Deep learningDeep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.
Machine learningMachine learning (ML) is an umbrella term for solving problems for which development of algorithms by human programmers would be cost-prohibitive, and instead the problems are solved by helping machines 'discover' their 'own' algorithms, without needing to be explicitly told what to do by any human-developed algorithms. Recently, generative artificial neural networks have been able to surpass results of many previous approaches.
Open scienceOpen science is the movement to make scientific research (including publications, data, physical samples, and software) and its dissemination accessible to all levels of society, amateur or professional. Open science is transparent and accessible knowledge that is shared and developed through collaborative networks. It encompasses practices such as publishing open research, campaigning for open access, encouraging scientists to practice open-notebook science (such as openly sharing data and code), broader dissemination and engagement in science and generally making it easier to publish, access and communicate scientific knowledge.
Scientific methodThe scientific method is an empirical method for acquiring knowledge that has characterized the development of science since at least the 17th century (with notable practitioners in previous centuries; see the article history of scientific method for additional detail.) It involves careful observation, applying rigorous skepticism about what is observed, given that cognitive assumptions can distort how one interprets the observation.
Open scientific dataOpen scientific data or open research data is a type of open data focused on publishing observations and results of scientific activities available for anyone to analyze and reuse. A major purpose of the drive for open data is to allow the verification of scientific claims, by allowing others to look at the reproducibility of results, and to allow data from many sources to be integrated to give new knowledge. The modern concept of scientific data emerged in the second half of the 20th century, with the development of large knowledge infrastructure to compute scientific information and observation.
Scientific communityThe scientific community is a diverse network of interacting scientists. It includes many "sub-communities" working on particular scientific fields, and within particular institutions; interdisciplinary and cross-institutional activities are also significant. Objectivity is expected to be achieved by the scientific method. Peer review, through discussion and debate within journals and conferences, assists in this objectivity by maintaining the quality of research methodology and interpretation of results.
DataIn common usage and statistics, data (USˈdætə; UKˈdeɪtə) is a collection of discrete or continuous values that convey information, describing the quantity, quality, fact, statistics, other basic units of meaning, or simply sequences of symbols that may be further interpreted formally. A datum is an individual value in a collection of data. Data is usually organized into structures such as tables that provide additional context and meaning, and which may themselves be used as data in larger structures.
Deep reinforcement learningDeep reinforcement learning (deep RL) is a subfield of machine learning that combines reinforcement learning (RL) and deep learning. RL considers the problem of a computational agent learning to make decisions by trial and error. Deep RL incorporates deep learning into the solution, allowing agents to make decisions from unstructured input data without manual engineering of the state space. Deep RL algorithms are able to take in very large inputs (e.g.
Center for Open ScienceThe Center for Open Science is a non-profit technology organization based in Charlottesville, Virginia with a mission to "increase the openness, integrity, and reproducibility of scientific research." Brian Nosek and Jeffrey Spies founded the organization in January 2013, funded mainly by the Laura and John Arnold Foundation and others. The organization began with work in reproducibility of psychology research, with the large-scale initiative Reproducibility Project: Psychology.
Computational complexityIn computer science, the computational complexity or simply complexity of an algorithm is the amount of resources required to run it. Particular focus is given to computation time (generally measured by the number of needed elementary operations) and memory storage requirements. The complexity of a problem is the complexity of the best algorithms that allow solving the problem. The study of the complexity of explicitly given algorithms is called analysis of algorithms, while the study of the complexity of problems is called computational complexity theory.
Open researchOpen research is research that is openly accessible by others. Those who publish research in this way are often concerned with making research more transparent, more collaborative, more wide-reaching, and more efficient. Open research aims to make both research methods and the resulting data freely available, often via the internet, in order to support reproducibility and, potentially, massively distributed research collaboration. In this regard, it is related to both open source software and citizen science.
Adversarial machine learningAdversarial machine learning is the study of the attacks on machine learning algorithms, and of the defenses against such attacks. A survey from May 2020 exposes the fact that practitioners report a dire need for better protecting machine learning systems in industrial applications. To understand, note that most machine learning techniques are mostly designed to work on specific problem sets, under the assumption that the training and test data are generated from the same statistical distribution (IID).
Computational resourceIn computational complexity theory, a computational resource is a resource used by some computational models in the solution of computational problems. The simplest computational resources are computation time, the number of steps necessary to solve a problem, and memory space, the amount of storage needed while solving the problem, but many more complicated resources have been defined. A computational problem is generally defined in terms of its action on any valid input.
Computational complexity theoryIn theoretical computer science and mathematics, computational complexity theory focuses on classifying computational problems according to their resource usage, and relating these classes to each other. A computational problem is a task solved by a computer. A computation problem is solvable by mechanical application of mathematical steps, such as an algorithm. A problem is regarded as inherently difficult if its solution requires significant resources, whatever the algorithm used.
Computational problemIn theoretical computer science, a computational problem is a problem that may be solved by an algorithm. For example, the problem of factoring "Given a positive integer n, find a nontrivial prime factor of n." is a computational problem. A computational problem can be viewed as a set of instances or cases together with a, possibly empty, set of solutions for every instance/case. For example, in the factoring problem, the instances are the integers n, and solutions are prime numbers p that are the nontrivial prime factors of n.
Scientific misconductScientific misconduct is the violation of the standard codes of scholarly conduct and ethical behavior in the publication of professional scientific research. A Lancet review on Handling of Scientific Misconduct in Scandinavian countries provides the following sample definitions, reproduced in The COPE report 1999: Danish definition: "Intention or gross negligence leading to fabrication of the scientific message or a false credit or emphasis given to a scientist" Swedish definition: "Intention[al] distortion of the research process by fabrication of data, text, hypothesis, or methods from another researcher's manuscript form or publication; or distortion of the research process in other ways.
Data analysisData analysis is the process of inspecting, cleansing, transforming, and modeling data with the goal of discovering useful information, informing conclusions, and supporting decision-making. Data analysis has multiple facets and approaches, encompassing diverse techniques under a variety of names, and is used in different business, science, and social science domains. In today's business world, data analysis plays a role in making decisions more scientific and helping businesses operate more effectively.
Big dataBig data primarily refers to data sets that are too large or complex to be dealt with by traditional data-processing application software. Data with many entries (rows) offer greater statistical power, while data with higher complexity (more attributes or columns) may lead to a higher false discovery rate. Though used sometimes loosely partly because of a lack of formal definition, the interpretation that seems to best describe big data is the one associated with a large body of information that we could not comprehend when used only in smaller amounts.
Scientific literatureScientific literature comprises academic papers that report original empirical and theoretical work in the natural and social sciences. Within a field of research, relevant papers are often referred to as "the literature". Academic publishing is the process of contributing the results of one's research into the literature, which often requires a peer-review process. Original scientific research published for the first time in scientific journals is called the primary literature.
Extreme learning machineExtreme learning machines are feedforward neural networks for classification, regression, clustering, sparse approximation, compression and feature learning with a single layer or multiple layers of hidden nodes, where the parameters of hidden nodes (not just the weights connecting inputs to hidden nodes) need to be tuned. These hidden nodes can be randomly assigned and never updated (i.e. they are random projection but with nonlinear transforms), or can be inherited from their ancestors without being changed.
