M-DISC (Millennial Disc) is a write-once optical disc technology introduced in 2009 by Millenniata, Inc. and available as DVD and Blu-ray discs. == Overview == M-DISC's design is intended to provide archival media longevity. M-Disc claims that properly stored M-DISC DVD recordings will last up to 1000 years. The M-DISC DVD looks like a standard disc, except it is almost transparent with later DVD and BD-R M-Disks having standard and inkjet printable labels. The patents protecting the M-DISC technology assert that the data layer is a glassy carbon material that is substantially inert to oxidation and has a melting point of 200–1000 °C (392–1832 °F). M-Discs are readable by most regular DVD players made after 2005 and Blu-Ray and BDXL disc drives and writable by most made after 2011. Available recording capacities conform to standard DVD/Blu-ray sizes: 4.7 GB DVD+R to 25 GB BD-R, 50 GB BD-R and 100 GB BDXL. == History == M-DISC developer Millenniata, Inc. was co-founded by Brigham Young University professors Barry Lunt, Matthew Linford, CEO Henry O'Connell and CTO Doug Hansen. The company was incorporated on May 13, 2010, in American Fork, Utah. Millenniata, Inc. officially went bankrupt in December 2016. Under the direction of CEO Paul Brockbank, Millenniata had issued convertible debt. When the obligation for conversion was not satisfied, the company defaulted on the debt payment and the debt holders took possession of all of the company's assets. The debt holders subsequently started a new company, Yours.co, to sell M-DISCs and related services. As of the 2020s, there are only 2 licensed manufacturers of M-Discs: Ritek, sold under the Ritek and RiDATA brands, and Verbatim with co-branded discs, marketed as the "Verbatim M-DISC". 128 GB BDXL never made it to market due to the 2016 bankruptcy. Early in 2022, Verbatim changed the formulation of their M-DISC branded Blu-rays. These new discs could be written at a faster rate than the previous ones – 6× speed instead of 4×. The new discs also had different colouration and markings compared with older version. Later in the year customers accused Verbatim of selling an inferior product and deceptive marketing. Verbatim responded that the new discs were a further development of the older discs and should have the same longevity, and that the technical changes therein were responsible for the altered appearance and higher write speeds. The updated M-DISC currently sold on the market uses the same metal ablative layer (MABL) metal oxide inorganic recording layer used in many of Verbatim's regular Blu-ray products. == Durability claims == The original M-DISC DVD+R was tested according to ISO/IEC 10995:2011 and ECMA-379 with a projected rated lifespan of several hundred years in archival use. The glassy carbon layers, in theory if preserved correctly in an environment like a salt mine, could store the data for over 10,000 years before going outside of readable specifications. However, the polycarbonate plastics, which are commonly used by almost all optical media and heavily in CBRN and ballistic protective equipment due to their optical, physical impact and chemical resistant properties, have a lifespan rating of only around 1000 years before degradation. Verbatim Japan claims that M-DISCs now use a titanium layer to prevent moisture ingression and to provide environmental stability. M-DISCs sold in Japan are advertised to have a projected lifespan of 100 years or more based on internal ISO/IEC 16963 testing, while other regional Verbatim websites claim that M-DISCs have a projected lifespan of "several hundred years" based on ISO/IEC 16963 testing. == Durability testing == In 2009, testing was done by the US Department of Defense (DoD) producing the China Lake Report testing Millenniata's M-Disk DVD to current market offerings from Delkin, MAM-A, Mitsubishi, Taiyo Yuden and Verbatim with all brands using organic dyes failing to pass the series of accelerated aging tests. From 2010 to 2012, the French National Laboratory of Metrology and Testing (LNE) used high-temperature accelerated aging testing, at 90 °C (194 °F) and 85% relative humidity inside a CLIMATS Excal 5423-U, for 250 to 1000 hours with a mix of inorganic DVD+R discs from MPO, Verbatim, Maxell, Syylex and DataTresor. The summary of the tests states that Syylex Glass Master Disc was rated for 1000+ hours, DataTresor Disc 250 hours+ and M-Disk under 250 hours. The Syylex disc was a custom-ordered product that could not be burned in a consumer player when they were still purchaseable from Syylex before their bankruptcy, so it was not truly in the same category as the others. In 2016, a consumer Mol Smith did real world stress testing on the 25 GB BD-R M-Disc alongside TDK's standard BD-R 25 GB disc using a copied movie, which demonstrated the reliability of M-Disc's molding compared to standard discs; after 60 days of outdoor direct exposure the M-Disk was played without error, while the TDK disc was physically destroyed. In 2022, the NIST Interagency Report NIST IR 8387 listed the M-Disc as an acceptable archival format rated for 100+ years, citing the aforementioned 2009 and 2012 tests by the US Department of Defense and French National Laboratory of Metrology and Testing as sources. == Commercial support == While recorded discs are readable in conventional DVD and BD drives, M-disc DVDs can only be burned by drives with firmware that supports the slightly higher power mode that M-Disk requires for burning its inorganic layers, as such writing speed is typically 2× speed. Blu-ray M-discs can be both written and read in most standard Blu-ray drives and are certified by the Blu-ray Disc Association to meet all current standard specifications as of 2019. Typically, the M-Discs cost 1.5–3× the price of standard Blu-Ray discs with DVD M-Discs now having