Learning and control

2018 ◽  
Author(s):  
Ivan Herreros
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Brain Function ◽  
Control Strategies ◽  
Learning Problems ◽  
Animal Learning ◽  
Feed Forward Control ◽  
Machine Learning Applications ◽  
And Control

This chapter discusses basic concepts from control theory and machine learning to facilitate a formal understanding of animal learning and motor control. It first distinguishes between feedback and feed-forward control strategies, and later introduces the classification of machine learning applications into supervised, unsupervised, and reinforcement learning problems. Next, it links these concepts with their counterparts in the domain of the psychology of animal learning, highlighting the analogies between supervised learning and classical conditioning, reinforcement learning and operant conditioning, and between unsupervised and perceptual learning. Additionally, it interprets innate and acquired actions from the standpoint of feedback vs anticipatory and adaptive control. Finally, it argues how this framework of translating knowledge between formal and biological disciplines can serve us to not only structure and advance our understanding of brain function but also enrich engineering solutions at the level of robot learning and control with insights coming from biology.

scholarly journals Entropy-Penalized Semidefinite Programming

2019 ◽  
Author(s):  
Mikhail Krechetov ◽  
Jakub Marecek ◽  
Yury Maximov ◽  
Martin Takac
Keyword(s):  
Machine Learning ◽  
Time Complexity ◽  
Optimization Problems ◽  
Linear Time ◽  
Broad Class ◽  
Low Rank ◽  
Learning Problems ◽  
Unified Framework ◽  
Gradient Computation ◽  
Machine Learning Applications

Low-rank methods for semi-definite programming (SDP) have gained a lot of interest recently, especially in machine learning applications. Their analysis often involves determinant-based or Schatten-norm penalties, which are difficult to implement in practice due to high computational efforts. In this paper, we propose Entropy-Penalized Semi-Definite Programming (EP-SDP), which provides a unified framework for a broad class of penalty functions used in practice to promote a low-rank solution. We show that EP-SDP problems admit an efficient numerical algorithm, having (almost) linear time complexity of the gradient computation; this makes it useful for many machine learning and optimization problems. We illustrate the practical efficiency of our approach on several combinatorial optimization and machine learning problems.

Programming Language Support for Implementing Machine Learning Algorithms

2020 ◽  
pp. 402-421
Author(s):  
Anitha Elavarasi S. ◽  
Jayanthi J.
Keyword(s):  
Machine Learning ◽  
Programming Languages ◽  
Programming Language ◽  
Domain Knowledge ◽  
Learning Algorithm ◽  
Mathematical Optimization ◽  
Machine Learning Algorithms ◽  
Application Development ◽  
Machine Learning Applications ◽  
And Control

Machine learning provides the system to automatically learn without human intervention and improve their performance with the help of previous experience. It can access the data and use it for learning by itself. Even though many algorithms are developed to solve machine learning issues, it is difficult to handle all kinds of inputs data in-order to arrive at accurate decisions. The domain knowledge of statistical science, probability, logic, mathematical optimization, reinforcement learning, and control theory plays a major role in developing machine learning based algorithms. The key consideration in selecting a suitable programming language for implementing machine learning algorithm includes performance, concurrence, application development, learning curve. This chapter deals with few of the top programming languages used for developing machine learning applications. They are Python, R, and Java. Top three programming languages preferred by data scientist are (1) Python more than 57%, (2) R more than 31%, and (3) Java used by 17% of the data scientists.

Progress in sensor technology - progress in process control? Part I: Sensor property investigation and classification

2003 ◽  
Vol 47 (2) ◽  
pp. 103-112 ◽  
Author(s):  
L. Rieger ◽  
J. Alex ◽  
S. Winkler ◽  
M. Boehler ◽  
M. Thomann ◽  
...  
Keyword(s):  
Control Strategies ◽  
Sensor Technology ◽  
Limiting Factor ◽  
Test Environment ◽  
Sensor Property ◽  
Sensor Models ◽  
The Cost ◽  
And Control ◽  
Measurement And Control

To ensure correctly operating control systems, the measurement and control equipment in WWTPs must be mutually consistent. The dynamic simulation of activated sludge systems could offer a suitable tool for designing and optimising control strategies. Ideal or simplified sensor models represent a limiting factor for comparability with field applications. More realistic sensor models are therefore required. Two groups of sensor models are proposed on the basis of field and laboratory tests: one for specific sensors and another for a classification of sensor types to be used with the COST simulation benchmark environment. This should lead to a more realistic test environment and allow control engineers to define the requirements of the measuring equipment as a function of the selected control strategy.

scholarly journals Newly Proposed Technique for Autism Spectrum Disorder based Machine Learning

2021 ◽  
Vol 13 (2) ◽  
pp. 1-15
Author(s):  
Sherif Kamel ◽  
Rehab Al-harbi
Keyword(s):  
Machine Learning ◽  
Autism Spectrum Disorder ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Screening Methods ◽  
Disease Prediction ◽  
Healthcare Organizations ◽  
Machine Learning Applications ◽  
Research Stage

The rapid growth in the number of autism disorder among toddlers needs for the development of easily implemented and effective screening methods. In this current era, the causes of Autism Spectrum Disorder (ASD) do not know yet, however, the diagnosis and detection of ASD is based on behaviours and symptoms. This paper aims to improve ASD disease prediction accuracy among toddlers by using the Logistic Regression model of Machine Learning, through the collected health care dataset and by using an algorithm for rapid classification of the behaviours to check whether the children are having autism diseases or not according to information in the dataset. Therefore, Machine Learning decreasing the time needed to detect the disorder, then providing the necessary health services early for infected toddlers to enhance their lifestyle. In healthcare, most machine learning applications are in the research stage, and to take the advantage of emerging software tools that incorporate artificial intelligence, healthcare organizations first need to overcome a variety of challenges.

