Semi-Automatic Ground Environment

The Semi-Automated Ground Environment (SAGE) was a system of large computers and associated networking equipment that coordinated data from many radar sites and processed it to produce a single unified image of the airspace over a wide area. SAGE directed and controlled the NORAD response to a possible Soviet air attack, operating in this role from the late 1950s into the 1980s. The processing power behind SAGE was supplied by the largest discrete component-based computer ever built, the AN/FSQ-7, manufactured by IBM. Each SAGE Direction Center (DC) housed an FSQ-7 which occupied an entire floor, approximately 22,000 square feet (2,000 m2) not including supporting equipment. The FSQ-7 was actually two computers, "A" side and "B" side. Computer processing was switched from "A" side to "B" side on a regular basis, allowing maintenance on the unused side. Information was fed to the DCs from a network of radar stations as well as readiness information from various defense sites. The computers, based on the raw radar data, developed "tracks" for the reported targets, and automatically calculated which defenses were within range. Operators used light guns to select targets on-screen for further information, select one of the available defenses, and issue commands to attack. These commands would then be automatically sent to the defense site via teleprinter. Connecting the various sites was an enormous network of telephones, modems and teleprinters. Later additions to the system allowed SAGE's tracking data to be sent directly to CIM-10 Bomarc missiles and some of the US Air Force's interceptor aircraft in-flight, directly updating their autopilots to maintain an intercept course without operator intervention. Each DC also forwarded data to a Combat Center (CC) for "supervision of the several sectors within the division" ("each combat center [had] the capability to coordinate defense for the whole nation"). SAGE became operational in the late 1950s and early 1960s at an estimated total cost between 8 and 12 billion dollars, four times the cost of the Manhattan Project. Throughout its development, there were continual concerns about its real ability to deal with large attacks, and the Operation Sky Shield tests showed that only about one-fourth of enemy bombers would have been intercepted. Nevertheless, SAGE was the backbone of NORAD's air defense system into the 1980s, by which time the tube-based FSQ-7s were increasingly costly to maintain and completely outdated. Today the same command and control task is carried out by microcomputers, based on the same basic underlying data. == Background == === Earlier systems === Just prior to World War II, Royal Air Force (RAF) tests with the new Chain Home (CH) radars had demonstrated that relaying information to the fighter aircraft directly from the radar sites was not feasible. The radars determined the map coordinates of the enemy, but could generally not see the fighters at the same time. This meant the fighters had to be able to determine where to fly to perform an interception but were often unaware of their own exact location and unable to calculate an interception while also flying their aircraft. The solution was to send all of the radar information to a central control station where operators collated the reports into single tracks, and then reported these tracks to the airbases, or sectors. The sectors used additional systems to track their own aircraft, plotting both on a single large map. Operators viewing the map could then see what direction their fighters would have to fly to approach their targets and relay that simply by telling them to fly along a certain heading or vector. This Dowding system was the first ground-controlled interception (GCI) system of large scale, covering the entirety of the UK. It proved enormously successful during the Battle of Britain, and is credited as being a key part of the RAF's success. The system was slow, often providing information that was up to five minutes out of date. Against propeller driven bombers flying at perhaps 225 miles per hour (362 km/h) this was not a serious concern, but it was clear the system would be of little use against jet-powered bombers flying at perhaps 600 miles per hour (970 km/h). The system was extremely expensive in manpower terms, requiring hundreds of telephone operators, plotters and trackers in addition to the radar operators. This was a serious drain on manpower, making it difficult