Preventing undesirable behavior of intelligent machines

Science ◽  
2019 ◽  
Vol 366 (6468) ◽  
pp. 999-1004 ◽  
Author(s):  
Philip S. Thomas ◽  
Bruno Castro da Silva ◽  
Andrew G. Barto ◽  
Stephen Giguere ◽  
Yuriy Brun ◽  
...  
Keyword(s):  
Machine Learning ◽  
Pattern Recognition ◽  
Data Analysis ◽  
Complex Systems ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Intelligent Machines ◽  
Dangerous Behavior ◽  
Flexible Framework ◽  
Undesirable Behavior

Intelligent machines using machine learning algorithms are ubiquitous, ranging from simple data analysis and pattern recognition tools to complex systems that achieve superhuman performance on various tasks. Ensuring that they do not exhibit undesirable behavior—that they do not, for example, cause harm to humans—is therefore a pressing problem. We propose a general and flexible framework for designing machine learning algorithms. This framework simplifies the problem of specifying and regulating undesirable behavior. To show the viability of this framework, we used it to create machine learning algorithms that precluded the dangerous behavior caused by standard machine learning algorithms in our experiments. Our framework for designing machine learning algorithms simplifies the safe and responsible application of machine learning.

Machine learning algorithms for smart data analysis in the Internet of things: an overview

2021 ◽  
pp. 307-327
Author(s):  
Mohammed H. Alsharif ◽  
Anabi Hilary Kelechi ◽  
Imran Khan ◽  
Mahmoud A. Albreem ◽  
Abu Jahid ◽  
...  
Keyword(s):  
Machine Learning ◽  
Data Analysis ◽  
Internet Of Things ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
The Internet ◽  
Smart Data ◽  
The Internet Of Things

scholarly journals Predicting the Tensile Behaviour of Cast Alloys by a Pattern Recognition Analysis on Experimental Data

Metals ◽  
2019 ◽  
Vol 9 (5) ◽  
pp. 557 ◽  
Author(s):  
Cristiano Fragassa ◽  
Matej Babic ◽  
Carlos Perez Bergmann ◽  
Giangiacomo Minak
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Mechanical Properties ◽  
Pattern Recognition ◽  
Cast Iron ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Tensile Behaviour ◽  
Cast Alloys ◽  
Pattern Recognition Analysis

The ability to accurately predict the mechanical properties of metals is essential for their correct use in the design of structures and components. This is even more important in the presence of materials, such as metal cast alloys, whose properties can vary significantly in relation to their constituent elements, microstructures, process parameters or treatments. This study shows how a machine learning approach, based on pattern recognition analysis on experimental data, is able to offer acceptable precision predictions with respect to the main mechanical properties of metals, as in the case of ductile cast iron and compact graphite cast iron. The metallographic properties, such as graphite, ferrite and perlite content, extrapolated through macro indicators from micrographs by image analysis, are used as inputs for the machine learning algorithms, while the mechanical properties, such as yield strength, ultimate strength, ultimate strain and Young’s modulus, are derived as output. In particular, 3 different machine learning algorithms are trained starting from a dataset of 20–30 data for each material and the results offer high accuracy, often better than other predictive techniques. Concerns regarding the applicability of these predictive techniques in material design and product/process quality control are also discussed.

scholarly journals Not All Attributes are Created Equal: dX -Private Mechanisms for Linear Queries

2020 ◽  
Vol 2020 (1) ◽  
pp. 103-125
Author(s):  
Parameswaran Kamalaruban ◽  
Victor Perrier ◽  
Hassan Jameel Asghar ◽  
Mohamed Ali Kaafar
Keyword(s):  
Machine Learning ◽  
Data Analysis ◽  
Differential Privacy ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Trade Off ◽  
Systematic Procedure ◽  
Privacy Budget ◽  
Sensitivity Vector

AbstractDifferential privacy provides strong privacy guarantees simultaneously enabling useful insights from sensitive datasets. However, it provides the same level of protection for all elements (individuals and attributes) in the data. There are practical scenarios where some data attributes need more/less protection than others. In this paper, we consider dX -privacy, an instantiation of the privacy notion introduced in [6], which allows this flexibility by specifying a separate privacy budget for each pair of elements in the data domain. We describe a systematic procedure to tailor any existing differentially private mechanism that assumes a query set and a sensitivity vector as input into its dX -private variant, specifically focusing on linear queries. Our proposed meta procedure has broad applications as linear queries form the basis of a range of data analysis and machine learning algorithms, and the ability to define a more flexible privacy budget across the data domain results in improved privacy/utility tradeoff in these applications. We propose several dX -private mechanisms, and provide theoretical guarantees on the trade-off between utility and privacy. We also experimentally demonstrate the effectiveness of our procedure, by evaluating our proposed dX -private Laplace mechanism on both synthetic and real datasets using a set of randomly generated linear queries.

Finger Movement Pattern Recognition from Surface EMG Signals Using Machine Learning Algorithms

ICTMI 2017 ◽  
2019 ◽  
pp. 75-89 ◽  
Author(s):  
Shravan Krishnan ◽  
Ravi Akash ◽  
Dilip Kumar ◽  
Rishab Jain ◽  
Karthik Murali Madhavan Rathai ◽  
...  
Keyword(s):  
Machine Learning ◽  
Pattern Recognition ◽  
Learning Algorithms ◽  
Movement Pattern ◽  
Surface Emg ◽  
Machine Learning Algorithms ◽  
Finger Movement
Sign in / Sign up

Export Citation Format

Share Document