sparse availability. With the first-generation DVD M-DISCs, it was difficult to determine which was the writable side of the disc due to being near fully translucent, until coloring and later labels similar to that on standard DVD discs was added to discs to help distinguish the sides preventing user error. Asus, LG Electronics, Lite-On, Pioneer, Buffalo Technology, and Hitachi-LG produce drives that can record M-DISC media while Verbatim and Ritek produce M-DISC discs. == Adoption == The regional government of the U.S. state of Utah has used M-Disc since 2011. Some consumers and avid datahoarders have adopted the format for cold digital data storage. == Alternative technologies == === Optical === Syylex Glass Master Disc: these discs use etched glass and are only typically degradable by physical or chemical damage, but not by normal ageing inside an archival environment. Current BD 25 GB, BD-R DL 50 GB & BDXL 100 GB (three layer) and Sony's BDXL 128 GB (four layer) discs are rated for up to 50 years (Standard inorganic HTL discs). Sony's Optical Disc Archive, is an optical competitor to the LTO tape-based data storage system, currently with up to 5.5 TB cartridges of dual-sided 120mm discs, with desktop readers and automated rackmount standard archival systems allowing for large scale archival and data retrieval rated for an estimated 100+ years. Pioneer DM for Archive is a disc media and drive combination developed by Pioneer to meet the requirements laid out by the Japanese government for preservation of financial data for a minimum of 100 years. The discs use a MABL type recording layer and are manufactured with tight tolerances. Although burnable in any BD Writer, when burned in Pioneers DM for Archive writers using the DM Archiver software the media and burn quality meet ISO/IEC 18630 which defines the testing methods needed for ensuring media and burn quality. === Magnetic === Linear Tape-Open (LTO) is rated for up to 30 years in a climate-controlled environment and is currently in use by most industries, including broadcast and corporate digital data systems. The latest generation released in 2026 is LTO-10, it defines two unique cartridge types which can hold 30 TB or 40 TB each Hard disk drives are currently available up to 30 TB (HDD) capacity in 3.5-inch format and 5 TB in 2.5-inch laptop format. However, unlike optical media, they are limited to 5–25 years of operation lifespan due to inevitable mechanical failure or magnetic instability. == Gallery ==
Client honeypot
Honeypots are security devices whose value lie in being probed and compromised. Traditional honeypots are servers (or devices that expose server services) that wait passively to be attacked. Client Honeypots are active security devices in search of malicious servers that attack clients. The client honeypot poses as a client and interacts with the server to examine whether an attack has occurred. Often the focus of client honeypots is on web browsers, but any client that interacts with servers can be part of a client honeypot (for example ftp, email, ssh, etc.). There are several terms that are used to describe client honeypots. Besides client honeypot, which is the generic classification, honeyclient is the other term that is generally used and accepted. However, there is a subtlety here, as "honeyclient" is actually a homograph that could also refer to the first known open source client honeypot implementation (see below), although this should be clear from the context. == Architecture == A client honeypot is composed of three components. The first component, a queuer, is responsible for creating a list of servers for the client to visit. This list can be created, for example, through crawling. The second component is the client itself, which is able to make a requests to servers identified by the queuer. After the interaction with the server has taken place, the third component, an analysis engine, is responsible for determining whether an attack has taken place on the client honeypot. In addition to these components, client honeypots are usually equipped with some sort of containment strategy to prevent successful attacks from spreading beyond the client honeypot. This is usually achieved through the use of firewalls and virtual machine sandboxes. Analogous to traditional server honeypots, client honeypots are mainly classified by their interaction level: high or low; which denotes the level of functional interaction the server can utilize on the client honeypot. In addition to this there are also newly hybrid approaches which denotes the usage of both high and low interaction detection techniques. == High interaction == High interaction client honeypots are fully functional systems comparable to real systems with real clients. As such, no functional limitations (besides the containment strategy) exist on high interaction client honeypots. Attacks on high interaction client honeypots are detected via inspection of the state of the system after a server has been interacted with. The detection of changes to the client honeypot may indicate the occurrence of an attack against that has exploited a vulnerability of the client. An example of such a change is the presence of a new or altered file. High interaction client honeypots are very effective at detecting unknown attacks on clients. However, the tradeoff for this accuracy is a performance hit from the amount of system state that has to be monitored to make an attack assessment. Also, this detection mechanism is prone to various forms of evasion by the exploit. For example, an attack could delay the exploit from immediately triggering (time bombs) or could trigger upon a particular set of conditions or actions (logic bombs). Since no immediate, detectable state change occurred, the client honeypot is likely to