to expand the network. The idea of using a computer to handle the task of taking reports and developing tracks had been explored beginning late in the war. By 1944, analog computers had been installed at the CH stations to automatically convert radar readings into map locations, eliminating two people. Meanwhile, the Royal Navy began experimenting with the Comprehensive Display System (CDS), another analog computer that took X and Y locations from a map and automatically generated tracks from repeated inputs. Similar systems began development with the Royal Canadian Navy, DATAR, and the US Navy, the Naval Tactical Data System (NTDS). A similar system was also specified for the Nike SAM project, specifically referring to a US version of CDS, coordinating the defense over a battle area so that multiple batteries did not fire on a single target. All of these systems were relatively small in geographic scale, generally tracking within a city-sized area. === Valley Committee === When the Soviet Union tested its first atomic bomb in August 1949, the topic of air defense of the US became important for the first time. A study group, the "Air Defense Systems Engineering Committee", was set up under the direction of Dr. George Valley to consider the problem and is known to history as the "Valley Committee". Their December report noted a key problem in air defense using ground-based radars. A bomber approaching a radar station would detect the signals from the radar long before the reflection off the bomber was strong enough to be detected by the station. The committee suggested that when this occurred, the bomber would descend to low altitude, thereby greatly limiting the radar horizon, allowing the bomber to fly past the station undetected. Although flying at low altitude greatly increased fuel consumption, the team calculated that the bomber would only need to do this for about 10% of its flight, making the fuel penalty acceptable. The only solution to this problem was to build a huge number of stations with overlapping coverage. At that point the problem became one of managing the information. Manual plotting was ruled out as too slow, and a computerized solution was the only possibility. To handle this task, the computer would need to be fed information directly, eliminating any manual translation by phone operators, and it would have to be able to analyze that information and automatically develop tracks. A system tasked with defending cities against the predicted future Soviet bomber fleet would have to be dramatically more powerful than the models used in the NTDS or DATAR. The Committee then had to consider whether or not such a computer was possible. The Valley Committee was introduced to Jerome Wiesner, associate director of the Research Laboratory of Electronics at MIT. Wiesner noted that the Servomechanisms Laboratory had already begun development of a machine that might be fast enough. This was the Whirlwind I, originally developed for the Office of Naval Research as a general purpose flight simulator that could simulate any current or future aircraft by changing its software. Wiesner introduced the Valley Committee to Whirlwind's project lead, Jay Forrester, who convinced him that Whirlwind was sufficiently capable. In September 1950, an early microwave early-warning radar system at Hanscom Field was connected to Whirlwind using a custom interface developed by Forrester's team. An aircraft was flown past the site, and the system digitized the radar information and successfully sent it to Whirlwind. With this demonstration, the technical concept was proven. Forrester was invited to join the committee. === Project Charles === With this successful demonstration, Louis Ridenour, chief scientist of the Air Force, wrote a memo stating "It is now apparent that the experimental work necessary to develop, test, and evaluate the systems proposals made by ADSEC will require a substantial amount of laboratory and field effort." Ridenour approached MIT President James Killian with the aim of beginning a development lab similar to the war-era Radiation Laboratory that made enormous progress in radar technology. Killian was initially uninterested, desiring to return the school to its peacetime civilian charter. Ridenour eventually convinced Killian the idea was sound by describing the way the lab would lead to the development of a local electronics industry based on the needs of the lab and the students who would leave the lab to start their

