Domain adaptation-based transfer learning using adversarial networks

2020 ◽  
Vol 35 ◽  
Author(s):  
Farzaneh Shoeleh ◽  
Mohammad Mehdi Yadollahi ◽  
Masoud Asadpour
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Transfer Learning ◽  
Domain Adaptation ◽  
Machine Learning Techniques ◽  
Implicit Assumption ◽  
Adversarial Networks ◽  
Learning Techniques ◽  
Speed Up ◽  
Similar Domain

Abstract There is an implicit assumption in machine learning techniques that each new task has no relation to the tasks previously learned. Therefore, tasks are often addressed independently. However, in some domains, particularly reinforcement learning (RL), this assumption is often incorrect because tasks in the same or similar domain tend to be related. In other words, even though tasks are quite different in their specifics, they may have general similarities, such as shared skills, making them related. In this paper, a novel domain adaptation-based method using adversarial networks is proposed to do transfer learning in RL problems. Our proposed method incorporates skills previously learned from source task to speed up learning on a new target task by providing generalization not only within a task but also across different, but related tasks. The experimental results indicate the effectiveness of our method in dealing with RL problems.

scholarly journals Applying a Deep Q Network for OpenAIs Car Racing Game

2020 ◽  
Author(s):  
Ali Fakhry
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Transfer Learning ◽  
State Of The Art ◽  
Learning Techniques ◽  
Car Racing ◽  
Custom Made ◽  
Learning Technique ◽  
Reward Threshold

The applications of Deep Q-Networks are seen throughout the field of reinforcement learning, a large subsect of machine learning. Using a classic environment from OpenAI, CarRacing-v0, a 2D car racing environment, alongside a custom based modification of the environment, a DQN, Deep Q-Network, was created to solve both the classic and custom environments. The environments are tested using custom made CNN architectures and applying transfer learning from Resnet18. While DQNs were state of the art years ago, using it for CarRacing-v0 appears somewhat unappealing and not as effective as other reinforcement learning techniques. Overall, while the model did train and the agent learned various parts of the environment, attempting to reach the reward threshold for the environment with this reinforcement learning technique seems problematic and difficult as other techniques would be more useful.

scholarly journals OCCAM: prediction of small ORFs in bacterial genomes by means of a target-decoy database approach and machine learning techniques

Database ◽  
2020 ◽  
Vol 2020 ◽  
Author(s):  
Fabio R. Cerqueira ◽  
Ana Tereza Ribeiro Vasconcelos
Keyword(s):  
Machine Learning ◽  
Machine Learning Algorithms ◽  
Open Reading Frames ◽  
Machine Learning Techniques ◽  
Bacterial Genomes ◽  
Small Proteins ◽  
Learning Techniques ◽  
Speed Up ◽  
Computational Procedures ◽  
Small Orfs

Abstract Small open reading frames (ORFs) have been systematically disregarded by automatic genome annotation. The difficulty in finding patterns in tiny sequences is the main reason that makes small ORFs to be overlooked by computational procedures. However, advances in experimental methods show that small proteins can play vital roles in cellular activities. Hence, it is urgent to make progress in the development of computational approaches to speed up the identification of potential small ORFs. In this work, our focus is on bacterial genomes. We improve a previous approach to identify small ORFs in bacteria. Our method uses machine learning techniques and decoy subject sequences to filter out spurious ORF alignments. We show that an advanced multivariate analysis can be more effective in terms of sensitivity than applying the simplistic and widely used e-value cutoff. This is particularly important in the case of small ORFs for which alignments present higher e-values than usual. Experiments with control datasets show that the machine learning algorithms used in our method to curate significant alignments can achieve average sensitivity and specificity of 97.06% and 99.61%, respectively. Therefore, an important step is provided here toward the construction of more accurate computational tools for the identification of small ORFs in bacteria.

