Edgar Analytics & Complex Systems
510 views | +0 today
Follow
 
Rescooped by Nuno Edgar Fernandes from Quantitative Finance
onto Edgar Analytics & Complex Systems
Scoop.it!

Date Formats in R

Date Formats in R | Edgar Analytics & Complex Systems | Scoop.it
(This article was first published on Mollie's Research Blog, and kindly contributed to R-bloggers)
Importing DatesDates can be imported from character, numeric, POSIXlt, and POSIXct formats using the as.Date function from the base package.

Via Vincent Denoiseux
more...
No comment yet.
Edgar Analytics & Complex Systems
A space to Scoop about Big Data and Complexity
Your new post is loading...
Your new post is loading...
Rescooped by Nuno Edgar Fernandes from CxConferences
Scoop.it!

Call for Satellites: Conference on Complex Systems 2017

Call for Satellites: Conference on Complex Systems 2017 | Edgar Analytics & Complex Systems | Scoop.it
As usual with the Conferences on Complex Systems, apart form the main tracks of the conference, there will be two full days of satellites (Wednesday, September 20th and Thursday, September 21st). We therefore call for satellite proposals for half a day or full day events. Satellite organizers are responsible for promoting, organizing, reviewing, and scheduling their session.

Scientifically sound proposals should be less than 1000 words, including scope of the satellite, goals, tentative program (format, half-day/full day, invited speakers), estimated attendance, and organizers.

Proposals should be submitted in PDF format to satellites@ccs17.unam.mx

Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from CxConferences
Scoop.it!

GEFENOL Summer School 2017

GEFENOL Summer School 2017 | Edgar Analytics & Complex Systems | Scoop.it

Statistical Physics, which was born as an attempt to explain thermodynamic properties of systems from its atomic and molecular components, has evolved into a solid body of knowledge that allows for the understanding of macroscopic collective phenomena. The tools developed by the Statistical Physics together with the Theory of Dynamical Systems are of key importance in the understanding of Complex Systems which are characterized by the emergent and collective phenomena of many interacting units. While the basic body of knowledge of Statistical Physics and Dynamical Systems is well described in textbooks at undergraduate or master level, the applications to open problems in the context of Complex Systems are well beyond the scope of those textbooks. Aiming at bridging this gap the Topical Group on Statistical and Non Linear Physics (GEFENOL)  of the Royal Spanish Physical Society is promoting the Summer School on Statistical Physics of Complex Systems series, open to PhD students and young postdocs world-wide.
Following the spirit and concept of precedent succesful editions (Palma de Mallorca 2011, 2013, 2014, Benasque 2012, Barcelona 2015 and Pamplona 2016)  the 7th edition will take place from June 19 to 30, 2017. During these two weeks there will be a total of six courses

 

VII GEFENOL Summer School on
Statistical Physics of Complex Systems
IFISC, Palma de Mallorca, Spain, June 19-30, 2017


Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from Papers
Scoop.it!

Minorities report: optimal incentives for collective intelligence

Collective intelligence is the ability of a group to perform more effectively than any individual alone. Diversity among group members is a key condition for the emergence of collective intelligence, but maintaining diversity is challenging in the face of social pressure to imitate one's peers. We investigate the role incentives play in maintaining useful diversity through an evolutionary game-theoretic model of collective prediction. We show that market-based incentive systems produce herding effects, reduce information available to the group and suppress collective intelligence. In response, we propose a new incentive scheme that rewards accurate minority predictions, and show that this produces optimal diversity and collective predictive accuracy. We conclude that real-world systems should reward those who have demonstrated accuracy when majority opinion has been in error.

 

Minorities report: optimal incentives for collective intelligence

Richard P. Mann, Dirk Helbing


Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from Teacher's corner
Scoop.it!

Our Brains Have a Basic Algorithm That Enables Our Intelligence

Our Brains Have a Basic Algorithm That Enables Our Intelligence | Edgar Analytics & Complex Systems | Scoop.it
Neuroscience News has recent neuroscience research articles, brain research news, neurology studies and neuroscience resources for neuroscientists, students, and science fans and is always free to join. Our neuroscience social network has science groups, discussion forums, free books, resources, science videos and more.