incorrectly classify the server as safe even though it did successfully perform its attack on the client. Finally, if the client honeypots are running in virtual machines, then an exploit may try to detect the presence of the virtual environment and cease from triggering or behave differently. === Capture-HPC === Capture [1] is a high interaction client honeypot developed by researchers at Victoria University of Wellington, NZ. Capture differs from existing client honeypots in various ways. First, it is designed to be fast. State changes are being detected using an event based model allowing to react to state changes as they occur. Second, Capture is designed to be scalable. A central Capture server is able to control numerous clients across a network. Third, Capture is supposed to be a framework that allows to utilize different clients. The initial version of Capture supports Internet Explorer, but the current version supports all major browsers (Internet Explorer, Firefox, Opera, Safari) as well as other HTTP aware client applications, such as office applications and media players. === HoneyClient === HoneyClient [2] is a web browser based (IE/FireFox) high interaction client honeypot designed by Kathy Wang in 2004 and subsequently developed at MITRE. It was the first open source client honeypot and is a mix of Perl, C++, and Ruby. HoneyClient is state-based and detects attacks on Windows clients by monitoring files, process events, and registry entries. It has integrated the Capture-HPC real-time integrity checker to perform this detection. HoneyClient also contains a crawler, so it can be seeded with a list of initial URLs from which to start and can then continue to traverse web sites in search of client-side malware. === HoneyMonkey (dead since 2010) === HoneyMonkey [3] is a web browser based (IE) high interaction client honeypot implemented by Microsoft in 2005. It is not available for download. HoneyMonkey is state based and detects attacks on clients by monitoring files, registry, and processes. A unique characteristic of HoneyMonkey is its layered approach to interacting with servers in order to identify zero-day exploits. HoneyMonkey initially crawls the web with a vulnerable configuration. Once an attack has been identified, the server is reexamined with a fully patched configuration. If the attack is still detected, one can conclude that the attack utilizes an exploit for which no patch has been publicly released yet and therefore is quite dangerous. === SHELIA (dead since 2009) === Shelia [4] is a high interaction client honeypot developed by Joan Robert Rocaspana at Vrije Universiteit Amsterdam. It integrates with an email reader and processes each email it receives (URLs & attachments). Depending on the type of URL or attachment received, it opens a different client application (e.g. browser, office application, etc.) It monitors whether executable instructions are executed in data area of memory (which would indicate a buffer overflow exploit has been triggered). With such an approach, SHELIA is not only able to detect exploits, but is able to actually ward off exploits from triggering. === UW Spycrawler === The Spycrawler [5] developed at the University of Washington is yet another browser based (Mozilla) high interaction client honeypot developed by Moshchuk et al. in 2005. This client honeypot is not available for download. The Spycrawler is state based and detects attacks on clients by monitoring files, processes, registry, and browser crashes. Spycrawlers detection mechanism is event based. Further, it increases the passage of time of the virtual machine the Spycrawler is operating in to overcome (or rather reduce the impact of) time bombs. === Web Exploit Finder === WEF [6] is an implementation of an automatic drive-by-download – detection in a virtualized environment, developed by Thomas Müller, Benjamin Mack and Mehmet Arziman, three students from the Hochschule der Medien (HdM), Stuttgart during the summer term in 2006. WEF can be used as an active HoneyNet with a complete virtualization architecture underneath for rollbacks of compromised virtualized machines. == Low interaction == Low interaction client honeypots differ from high interaction client honeypots in that they do not utilize an entire real system, but rather use lightweight or simulated clients to interact with the server. (in the browser world, they are similar to web crawlers). Responses from servers are examined directly to assess whether an attack has taken place. This could be done, for example, by examining the response for the presence of malicious strings. Low interaction client honeypots are easier to deploy and operate than high interaction client honeypots and also perform better. However, they are likely to have a lower detection rate since attacks have to be known to the client honeypot in order for it to detect them; new attacks are likely to go unnoticed. They also suffer from the problem of evasion by exploits, which may be exacerbated due to their simplicity, thus making it easier for an exploit to detect the presence of the client honeypot. === HoneyC === HoneyC [7] is a low interaction client honeypot developed at Victoria University of Wellington by Christian Seifert in 2006. HoneyC is a platform independent open source framework written in Ruby. It currently concentrates driving a web browser simulator to interact with servers. Malicious servers are detected by statically examining the web server's response for malicious strings through the usage of Snort signatures. === Monkey-Spider (dead since 2008) === Monkey-Spider [8] is a low-interaction client honeypot i
Granular computing