scholarly journals Decomposition Methods for Machine Learning with Small, Incomplete or Noisy Datasets

2020 ◽  
Vol 10 (23) ◽  
pp. 8481
Author(s):  
Cesar Federico Caiafa ◽  
Jordi Solé-Casals ◽  
Pere Marti-Puig ◽  
Sun Zhe ◽  
Toshihisa Tanaka
Keyword(s):  
Machine Learning ◽  
Data Augmentation ◽  
Unsupervised Classification ◽  
Decomposition Methods ◽  
Signal Decomposition ◽  
Learning Performance ◽  
Decomposition Approach ◽  
Data Completion ◽  
Machine Learning Applications

In many machine learning applications, measurements are sometimes incomplete or noisy resulting in missing features. In other cases, and for different reasons, the datasets are originally small, and therefore, more data samples are required to derive useful supervised or unsupervised classification methods. Correct handling of incomplete, noisy or small datasets in machine learning is a fundamental and classic challenge. In this article, we provide a unified review of recently proposed methods based on signal decomposition for missing features imputation (data completion), classification of noisy samples and artificial generation of new data samples (data augmentation). We illustrate the application of these signal decomposition methods in diverse selected practical machine learning examples including: brain computer interface, epileptic intracranial electroencephalogram signals classification, face recognition/verification and water networks data analysis. We show that a signal decomposition approach can provide valuable tools to improve machine learning performance with low quality datasets.

scholarly journals Classification of Big Data: Machine Learning Problems and Challenges in Network Intrusion Prediction

2018 ◽  
Vol 7 (4.36) ◽  
pp. 1189
Author(s):  
Yasser Mohammad Al-Sharo ◽  
Ghazi Shakah ◽  
Mutasem Sh.Alkhaswneh ◽  
Bajes Zeyad Aljunaeidi ◽  
Malik Bader Alazzam
Keyword(s):  
Machine Learning ◽  
Big Data ◽  
Representation Learning ◽  
Learning Problems ◽  
Traffic Information ◽  
Classification Problems ◽  
Network Intrusion ◽  
Learning Techniques ◽  
Geometric Techniques

Centre of attraction of paper is on the main complication on classification of Big Data on network encroachment on traffic. It also explains the disputes this system faces that is bestowed by the Big Data difficulties that are correlate with the network interruption forecast. Forecasting of an attainable interruption in a network entails a prolonged accumulation of traffic information or data and being able to get the concept on their features on motion. The constant accumulation in the network of traffic data thereafter ends with Big Data difficulties that as a result of the large amount, change and possessions of Big Data. In order to learn the features of a network, one needs to have the skills in the machine techniques that are always able to capture world skills and knowledge of the traffic to be in order. The properties of Big Data will always end to an important system disputes to be able to apply machine learning foundation. The paper also discusses the disputes and problems in the way of taking care of Big Data categorization representing geometric techniques of learning along with the existing technologies of Big networking. The study particularly explains challenges that have a relationship with the combined directed by the techniques one learns, machine long learning techniques, and representation-learning techniques and technologies that are related to Big Data for example Hive, Hadoop and Cloud that are basics that enhances problem-solving that gives relevant solutions to classification problems in traffic networking.  

scholarly journals Methods of intelligent protection from asymmetrical conditions in electric networks

2020 ◽  
Vol 209 ◽  
pp. 07004
Author(s):  
H.B Guliyev ◽  
N.V. Tomin ◽  
F.Sh Ibrahimov
Keyword(s):  
Machine Learning ◽  
Fuzzy Logic ◽  
Reinforcement Learning ◽  
Electrical Network ◽  
Learning Models ◽  
Structural Diagram ◽  
Electric Networks ◽  
Drive Systems ◽  
And Control ◽  
Machine Learning Models

Possible cases of non-fulfilment of the requirements of the necessary sensitivity and the selectivity of the existing protection against incomplete-phase and asymmetric modes in the electrical network under conditions of uncertainty of the initial data are determined. The paper considers the issue of intellectualization of protection from asymmetric modes based on theories of fuzzy logic, as well as machine learning models, and offers a structural diagram and an algorithm for the functioning of protection. The results of the synthesis of intelligent protection and an approach to modelling and control for controlled drive systems based on reinforcement learning are presented.

scholarly journals Exploration Using Without-Replacement Sampling of Actions Is Sometimes Inferior

2019 ◽  
Vol 1 (2) ◽  
pp. 698-714
Author(s):  
Stephen W. Carden ◽  
S. Dalton Walker
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Shortest Path ◽  
Numerical Experiments ◽  
Action Selection ◽  
Selection Strategy ◽  
Goal State ◽  
Stochastic Shortest Path ◽  
Expected Time ◽  
Machine Learning Applications

In many statistical and machine learning applications, without-replacement sampling is considered superior to with-replacement sampling. In some cases, this has been proven, and in others the heuristic is so intuitively attractive that it is taken for granted. In reinforcement learning, many count-based exploration strategies are justified by reliance on the aforementioned heuristic. This paper will detail the non-intuitive discovery that when measuring the goodness of an exploration strategy by the stochastic shortest path to a goal state, there is a class of processes for which an action selection strategy based on without-replacement sampling of actions can be worse than with-replacement sampling. Specifically, the expected time until a specified goal state is first reached can be provably larger under without-replacement sampling. Numerical experiments describe the frequency and severity of this inferiority.

Sign in / Sign up

Export Citation Format

Share Document