Via Suvi Salo
more...
Suvi Salo's curator insight, November 21, 2016 3:33 PM
via @NeuroscienceNew
Rescooped by Nuno Edgar Fernandes from Papers
Scoop.it!

Transfer entropy in continuous time, with applications to jump and neural spiking processes

Transfer entropy has been used to quantify the directed flow of information between source and target variables in many complex systems. Originally formulated in discrete time, we provide a framework for considering transfer entropy in continuous time systems. By appealing to a measure theoretic formulation we generalise transfer entropy, describing it in terms of Radon-Nikodym derivatives between measures of complete path realisations. The resulting formalism introduces and emphasises the idea that transfer entropy is an expectation of an individually fluctuating quantity along a path, in the same way we consider the expectation of physical quantities such as work and heat. We recognise that transfer entropy is a quantity accumulated over a finite time interval, whilst permitting an associated instantaneous transfer entropy rate. We use this approach to produce an explicit form for the transfer entropy for pure jump processes, and highlight the simplified form in the specific case of point processes (frequently used in neuroscience to model neural spike trains). We contrast our approach with previous attempts to formulate information flow between continuous time point processes within a discrete time framework, which incur issues that our continuous time approach naturally avoids. Finally, we present two synthetic spiking neuron model examples to exhibit the pertinent features of our formalism, namely that the information flow for point processes consists of discontinuous jump contributions (at spikes in the target) interrupting a continuously varying contribution (relating to waiting times between target spikes).

 

Transfer entropy in continuous time, with applications to jump and neural spiking processes

Richard E. Spinney, Mikhail Prokopenko, Joseph T. Lizier


Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from CxConferences
Scoop.it!

8th Conference on Complex Networks

8th Conference on Complex Networks | Edgar Analytics & Complex Systems | Scoop.it

CompleNet 2017 - 8th Conference on Complex Networks
http://complenet.weebly.com/
 
Where and When:
Dubrovnik, Croatia, March 21st-24th, 2016.
 
Important dates:
* Abstract/Paper submission deadline: November 27, 2016
* Notification of acceptance: December 23, 2016
* Submission of Camera-Ready (papers): January 8, 2017
* Early registration ends on: January 20, 2017


Via Complexity Digest
more...
No comment yet.
Scooped by Nuno Edgar Fernandes
Scoop.it!

Digitization of Industrie - Plattform Industrie 4.0

Digitization of Industrie - Plattform Industrie 4.0 | Edgar Analytics & Complex Systems | Scoop.it
Available as PDF "Digitization of Industrie - Plattform Industrie 4.0"
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from Papers
Scoop.it!

How complexity originates: Examples from history reveal additional roots to complexity

Most scientists will characterize complexity as the result of one or more factors out of three: (i) high dimensionality, (ii) interaction networks, and (iii) nonlinearity. High dimensionality alone need not give rise to complexity. The best known cases come from linear algebra: To determine the eigenvalues and eigenvectors of a large quadratic matrix, for example, is complicated but not complex. Every mathematician, physicist or economist, and most scholars from other disciplines can write down an algorithm that would work provided infinite resources in computer time and storage space are given. (...) 

 

How complexity originates: Examples from history reveal additional roots to complexity
Peter Schuster
Complexity
DOI: 10.1002/cplx.21841


Via Complexity Digest
more...
Marcelo Errera's curator insight, October 28, 2016 2:23 PM
It's reasonable to assume there is an underlying physics principle that drives systems to complexity.  Once the principle is identified, one will be able to discover when complexity emerges or not.
Rescooped by Nuno Edgar Fernandes from Papers
Scoop.it!

Compression and the origins of Zipf's law for word frequencies

Here we sketch a new derivation of Zipf's law for word frequencies based on optimal coding. The structure of the derivation is reminiscent of Mandelbrot's random typing model but it has multiple advantages over random typing: (1) it starts from realistic cognitive pressures, (2) it does not require fine tuning of parameters, and (3) it sheds light on the origins of other statistical laws of language and thus can lead to a compact theory of linguistic laws. Our findings suggest that the recurrence of Zipf's law in human languages could originate from pressure for easy and fast communication.