Controlling a Simulated Robot Using Machine Learning Techniques

2010 ◽  
Author(s):  
Jonathan Becker ◽  
Aveek Purohit ◽  
Zheng Sun
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Linear Regression ◽  
Pid Controller ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
Gaming Environment ◽  
Using Data

USARSim group at NIST developed a simulated robot that operated in the Unreal Tournament 3 (UT3) gaming environment. They used a software PID controller to control the robot in UT3 worlds. Unfortunately, the PID controller did not work well, so NIST asked us to develop a better controller using machine learning techniques. In the process, we characterized the software PID controller and the robot’s behavior in UT3 worlds. Using data collected from our simulations, we compared different machine learning techniques including linear regression and reinforcement learning (RL). Finally, we implemented a RL based controller in Matlab and ran it in the UT3 environment via a TCP/IP link between Matlab and UT3.

scholarly journals Hybrid Deep-Learning and Machine-Learning Models for Predicting COVID-19

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Talal S. Qaid ◽  
Hussein Mazaar ◽  
Mohammad Yahya H. Al-Shamri ◽  
Mohammed S. Alqahtani ◽  
Abeer A. Raweh ◽  
...  
Keyword(s):  
Machine Learning ◽  
Transfer Learning ◽  
Healthcare Systems ◽  
Viral Pneumonia ◽  
Machine Learning Techniques ◽  
Full Potential ◽  
Learning Models ◽  
Local Data ◽  
Data Set ◽  
Learning Techniques

The COVID-19 pandemic has had a significant impact on public life and health worldwide, putting the world’s healthcare systems at risk. The first step in stopping this outbreak is to detect the infection in its early stages, which will relieve the risk, control the outbreak’s spread, and restore full functionality to the world’s healthcare systems. Currently, PCR is the most prevalent diagnosis tool for COVID-19. However, chest X-ray images may play an essential role in detecting this disease, as they are successful for many other viral pneumonia diseases. Unfortunately, there are common features between COVID-19 and other viral pneumonia, and hence manual differentiation between them seems to be a critical problem and needs the aid of artificial intelligence. This research employs deep- and transfer-learning techniques to develop accurate, general, and robust models for detecting COVID-19. The developed models utilize either convolutional neural networks or transfer-learning models or hybridize them with powerful machine-learning techniques to exploit their full potential. For experimentation, we applied the proposed models to two data sets: the COVID-19 Radiography Database from Kaggle and a local data set from Asir Hospital, Abha, Saudi Arabia. The proposed models achieved promising results in detecting COVID-19 cases and discriminating them from normal and other viral pneumonia with excellent accuracy. The hybrid models extracted features from the flatten layer or the first hidden layer of the neural network and then fed these features into a classification algorithm. This approach enhanced the results further to full accuracy for binary COVID-19 classification and 97.8% for multiclass classification.

scholarly journals Toward a Comparison of Classical and New Privacy Mechanism

Entropy ◽  
2021 ◽  
Vol 23 (4) ◽  
pp. 467
Author(s):  
Daniel Heredia-Ductram ◽  
Miguel Nunez-del-Prado ◽  
Hugo Alatrista-Salas
Keyword(s):  
Machine Learning ◽  
Differential Privacy ◽  
Machine Learning Techniques ◽  
Generative Adversarial Networks ◽  
Current Effort ◽  
Privacy Concerns ◽  
Adversarial Networks ◽  
Learning Techniques ◽  
Statistical Disclosure ◽  
Big Data Technologies

In the last decades, the development of interconnectivity, pervasive systems, citizen sensors, and Big Data technologies allowed us to gather many data from different sources worldwide. This phenomenon has raised privacy concerns around the globe, compelling states to enforce data protection laws. In parallel, privacy-enhancing techniques have emerged to meet regulation requirements allowing companies and researchers to exploit individual data in a privacy-aware way. Thus, data curators need to find the most suitable algorithms to meet a required trade-off between utility and privacy. This crucial task could take a lot of time since there is a lack of benchmarks on privacy techniques. To fill this gap, we compare classical approaches of privacy techniques like Statistical Disclosure Control and Differential Privacy techniques to more recent techniques such as Generative Adversarial Networks and Machine Learning Copies using an entire commercial database in the current effort. The obtained results allow us to show the evolution of privacy techniques and depict new uses of the privacy-aware Machine Learning techniques.

scholarly journals Inductive and Transductive Transfer Learning for Zero-day Attack Detection

2019 ◽  
Vol 8 (11) ◽  
pp. 1765-1768
Keyword(s):  
Transfer Learning ◽  
Domain Adaptation ◽  
Attack Detection ◽  
Supervised Machine Learning ◽  
Intrusion Detection Systems ◽  
Machine Learning Techniques ◽  
Target Domain ◽  
Detection Systems ◽  
Learning Techniques ◽  
Manifold Alignment