Leakage (machine learning)

In statistics and machine learning, leakage (also known as data leakage or target leakage) refers to the use of information during model training that would not be available at prediction time. This results in overly optimistic performance estimates, as the model appears to perform better during evaluation than it actually would in a production environment. Leakage is often subtle and indirect, making it difficult to detect and eliminate. It can lead a statistician or modeler to select a suboptimal model, which may be outperformed by a leakage-free alternative. == Leakage modes == Leakage can occur at multiple stages of the machine learning workflow. Broadly, its sources can be divided into two categories: those arising from features and those arising from training examples. === Feature leakage === Feature or column-wise leakage is caused by the inclusion of columns which are one of the following: a duplicate label, a proxy for the label, or the label itself. These features, known as anachronisms, will not be available when the model is used for predictions, and result in leakage if included when the model is trained. For example, including a "MonthlySalary" column when predicting "YearlySalary"; or "MinutesLate" when predicting "IsLate". === Training example leakage === Row-wise leakage is caused by improper sharing of information between rows of data. Types of row-wise leakage include: Premature featurization; leaking from premature featurization before Cross-validation/Train/Test split (must fit MinMax/ngrams/etc on only the train split, then transform the test set) Duplicate rows between train/validation/test (for example, oversampling a dataset to pad its size before splitting; or, different rotations/augmentations of a single image; bootstrap sampling before splitting; or duplicating rows to up sample the minority class) Non-independent and identically distributed random (non-IID) data Time leakage (for example, splitting a time-series dataset randomly instead of newer data in test set using a train/test split or rolling-origin cross-validation) Group leakage—not including a grouping split column (for example, Andrew Ng's group had 100k x-rays of 30k patients, meaning ~3 images per patient. The paper used random splitting instead of ensuring that all images of a patient were in the same split. Hence the model partially memorized the patients instead of learning to recognize pneumonia in chest x-rays.) A 2023 review found data leakage to be "a widespread failure mode in machine-learning (ML)-based science", having affected at least 294 academic publications across 17 disciplines, and causing a potential reproducibility crisis. == Detection == Data leakage in machine learning can be detected through various methods, focusing on performance analysis, feature examination, data auditing, and model behavior analysis. Performance-wise, unusually high accuracy or significant discrepancies between training and test results often indicate leakage. Inconsistent cross-validation outcomes may also signal issues. Feature examination involves scrutinizing feature importance rankings and ensuring temporal integrity in time series data. A thorough audit of the data pipeline is crucial, reviewing pre-processing steps, feature engineering, and data splitting processes. Detecting duplicate entries across dataset splits is also important. For language models, the Min-K% method can detect the presence of data in a pretraining dataset. It presents a sentence suspected to be present in the pretraining dataset, and computes the log-likelihood of each token, then compute the average of the lowest K of these. If this exceeds a threshold, then the sentence is likely present. This method is improved by comparing against a baseline of the mean and variance. Analyzing model behavior can reveal leakage. Models relying heavily on counter-intuitive features or showing unexpected prediction patterns warrant investigation. Performance degradation over time when tested on new data may suggest earlier inflated metrics due to leakage. Advanced techniques include backward feature elimination, where suspicious features are temporarily removed to observe performance changes. Using a separate hold-out dataset for final validation before deployment is advisable.

Reference data

Reference data is data used to classify or categorize other data. Typically, they are static or slowly changing over time. Examples of reference data include: Units of measurement Country codes Corporate codes Fixed conversion rates e.g., weight, temperature, and length Calendar structure and constraints Reference data sets are sometimes alternatively referred to as a "controlled vocabulary" or "lookup" data. Reference data differs from master data. While both provide context for business transactions, reference data is concerned with classification and categorisation, while master data is concerned with business entities. A further difference between reference data and master data is that a change to the reference data values may require an associated change in business process to support the change, while a change in master data will always be managed as part of existing business processes. For example, adding a new customer or sales product is part of the standard business process. However, adding a new product classification (e.g. "restricted sales item") or a new customer type (e.g. "gold level customer") will result in a modification to the business processes to manage those items. == Externally-defined reference data == For most organisations, most or all reference data is defined and managed within that organisation. Some reference data, however, may be externally defined and managed, for example by standards organizations. An example of externally defined reference data is the set of country codes as defined in ISO 3166-1. == Reference data management == Curating and managing reference data is key to ensuring its quality and thus fitness for purpose. All aspects of an organisation, operational and analytical, are greatly dependent on the quality of an organization's reference data. Without consistency across business process or applications, for example, similar things may be described in quite different ways. Reference data gain in value when they are widely re-used and widely referenced. Examples of good practice in reference data management include: Formalize the reference data management Use external reference data as much as possible Govern the reference data specific to your enterprise Manage reference data at enterprise level Version control your reference data