 

Compression and the origins of Zipf's law for word frequencies
Ramon Ferrer-i-Cancho

Complexity


Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from Papers
Scoop.it!

Heroes and Villains in Complex Socio-technical Systems

The history of efforts to reduce ‘human errors’ across workplaces and industries suggests that people (or their weaknesses) are seen as a problem to control [1, 3, 15, 16]. However, some have proposed that humans can be heroes as they can adapt and compensate for weaknesses within a system and direct it away from potential catastrophes [15]. But the existence of heroes would suggest that villains (i.e. humans who cause a disaster) exist as well [16], and that it might well be the outcome that determines which human becomes which. The purpose of this chapter is to examine if complex socio-technical systems would allow for the existence of heroes and villains, as outcomes in such systems are usually thought to be the product of interactions rather than a single factor [17]. The chapter will first examine if the properties of complex systems as suggested by Dekker et al. [18] would allow for heroes and villains to exist. These include: (a) synthesis and holism, (b) emergence, (c) foreseeability of probabilities, not certainties, (d) time-irreversibility and, (e) perpetual incompleteness and uncertainty of knowledge, before concluding with a discussion of the implications of the (non) existence of heroes and villains in complex systems for the way we conduct investigations when something goes wrong inside of those systems.

Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from CxBooks
Scoop.it!

Energy, Complexity and Wealth Maximization (by Robert Ayres)

This book describes the evolution and mechanisms of natural wealth creation. The author explains how natural wealth consists of complex physical structures of condensed (“frozen”) energy and what the key requirements for wealth creation are, namely a change agent, a selection mechanism and a life-extending mechanism. He uses elements from multiple disciplines, from physics to biology to economics to illustrate this.

Human wealth is ultimately based on natural wealth, as materials transform into useful artifacts, and as useful information is transmitted by those artifacts when activated by energy. The question is if the new immaterial wealth of ideas of the knowledge economy can replace depleted natural wealth. This book reveals the vital challenge for economic and political leaders to explore how knowledge and natural capital, energy in particular, can interact to power the human wealth engine in the future.


Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from Papers
Scoop.it!

Networks: An Economic Perspective

We discuss social network analysis from the perspective of economics. We organize the presentaion around the theme of externalities: the effects that one's behavior has on others' well-being. Externalities underlie the interdependencies that make networks interesting. We discuss network formation, as well as interactions between peoples' behaviors within a given network, and the implications in a variety of settings. Finally, we highlight some empirical challenges inherent in the statistical analysis of network-based data.

 

Networks: An Economic Perspective
Matthew O. Jackson, Brian W. Rogers, Yves Zenou


Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from Papers
Scoop.it!

Introduction to Focus Issue: Complex Dynamics in Networks, Multilayered Structures and Systems

In the last years, network scientists have directed their interest to the multi-layer character of real-world systems, and explicitly considered the structural and dynamical organization of graphs made of diverse layers between its constituents. Most complex systems include multiple subsystems and layers of connectivity and, in many cases, the interdependent components of systems interact through many different channels. Such a new perspective is indeed found to be the adequate representation for a wealth of features exhibited by networked systems in the real world. The contributions presented in this Focus Issue cover, from different points of view, the many achievements and still open questions in the field of multi-layer networks, such as: new frameworks and structures to represent and analyze heterogeneous complex systems, different aspects related to synchronization and centrality of complex networks, interplay between layers, and applications to logistic, biological, social, and technological fields.

 

Introduction to Focus Issue: Complex Dynamics in Networks, Multilayered Structures and Systems
Stefano Boccaletti, Regino Criado, Miguel Romance and Joaquín J. Torres

Chaos 26, 065101 (2016); http://dx.doi.org/10.1063/1.4953595


Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from CxConferences
Scoop.it!

