vol 539 ◽  
pp. 181-184
Author(s):  
Wan Li Zuo ◽  
Zhi Yan Wang ◽  
Ning Ma ◽  
Hong Liang
Keyword(s):  
Text Categorization ◽  
Training Data ◽  
Experimental Result ◽  
Final Decision ◽  
Consistency Analysis ◽  
Training Set ◽  
Weak Classifier ◽  
Data Set ◽  
Basic Premise

Accurate classification of text is a basic premise of extracting various types of information on the Web efficiently and utilizing the network resources properly. In this paper, a brand new text classification method was proposed. Consistency analysis method is a type of iterative algorithm, which mainly trains different classifiers (weak classifier) by aiming at the same training set, and then these classifiers will be gathered for testing the consistency degrees of various classification methods for the same text, thus to manifest the knowledge of each type of classifier. It main determines the weight of each sample according to the fact is the classification of each sample is accurate in each training set, as well as the accuracy of the last overall classification, and then sends the new data set whose weight has been modified to the subordinate classifier for training. In the end, the classifier gained in the training will be integrated as the final decision classifier. The classifier with consistency analysis can eliminate some unnecessary training data characteristics and place the key words on key training data. According to the experimental result, the average accuracy of this method is 91.0%, while the average recall rate is 88.1%.

scholarly journals Evaluation of Power Insulator Detection Efficiency with the Use of Limited Training Dataset

2020 ◽  
Vol 10 (6) ◽  
pp. 2104
Author(s):  
Michał Tomaszewski ◽  
Paweł Michalski ◽  
Jakub Osuchowski
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Deep Neural Networks ◽  
Detection Efficiency ◽  
Training Data ◽  
Training Dataset ◽  
Training Set ◽  
Convolutional Network

This article presents an analysis of the effectiveness of object detection in digital images with the application of a limited quantity of input. The possibility of using a limited set of learning data was achieved by developing a detailed scenario of the task, which strictly defined the conditions of detector operation in the considered case of a convolutional neural network. The described solution utilizes known architectures of deep neural networks in the process of learning and object detection. The article presents comparisons of results from detecting the most popular deep neural networks while maintaining a limited training set composed of a specific number of selected images from diagnostic video. The analyzed input material was recorded during an inspection flight conducted along high-voltage lines. The object detector was built for a power insulator. The main contribution of the presented papier is the evidence that a limited training set (in our case, just 60 training frames) could be used for object detection, assuming an outdoor scenario with low variability of environmental conditions. The decision of which network will generate the best result for such a limited training set is not a trivial task. Conducted research suggests that the deep neural networks will achieve different levels of effectiveness depending on the amount of training data. The most beneficial results were obtained for two convolutional neural networks: the faster region-convolutional neural network (faster R-CNN) and the region-based fully convolutional network (R-FCN). Faster R-CNN reached the highest AP (average precision) at a level of 0.8 for 60 frames. The R-FCN model gained a worse AP result; however, it can be noted that the relationship between the number of input samples and the obtained results has a significantly lower influence than in the case of other CNN models, which, in the authors’ assessment, is a desired feature in the case of a limited training set.

scholarly journals Imitation Learning System Design with Small Training Data for Flexible Tool Manipulation

2021 ◽  
Vol 15 (5) ◽  
pp. 669-677
Author(s):  
Harumo Sasatake ◽  
Ryosuke Tasaki ◽  
Takahito Yamashita ◽  
Naoki Uchiyama ◽  
◽  
...  
Keyword(s):  
Deep Learning ◽  
Expert Knowledge ◽  
Teaching Method ◽  
Population Aging ◽  
Developed Countries ◽  
Learning System ◽  
Training Data ◽  
Robot Arm ◽  
Flexible Tool ◽  
Human Labor

Population aging has become a major problem in developed countries. As the labor force declines, robot arms are expected to replace human labor for simple tasks. A robotic arm attaches a tool specialized for a task and acquires the movement through teaching by an engineer with expert knowledge. However, the number of such engineers is limited; therefore, a teaching method that can be used by non-technical personnel is necessitated. As a teaching method, deep learning can be used to imitate human behavior and tool usage. However, deep learning requires a large amount of training data for learning. In this study, the target task of the robot is to sweep multiple pieces of dirt using a broom. The proposed learning system can estimate the initial parameters for deep learning based on experience, as well as the shape and physical properties of the tools. It can reduce the number of training data points when learning a new tool. A virtual reality system is used to move the robot arm easily and safely, as well as to create training data for imitation. In this study, cleaning experiments are conducted to evaluate the effectiveness of the proposed method. The experimental results confirm that the proposed method can accelerate the learning speed of deep learning and acquire cleaning ability using a small amount of training data.

scholarly journals Exemplar Guided Neural Dialogue Generation

2020 ◽  
Author(s):  
Hengyi Cai ◽  
Hongshen Chen ◽  
Yonghao Song ◽  
Xiaofang Zhao ◽  
Dawei Yin
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Training Data ◽  
Small Subset ◽  
Generation Model ◽  
Retrieval Model ◽  
Training Set ◽  
Dialogue Model ◽  
Quantitative Metrics ◽  
The Given

Humans benefit from previous experiences when taking actions. Similarly, related examples from the training data also provide exemplary information for neural dialogue models when responding to a given input message. However, effectively fusing such exemplary information into dialogue generation is non-trivial: useful exemplars are required to be not only literally-similar, but also topic-related with the given context. Noisy exemplars impair the neural dialogue models understanding the conversation topics and even corrupt the response generation. To address the issues, we propose an exemplar guided neural dialogue generation model where exemplar responses are retrieved in terms of both the text similarity and the topic proximity through a two-stage exemplar retrieval model. In the first stage, a small subset of conversations is retrieved from a training set given a dialogue context. These candidate exemplars are then finely ranked regarding the topical proximity to choose the best-matched exemplar response. To further induce the neural dialogue generation model consulting the exemplar response and the conversation topics more faithfully, we introduce a multi-source sampling mechanism to provide the dialogue model with both local exemplary semantics and global topical guidance during decoding. Empirical evaluations on a large-scale conversation dataset show that the proposed approach significantly outperforms the state-of-the-art in terms of both the quantitative metrics and human evaluations.

scholarly journals Generating stable molecules using imitation and reinforcement learning

2021 ◽  
Author(s):  
Søren Ager Meldgaard ◽  
Jonas Köhler ◽  
Henrik Lund Mortensen ◽  
Mads-Peter Verner Christiansen ◽  
Frank Noé ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Chemical Space ◽  
Training Data ◽  
Graph Representation ◽  
Imitation Learning ◽  
Training Set ◽  
Machine Learning Methods ◽  
Multiple Copies ◽  
The Stability ◽  
3D Information

Abstract Chemical space is routinely explored by machine learning methods to discover interesting molecules, before time-consuming experimental synthesizing is attempted. However, these methods often rely on a graph representation, ignoring 3D information necessary for determining the stability of the molecules. We propose a reinforcement learning approach for generating molecules in cartesian coordinates allowing for quantum chemical prediction of the stability. To improve sample-efficiency we learn basic chemical rules from imitation learning on the GDB-11 database to create an initial model applicable for all stoichiometries. We then deploy multiple copies of the model conditioned on a specific stoichiometry in a reinforcement learning setting. The models correctly identify low energy molecules in the database and produce novel isomers not found in the training set. Finally, we apply the model to larger molecules to show how reinforcement learning further refines the imitation learning model in domains far from the training data.

Sign in / Sign up

Export Citation Format

Share Document