Organizational metacognition

Organizational metacognition is knowing what an organization knows, a concept related to metacognition, organizational learning, the learning organization and sensemaking. It is used to describe how organizations and teams develop an awareness of their own thinking, learning how to learn, where awareness of ignorance can motivate learning. The organizational deutero-learning concept identified by Argyris and Schon defines when organizations learn how to carry out single-loop and double-loop learning. It has also been described as learning how to learn through a process of collaborative inquiry and reflection (evaluative inquiry). "When an organization engages in deutero-learning its members learn about the previous context for learning. They reflect on and inquire into previous episodes of organizational learning, or failure to learn. They discover what they did that facilitated or inhibited learning, they invent new strategies for learning, they produce these strategies, and they evaluate and generalize what they have produced" Learning what facilitates and inhibits learning enables organizations to develop new strategies to develop their knowledge. For example, identification of a gap between perceived performance (such as satisfaction) and actual performance (outcomes) creates an awareness that makes the organization understand that learning needs to occur, driving appropriate changes to the environment and processes. == Learning prototypes == Wijnhoven (2001) grouped four learning prototypes that best meet learning needs, the match between these needs and learning norms dictating an organization's learning capabilities; deutero-learning is the acquisition of these capabilities. knowledge gap analysis classification of problems to select operationally required knowledge and skills coping with organizational tremors and jolts by anticipation, response and adjustments of behavioural repertoires decisional uncertainty measurement == Terminological ambiguities == Organizational metacognition and organizational deutero-learning have both been described as the concept or phenomenon where organizations learn how to learn. Argyris and Schon (1978) place deutero-learning into their cognitive theory of action framework, neglecting aspects of adaptive behaviour and context core to Bateson's (1972) original definitions. In order to resolve terminological ambiguities, Visser (2007) reviewed and reformulated the concept of deutero-learning as, "the behavioral adaptation to patterns of conditioning in relationships in organizational contexts, distinguishing it from meta-learning and planned learning" (pg. 659). == Significance == Organizational metacognition is considered a key norm to the prescriptive concept of the learning organization. Its significance has been recognized by industry, the military and in disaster response. == Examples in practice == Examples of poor metacognition (deutero-learning) have been described in knowledge network environments, "Knowledge networking is important to most competitive enterprises today. Enterprise knowledge is becoming ever more specialized in nature, so no single person or organization can know everything in detail. Hence addressing complex, multidisciplinary problems requires developing and accessing a network of knowledgeable people and organizations. The problem is, many otherwise knowledgeable people and organizations are not fully aware of their knowledge networks, and even more problematic, they are not aware that they are not aware. This focuses our attention toward organizational metacognition."