1st Call for Abstracts: Conference on Complex Systems 2017

1st Call for Abstracts: Conference on Complex Systems 2017 | Edgar Analytics & Complex Systems | Scoop.it
The flagship conference of the Complex Systems Society will go to Latin America for the first time in 2017. The Mexican complex systems community is enthusiast to welcome colleagues to one of our richest destinations: Cancun.

The conference will include presentations by Mario Molina (Environment, Nobel Prize in Chemistry), Ranulfo Romo (neuroscience), Antonio Lazcano (origins of life), Marta González (human mobility), Dirk Brockmann (epidemiology), Stefano Battiston (economics) John Quackenbush (computational biology), and many more.

 

Important dates:
Abstract deadline                      March 10
Notifications of Acceptance      April 21
Conference                                September 17-22


Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from CxBooks
Scoop.it!

An Introduction to Transfer Entropy: Information Flow in Complex Systems

An Introduction to Transfer Entropy: Information Flow in Complex Systems | Edgar Analytics & Complex Systems | Scoop.it

T. Bossomaier, L. Barnett, M. Harré, J.T. Lizier
"An Introduction to Transfer Entropy: Information Flow in Complex Systems"
Springer, 2016.

This book considers a relatively new measure in complex systems, transfer entropy, derived from a series of measurements, usually a time series. After a qualitative introduction and a chapter that explains the key ideas from statistics required to understand the text, the authors then present information theory and transfer entropy in depth. A key feature of the approach is the authors' work to show the relationship between information flow and complexity. The later chapters demonstrate information transfer in canonical systems, and applications, for example in neuroscience and in finance.
 
The book will be of value to advanced undergraduate and graduate students and researchers in the areas of computer science, neuroscience, physics, and engineering.

 

SpringerLink access to PDFs: http://bit.ly/te-book-2016

Springer hard copy listing: http://bit.ly/te-book-2016-hardcopy

Amazon listing: http://amzn.to/2f5YdYW


Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from Papers
Scoop.it!

Transfer entropy in continuous time, with applications to jump and neural spiking processes

Transfer entropy has been used to quantify the directed flow of information between source and target variables in many complex systems. Originally formulated in discrete time, we provide a framework for considering transfer entropy in continuous time systems. By appealing to a measure theoretic formulation we generalise transfer entropy, describing it in terms of Radon-Nikodym derivatives between measures of complete path realisations. The resulting formalism introduces and emphasises the idea that transfer entropy is an expectation of an individually fluctuating quantity along a path, in the same way we consider the expectation of physical quantities such as work and heat. We recognise that transfer entropy is a quantity accumulated over a finite time interval, whilst permitting an associated instantaneous transfer entropy rate. We use this approach to produce an explicit form for the transfer entropy for pure jump processes, and highlight the simplified form in the specific case of point processes (frequently used in neuroscience to model neural spike trains). We contrast our approach with previous attempts to formulate information flow between continuous time point processes within a discrete time framework, which incur issues that our continuous time approach naturally avoids. Finally, we present two synthetic spiking neuron model examples to exhibit the pertinent features of our formalism, namely that the information flow for point processes consists of discontinuous jump contributions (at spikes in the target) interrupting a continuously varying contribution (relating to waiting times between target spikes).

 

Transfer entropy in continuous time, with applications to jump and neural spiking processes

Richard E. Spinney, Mikhail Prokopenko, Joseph T. Lizier


Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from Papers
Scoop.it!

Percolation in real multiplex networks

We present an exact mathematical framework able to describe site-percolation transitions in real multiplex networks. Specifically, we consider the average percolation diagram valid over an infinite number of random configurations where nodes are present in the system with given probability. The approach relies on the locally treelike ansatz, so that it is expected to accurately reproduce the true percolation diagram of sparse multiplex networks with negligible number of short loops. The performance of our theory is tested in social, biological, and transportation multiplex graphs. When compared against previously introduced methods, we observe improvements in the prediction of the percolation diagrams in all networks analyzed. Results from our method confirm previous claims about the robustness of real multiplex networks, in the sense that the average connectedness of the system does not exhibit any significant abrupt change as its individual components are randomly destroyed.