Upon application of supervised machine learning techniques Intrusion Detection Systems (IDSs) are successful in detecting known attacks as they use predefined attack signatures. However, detecting zero-day attacks is challenged because of the scarcity of the labeled instances for zero-day attacks. Advanced research on IDS applies the concept of Transfer Learning (TL) to compensate the scarcity of labeled instances of zero-day attacks by making use of abundant labeled instances present in related domain(s). This paper explores the potential of Inductive and Transductive transfer learning for detecting zero-day attacks experimentally, where inductive TL deals with the presence of minimal labeled instances in the target domain and transductive TL deals with the complete absence of labeled instances in the target domain. The concept of domain adaptation with manifold alignment (DAMA) is applied in inductive TL where the variant of DAMA is proposed to handle transductive TL due to non-availability of labeled instances. NSL_KDD dataset is used for experimentation

scholarly journals Adaptive Inception Based on Transfer Learning for Effective Visual Recognition

2020 ◽  
Vol 13 (6) ◽  
pp. 1-10
Author(s):  
Balaji Sreenivasulu ◽  
◽  
Anjaneyulu Pasala ◽  
Gaikwad Vasanth ◽  
◽  
...  
Keyword(s):  
Transfer Learning ◽  
Visual Recognition ◽  
Data Augmentation ◽  
Research Study ◽  
Domain Adaptation ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Convolutional Networks ◽  
Learning Techniques ◽  
Two Phases

In computer vision, domain adaptation or transfer learning plays an important role because it learns a target classifier characteristics using labeled data from various distribution. The existing researches mostly focused on minimizing the time complexity of neural networks and it effectively worked on low-level features. However, the existing method failed to concentrate on data augmentation time and cost of labeled data. Moreover, machine learning techniques face difficulty to obtain the large amount of distributed label data. In this research study, the pre-trained network called inception layer is fine-tuned with the augmented data. There are two phases present in this study, where the effectiveness of data augmentation for Inception pre-trained networks is investigated in the first phase. The transfer learning approach is used to enhance the results of the first phase and the Support Vector Machine (SVM) is used to learn all the features extracted from inception layers. The experiments are conducted on a publicly available dataset to estimate the effectiveness of proposed method. The results stated that the proposed method achieved 95.23% accuracy, where the existing techniques namely deep neural network and traditional convolutional networks achieved 87.32% and 91.32% accuracy respectively. This validation results proved that the developed method nearly achieved 4-8% improvement in accuracy than existing techniques.

scholarly journals Reinforcement Learning and Physics

2021 ◽  
Vol 11 (18) ◽  
pp. 8589
Author(s):  
José D. Martín-Guerrero ◽  
Lucas Lamata
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Scientific Discovery ◽  
Machine Learning Techniques ◽  
Physical Systems ◽  
The Past ◽  
Learning Techniques ◽  
Science Community ◽  
Learning Protocols

Machine learning techniques provide a remarkable tool for advancing scientific research, and this area has significantly grown in the past few years. In particular, reinforcement learning, an approach that maximizes a (long-term) reward by means of the actions taken by an agent in a given environment, can allow one for optimizing scientific discovery in a variety of fields such as physics, chemistry, and biology. Morover, physical systems, in particular quantum systems, may allow one for more efficient reinforcement learning protocols. In this review, we describe recent results in the field of reinforcement learning and physics. We include standard reinforcement learning techniques in the computer science community for enhancing physics research, as well as the more recent and emerging area of quantum reinforcement learning, inside quantum machine learning, for improving reinforcement learning computations.

scholarly journals Survey on Civil Complaints Management System by Using Machine Learning Techniques

2021 ◽  
pp. 606-610
Author(s):  
Sayali Bhosale ◽  
Sonali Patankar ◽  
Kshitija Kadam ◽  
Rujuta Dhere ◽  
Prof. Manisha Desai
Keyword(s):  
Machine Learning ◽  
Machine Learning Techniques ◽  
Clustering Method ◽  
Registration System ◽  
Handling System ◽  
Complaint Handling ◽  
Learning Techniques ◽  
Framework Model ◽  
Speed Up ◽  
The Government

Today’s Government Complaints Registration System is totally Human Operable hence it consumes lot of time to resolve each of those complaint. The proposed system is being developed for the government offices to create a helpful complaint registering platform which will be efficient. The Framework model of civil complaint handling system is done by using sentimental analysis and ML techniques to speed up the process of categorization and prioritization of complaints. The system will analyses the citizen sentiment to prioritize the complaints. Later then the categorization of complaints done by using clustering method and give them priority based upon urgency of each one respectively. The municipality can use this method to identify citizen’s needs and estimate their satisfaction.

Sign in / Sign up

Export Citation Format

Share Document