Best arm identification

Best arm identification (BAI) is a sequential one-player game where the player has to find the best action (arm) among a list of actions (arms) by collecting information in the most efficient way. It is a multi-armed bandit game as a player only gets information about an arm by playing it. The most common objective in multi-armed bandit games is to minimize the regret (i.e., play the best action as much as possible), but in BAI, the goal is to find the best arm as efficiently as possible. This problem naturally arises in scenarios such as adaptive clinical trials where the number of patients is limited and the quantification of the confidence in a treatment is important. It also arises in hyperparameter optimization where the goal is to find the optimal choice of hyperparameters for an algorithm with the smallest possible number of experiments, as it can be costly in terms of time, energy, or money. == Stochastic multi-armed bandit == The stochastic multi-armed bandit (MAB) is a sequential game with one player and K {\displaystyle K} actions (arms). Each arm has an unknown probability distribution associated with it. At each turn, the player has to choose one action and receive an observation from the probability distribution associated with the arm. The more you play an arm, the more you get information on its probability distribution. === Best arm identification === In BAI the goal is to find the arm that has the probability distribution with the highest mean. BAI may be either fixed confidence or fixed horizon. In a fixed-confidence game, a confidence level δ {\displaystyle \delta } is fixed at the beginning of the game and the goal is to find the best arm with this confidence level in as few turns as possible. In a fixed horizon game, the number of turns T {\displaystyle T} is fixed, and the goal is to find the best arm with the highest possible confidence in T {\displaystyle T} turns. === Math formalisation === We have one player and K {\displaystyle K} actions (arms). Behind each arm k ∈ { 1 , … , K } {\displaystyle k\in \{1,\ldots ,K\}} lies an unknown distribution ν k {\displaystyle \nu _{k}} with mean μ k {\displaystyle \mu _{k}} . Each distribution ν k {\displaystyle \nu _{k}} belongs to a known family D {\displaystyle {\mathcal {D}}} (such as the set of Gaussian distributions or Bernoulli distributions). At each time step t {\displaystyle t} , the player selects an arm a t {\displaystyle a_{t}} and observes an independent sample X t ∼ ν a t {\displaystyle X_{t}\sim \nu _{a_{t}}} from the corresponding distribution. We will note μ ∗ := max μ a {\displaystyle \mu ^{}:=\max \mu _{a}} the highest mean. An arm a {\displaystyle a} that satisfies μ a = μ ∗ {\displaystyle \mu _{a}=\mu ^{}} is called an optimal arm; otherwise it is called suboptimal arm. In best arm identification (BAI) the objective is to identify an optimal arm. Two main settings for BAI appear in the literature: Fixed confidence: In this setting, one typically assumes that there exists a unique optimal arm. A confidence level δ ∈ ( 0 , 1 ) {\displaystyle \delta \in (0,1)} is specified at the beginning. The algorithm must stop at some finite stopping time τ δ < + ∞ {\displaystyle \tau _{\delta }<+\infty } and return an arm a ^ τ δ {\displaystyle {\hat {a}}_{\tau _{\delta }}} such that the probability of error is bounded: P ( a ^ τ δ ≠ a ∗ ) ≤ δ {\displaystyle \mathbb {P} ({\hat {a}}_{\tau _{\delta }}\neq a^{})\leq \delta } . The objective is to minimize the expected sample complexity E [ τ δ ] {\displaystyle \mathbb {E} [\tau _{\delta }]} . Such a setting appears, for example, when a constraint on the confidence is required (for example, if we require a confidence level of 95%, so δ = 1 − 0.95 = 0.05 {\displaystyle \delta =1-0.95=0.05} ). Fixed horizon: In this setting, the number of samples T {\displaystyle T} is fixed in advance. The goal is to design an algorithm that minimizes the probability of misidentifying the optimal arm: P ( a ^ T ≠ a ∗ ) {\displaystyle \mathbb {P} ({\hat {a}}_{T}\neq a^{})} . This setting appears when the number of experiments is limited (for drug tests, the number of patients can be fixed in advance). === Example of simple modelling === In the case where we have K {\displaystyle K} treatments and we want to be sure with a confidence level of 95% which treatment is the best to heal a specific disease. Each treatment heals or does not heal the disease with a probability μ k {\displaystyle \mu _{k}} , which means that each distribution is a Bernoulli distribution, so D {\displaystyle {\mathcal {D}}} is the set of Bernoulli distributions. We can use a BAI algorithm to minimize E [ τ 0.05 ] {\displaystyle \mathbb {E} [\tau _{0.05}]} , the number of patients required to find the best treatment with probability 95%. == Applications == Best arm identification naturally arises in several practical domains: Adaptive clinical trials: The objective is to identify the most effective treatment based on sequentially collected patient data. Each treatment can be modeled as having an underlying distribution of outcomes. The goal is to identify the treatment with the highest expected outcome with high confidence (fixed confidence setting δ {\displaystyle \delta } ) while minimizing the number of drug test patients (minimise E [ τ δ ] {\displaystyle \mathbb {E} [\tau _{\delta }]} ), as it costs to pay patients for this and we would like to use as little as possible less effective drugs. Hyperparameter tuning: Selecting the best configuration for machine learning models efficiently by treating each hyperparameter setting as an arm. The goal is to find the best hyperparameter with as few experiments possible as experiments are costly in time and in energy == Fixed confidence level == In the fixed-confidence setting, the goal is to design an algorithm that identifies the best arm with a prescribed confidence level δ {\displaystyle \delta } while minimizing the expected number of samples. Any such algorithm requires two key components: Stopping rule: A decision criterion that determines when to stop sampling. Formally, this defines a stopping time τ δ {\displaystyle \tau _{\delta }} and returns an arm a ^ τ δ {\displaystyle {\hat {a}}_{\tau _{\delta }}} such that P ( a ^ τ δ ≠ a ⋆ ) ≤ δ {\displaystyle \mathbb {P} ({\hat {a}}_{\tau _{\delta }}\neq a^{\star })\leq \delta } and P ( τ δ < + ∞ ) = 1 {\displaystyle \mathbb {P} (\tau _{\delta }<+\infty )=1} . Sampling rule: A policy π {\displaystyle \pi } that, at each round t {\displaystyle t} , selects the next arm to sample a t {\displaystyle a_{t}} based on all previous observations ( a s , X s ) s < t {\displaystyle (a_{s},X_{s})_{s