 

Percolation in real multiplex networks

Ginestra Bianconi, Filippo Radicchi


Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from Papers
Scoop.it!

Learning to Perform Physics Experiments via Deep Reinforcement Learning

When encountering novel object, humans are able to infer a wide range of physical properties such as mass, friction and deformability by interacting with them in a goal driven way. This process of active interaction is in the same spirit of a scientist performing an experiment to discover hidden facts. Recent advances in artificial intelligence have yielded machines that can achieve superhuman performance in Go, Atari, natural language processing, and complex control problems, but it is not clear that these systems can rival the scientific intuition of even a young child. In this work we introduce a basic set of tasks that require agents to estimate hidden properties such as mass and cohesion of objects in an interactive simulated environment where they can manipulate the objects and observe the consequences. We found that state of art deep reinforcement learning methods can learn to perform the experiments necessary to discover such hidden properties. By systematically manipulating the problem difficulty and the cost incurred by the agent for performing experiments, we found that agents learn different strategies that balance the cost of gathering information against the cost of making mistakes in different situations.

 

Learning to Perform Physics Experiments via Deep Reinforcement Learning

Misha Denil, Pulkit Agrawal, Tejas D Kulkarni, Tom Erez, Peter Battaglia, Nando de Freitas


Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from CxConferences
Scoop.it!

GECCO 2017

GECCO 2017 | Edgar Analytics & Complex Systems | Scoop.it
The Genetic and Evolutionary Computation Conference (GECCO) in 2017 will present the latest high-quality results in genetic and evolutionary computation. Topics include: genetic algorithms, genetic programming, ant colony optimization and swarm intelligence, complex systems (artificial life/robotics/evolvable hardware/generative and developmental systems/artificial immune systems), digital entertainment technologies and arts, evolutionary combinatorial optimization and metaheuristics, evolutionary machine learning, evolutionary multiobjective optimization, evolutionary numerical optimization, real world applications, search-based software engineering (including self-* search), theory and more.

 

2017 Genetic and Evolutionary Computation Conference (GECCO 2017)
July, 2017, Berlin, Germany
http://gecco-2017.sigevo.org/


Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from Papers
Scoop.it!

Evidence of Shared Aspects of Complexity Science and Quantum Phenomena

Complexity science concepts of emergence, self-organization, and feedback suggest that descriptions of systems and events are subjective, incomplete, and impermanent-similar to what we observe in quantum phenomena. Complexity science evinces an increasingly compelling alternative to reductionism for describing physical phenomena, now that shared aspects of complexity science and quantum phenomena are being scientifically substantiated. Establishment of a clear connection between chaotic complexity and quantum entanglement in small quantum systems indicates the presence of common processes involved in thermalization in large and small-scale systems. Recent findings in the fields of quantum physics, quantum biology, and quantum cognition demonstrate evidence of the complexity science characteristics of sensitivity to initial conditions and emergence of self-organizing systems. Efficiencies in quantum superposition suggest a new paradigm in which our very notion of complexity depends on which information theory we choose to employ.

 

Evidence of Shared Aspects of Complexity Science and Quantum Phenomena
Cynthia Larson

Cosmos and History: The Journal of Natural and Social Philosophy, Vol 12, No 2 (2016)


Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from Papers
Scoop.it!

Multimodel agent-based simulation environment for mass-gatherings and pedestrian dynamics

• A multimodel agent-based simulation environment (PULSE) is presented.
• Model integration techniques suggested: common space and commonly controlled agents.
• Crowd pressure metrics for simulating crushing and asphyxia in crowds are proposed.
• Simulations of evacuation from cinema building to the city streets are carried out.

 

Multimodel agent-based simulation environment for mass-gatherings and pedestrian dynamics
Vladislav Karbovskii, Daniil Voloshin, Andrey Karsakov, Alexey Bezgodov, Carlos Gershenson

Future Generation Computer Systems


Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from Papers
Scoop.it!