Statistical relational learning

Statistical relational learning (SRL) is a subdiscipline of artificial intelligence and machine learning that is concerned with domain models that exhibit both uncertainty (which can be dealt with using statistical methods) and complex, relational structure. Typically, the knowledge representation formalisms developed in SRL use (a subset of) first-order logic to describe relational properties of a domain in a general manner (universal quantification) and draw upon probabilistic graphical models (such as Bayesian networks or Markov networks) to model the uncertainty; some also build upon the methods of inductive logic programming. Significant contributions to the field have been made since the late 1990s. As is evident from the characterization above, the field is not strictly limited to learning aspects; it is equally concerned with reasoning (specifically probabilistic inference) and knowledge representation. Therefore, alternative terms that reflect the main foci of the field include statistical relational learning and reasoning (emphasizing the importance of reasoning) and first-order probabilistic languages (emphasizing the key properties of the languages with which models are represented). Another term that is sometimes used in the literature is relational machine learning (RML). == Canonical tasks == A number of canonical tasks are associated with statistical relational learning, the most common ones being. collective classification, i.e. the (simultaneous) prediction of the class of several objects given objects' attributes and their relations link prediction, i.e. predicting whether or not two or more objects are related link-based clustering, i.e. the grouping of similar objects, where similarity is determined according to the links of an object, and the related task of collaborative filtering, i.e. the filtering for information that is relevant to an entity (where a piece of information is considered relevant to an entity if it is known to be relevant to a similar entity) social network modelling object identification/entity resolution/record linkage, i.e. the identification of equivalent entries in two or more separate databases/datasets == Representation formalisms == One of the fundamental design goals of the representation formalisms developed in SRL is to abstract away from concrete entities and to represent instead general principles that are intended to be universally applicable. Since there are countless ways in which such principles can be represented, many representation formalisms have been proposed in recent years. In the following, some of the more common ones are listed in alphabetical order: Bayesian logic program BLOG model Markov logic networks Multi-entity Bayesian network Probabilistic logic programs Probabilistic relational model – a Probabilistic Relational Model (PRM) is the counterpart of a Bayesian network in statistical relational learning. Probabilistic soft logic Recursive random field Relational Bayesian network Relational dependency network Relational Markov network Relational Kalman filtering