The Self-Organizing Society: The Role of Institutions

Is it possible to constrain a human society in such a way that self-organization will thereafter tend to produce outcomes that advance the goals of the society? Such a society would be self-organizing in the sense that individuals who pursue only their own interests would none-the-less act in the interests of the society as a whole, irrespective of any intention to do so. I sketch an agent-based model that identifies the conditions that must be met if such a self-organizing society is to emerge. The model draws heavily on an understanding of how self-organizing societies have emerged repeatedly during the evolution of life on Earth (e.g. evolution has produced societies of molecular processes, of simple cells, of eukaryote cells and of multicellular organisms). The model demonstrates that the key enabling requirement for a self-organizing society is ‘consequence-capture’. Broadly this means that all agents in the society must capture sufficient of the benefits (and harms) that are produced by the impact of their actions on the goals of the society. If this condition is not met, agents that invest resources in actions that produce societal benefits will tend to be out-competed by those that do not. This ‘consequence-capture’ condition can be met where a society is managed by appropriate systems of evolvable constraints that suppress free riders and support pro-social actions. In human societies these constraints include institutions such as systems of governance and social norms. If a self-organizing society is to emerge, consequence-capture must occur for all agents in the society, including those involved in the establishment and adaptation of institutions. By implementing consequence-capture, appropriate institutions can produce a self-organizing society in which the interests of all agents (including individuals, associations, firms, multi-national corporations, political organizations, institutions and governments) are aligned with those of the society as a whole.

 

The Self-Organizing Society: The Role of Institutions
John E. Stewart


Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from Papers
Scoop.it!

The price of complexity in financial networks

Estimating systemic risk in networks of financial institutions represents, today, a major challenge in both science and financial policy making. This work shows how the increasing complexity of the network of contracts among institutions comes with the price of increasing inaccuracy in the estimation of systemic risk. The paper offers a quantitative method to estimate systemic risk and its accuracy.

 

The price of complexity in financial networks
Stefano Battiston, Guido Caldarelli, Robert M. May, Tarik Roukny, and Joseph E. Stiglitz

PNAS vol. 113 no. 36 


Via Samir, Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from CxBooks
Scoop.it!

Computational Personality Analysis | Yair Neuman

Computational Personality Analysis | Yair Neuman | Edgar Analytics & Complex Systems | Scoop.it

The emergence of intelligent technologies, sophisticated natural language processing methodologies and huge textual repositories, invites a new approach for the challenge of automatically identifying personality dimensions through the analysis of textual data. This short book aims to (1) introduce the challenge of computational personality analysis, (2) present a unique approach to personality analysis and (3) illustrate this approach through case studies and worked-out examples.
This book is of special relevance to psychologists, especially those interested in the new insights offered by new computational and data-intensive tools, and to computational social scientists interested in human personality and language processing.

 

Computational Personality Analysis: Introduction, Practical Applications and Novel Directions
Neuman, Yair


Via Complexity Digest
more...
No comment yet.
Rescooped by Nuno Edgar Fernandes from Papers
Scoop.it!

Combining satellite imagery and machine learning to predict poverty

Reliable data on economic livelihoods remain scarce in the developing world, hampering efforts to study these outcomes and to design policies that improve them. Here we demonstrate an accurate, inexpensive, and scalable method for estimating consumption expenditure and asset wealth from high-resolution satellite imagery. Using survey and satellite data from five African countries—Nigeria, Tanzania, Uganda, Malawi, and Rwanda—we show how a convolutional neural network can be trained to identify image features that can explain up to 75% of the variation in local-level economic outcomes. Our method, which requires only publicly available data, could transform efforts to track and target poverty in developing countries. It also demonstrates how powerful machine learning techniques can be applied in a setting with limited training data, suggesting broad potential application across many scientific domains.

 

Combining satellite imagery and machine learning to predict poverty
Neal Jean, Marshall Burke, Michael Xie, W. Matthew Davis, David B. Lobell, Stefano Ermon

Science  19 Aug 2016:
Vol. 353, Issue 6301, pp. 790-794
DOI: 10.1126/science.aaf7894


Via Complexity Digest
more...
No comment yet.