Knowledge spillover

Knowledge spillover is an exchange of ideas among individuals. Knowledge spillover is usually replaced by terminations of technology spillover, R&D spillover and/or spillover (economics) when the concept is specific to technology management and innovation economics. In knowledge management economics, knowledge spillovers are non-rival knowledge market costs incurred by a party not agreeing to assume the costs that has a spillover effect of stimulating technological improvements in a neighbor through one's own innovation. Such innovations often come from specialization within an industry. There are two kinds of knowledge spillovers: internal and external. Internal knowledge spillover occurs if there is a positive impact of knowledge between individuals within an organization that produces goods and/or services. An external knowledge spillover occurs when the positive impact of knowledge is between individuals outside of a production organization. Marshall–Arrow–Romer (MAR) spillovers, Porter spillovers and Jacobs spillovers are three types of spillovers. == Conceptualizations == === Marshall–Arrow–Romer === Marshall–Arrow–Romer (MAR) spillover has its origins in 1890, where the English economist Alfred Marshall developed a theory of knowledge spillovers. Knowledge spillovers later were extended by economists Kenneth Arrow (1962) and Paul Romer (1986). In 1992, Edward Glaeser, Hedi Kallal, José Scheinkman, and Andrei Shleifer pulled together the Marshall–Arrow–Romer views on knowledge spillovers and accordingly named the view MAR spillover in 1992. Under the Marshall–Arrow–Romer (MAR) spillover view, the proximity of firms within a common industry often affects how well knowledge travels among firms to facilitate innovation and growth. The closer the firms are to one another, the greater the MAR spillover. The exchange of ideas is largely from employee to employee, in that employees from different firms in an industry exchange ideas about new products and new ways to produce goods. The opportunity to exchange ideas that lead to innovations key to new products and improved production methods. Research on the Cambridge IT Cluster (UK) suggests that technological knowledge spillovers might only happen rarely and are less important than other cluster benefits such as labour market pooling. === Porter === Porter (1990), like MAR, argues that knowledge spillovers in specialized, geographically concentrated industries stimulate growth. He insists, however, that local competition, as opposed to local monopoly, fosters the pursuit and rapid adoption of innovation. He gives examples of Italian ceramics and gold jewellery industries, in which hundreds of firms are located together and fiercely compete to innovate since the alternative to innovation is demise. Porter's externalities are maximized in cities with geographically specialized, competitive industries. === Jacobs === Under the Jacobs spillover view, the proximity of firms from different industries affect how well knowledge travels among firms to facilitate innovation and growth. This is in contrast to MAR spillovers, which focus on firms in a common industry. The diverse proximity of a Jacobs spillover brings together ideas among individuals with different perspectives to encourage an exchange of ideas and foster innovation in an industrially diverse environment. Developed in 1969 by urbanist Jane Jacobs and John Jackson the concept that Detroit’s shipbuilding industry from the 1830s was the critical antecedent leading to the 1890s development of the auto industry in Detroit since the gasoline engine firms easily transitioned from building gasoline engines for ships to building them for automobiles. == Incoming and outgoing spillovers == Knowledge spillover has asymmetric directions. The focal entity and receives or outflows know-how to others, creating incoming and outgoing spillovers. Cassiman and Veugelers (2002) use survey data and estimate incoming and outgoing spillover and study the economic impacts. Incoming spillover increases growth opportunity and productivity improvements of receivers, while outgoing spillover leads to free rider problem in the technology competition. Chen et al. (2013) use econometric method to gauge incoming spillover, a way that applies for all companies without survey. They find that incoming spillover explains R&D profits of industrial firms. == Policy implications == As information is largely non-rival in nature, certain measures must be taken to ensure that, for the originator, the information remains a private asset. As the market cannot do this efficiently, public regulations have been implemented to facilitate a more appropriate equilibrium. As a result, the concept of intellectual property rights have developed and ensure the ability of entrepreneurs to temporarily hold on to the profitability of their ideas through patents, copyrights, trade secrets, and other governmental safeguards. Conversely, such barriers to entry prevent the exploitation of informational developments by rival firms within an industry. For example, Wang (2023) indicates that technology spillovers are reduced by 27% to 51% when trade secrets laws are implemented by the Uniform Trade Secrets Act in the US. On the other hand, when the research and development of a private firm results in a social benefit, unaccounted for within the market price, often greater than the private return of the firm's research, then a subsidy to offset the underproduction of that benefit might be offered to the firm in return for its continued output of that benefit. Government subsidies are often controversial, and while they might often result in a more appropriate social equilibrium, they could also lead to undesirable political repercussions as such a subsidy must come from taxpayers, some of whom may not directly benefit from the researching firm's subsidized knowledge spillover. The concept of knowledge spillover is also used to justify subsidies to foreign direct investment, as foreign investors help diffuse technology among local firms. == Examples == Business parks are a good specific example of concentrated businesses that may benefit from MAR spillover. Many semiconductor firms intentionally located their research and development facilities in Silicon Valley to take advantage of MAR spillover. In addition, the film industry in Los Angeles, California, and elsewhere relies on a geographic concentration of specialists (directors, producers, scriptwriters, and set designers) to bring together narrow aspects of movie-making into a final product. A general example of a knowledge spillover could be the collective growth associated with the research and development of online social networking tools like Facebook, YouTube, and Twitter. Such tools have not only created a positive feedback loop, and a host of originally unintended benefits for their users, but have also created an explosion of new software, programming platforms, and conceptual breakthroughs that have perpetuated the development of the industry as a whole. The advent of online marketplaces, the utilization of user profiles, the widespread democratization of information, and the interconnectivity between tools within the industry have all been products of each tool's individual developments. These developments have since spread outside the industry into the mainstream media as news and entertainment firms have developed their own market feedback applications within the tools themselves, and their own versions of online networking tools (e.g. CNN’s iReport).