Granular computing is an emerging computing paradigm of information processing that concerns the processing of complex information entities called "information granules", which arise in the process of data abstraction and derivation of knowledge from information or data. Generally speaking, information granules are collections of entities that usually originate at the numeric level and are arranged together due to their similarity, functional or physical adjacency, indistinguishability, coherency, or the like. At present, granular computing is more a theoretical perspective than a coherent set of methods or principles. As a theoretical perspective, it encourages an approach to data that recognizes and exploits the knowledge present in data at various levels of resolution or scales. In this sense, it encompasses all methods which provide flexibility and adaptability in the resolution at which knowledge or information is extracted and represented. == Types of granulation == As mentioned above, granular computing is not an algorithm or process; there is no particular method that is called "granular computing". It is rather an approach to looking at data that recognizes how different and interesting regularities in the data can appear at different levels of granularity, much as different features become salient in satellite images of greater or lesser resolution. On a low-resolution satellite image, for example, one might notice interesting cloud patterns representing cyclones or other large-scale weather phenomena, while in a higher-resolution image, one misses these large-scale atmospheric phenomena but instead notices smaller-scale phenomena, such as the interesting pattern that is the streets of Manhattan. The same is generally true of all data: At different resolutions or granularities, different features and relationships emerge. The aim of granular computing is to try to take advantage of this fact in designing more effective machine-learning and reasoning systems. There are several types of granularity that are often encountered in data mining and machine learning, and we review them below: === Value granulation (discretization/quantization) === One type of granulation is the quantization of variables. It is very common that in data mining or machine-learning applications the resolution of variables needs to be decreased in order to extract meaningful regularities. An example of this would be a variable such as "outside temperature" (temp), which in a given application might be recorded to several decimal places of precision (depending on the sensing apparatus). However, for purposes of extracting relationships between "outside temperature" and, say, "number of health-club applications" (club), it will generally be advantageous to quantize "outside temperature" into a smaller number of intervals. ==== Motivations ==== There are several interrelated reasons for granulating variables in this fashion: Based on prior domain knowledge, there is no expectation that minute variations in temperature (e.g., the difference between 80–80.7 °F (26.7–27.1 °C)) could have an influence on behaviors driving the number of health-club applications. For this reason, any "regularity" which our learning algorithms might detect at this level of resolution would have to be spurious, as an artifact of overfitting. By coarsening the temperature variable into intervals the difference between which we do anticipate (based on prior domain knowledge) might influence number of health-club applications, we eliminate the possibility of detecting these spurious patterns. Thus, in this case, reducing resolution is a method of controlling overfitting. By reducing the number of intervals in the temperature variable (i.e., increasing its grain size), we increase the amount of sample data indexed by each interval designation. Thus, by coarsening the variable, we increase sample sizes and achieve better statistical estimation. In this sense, increasing granularity provides an antidote to the so-called curse of dimensionality, which relates to the exponential decrease in statistical power with increase in number of dimensions or variable cardinality. Independent of prior domain knowledge, it is often the case that meaningful regularities (i.e., which can be detected by a given learning methodology, representational language, etc.) may exist at one level of resolution and not at another. For example, a simple learner or pattern recognition system may seek to extract regularities satisfying a conditional probability threshold such as p ( Y = y j | X = x i ) ≥ α . {\displaystyle p(Y=y_{j}|X=x_{i})\geq \alpha .} In the special case where α = 1 , {\displaystyle \alpha =1,} this recognition system is essentially detecting logical implication of the form X = x i → Y = y j {\displaystyle X=x_{i}\rightarrow Y=y_{j}} or, in words, "if X = x i , {\displaystyle X=x_{i},} then Y = y j {\displaystyle Y=y_{j}} ". The system's ability to recognize such implications (or, in general, conditional probabilities exceeding threshold) is partially contingent on the resolution with which the system analyzes the variables. As an example of this last point, consider the feature space shown to the right. The variables may each be regarded at two different resolutions. Variable X {\displaystyle X} may be regarded at a high (quaternary) resolution wherein it takes on the four values { x 1 , x 2 , x 3 , x 4 } {\displaystyle \{x_{1},x_{2},x_{3},x_{4}\}} or at a lower (binary) resolution wherein it takes on the two values { X 1 , X 2 } . {\displaystyle \{X_{1},X_{2}\}.} Similarly, variable Y {\displaystyle Y} may be regarded at a high (quaternary) resolution or at a lower (binary) resolution, where it takes on the values { y 1 , y 2 , y 3 , y 4 } {\displaystyle \{y_{1},y_{2},y_{3},y_{4}\}} or { Y 1 , Y 2 } , {\displaystyle \{Y_{1},Y_{2}\},} respectively. At the high resolution, there are no detectable implications of the form X = x i → Y = y j , {\displaystyle X=x_{i}\rightarrow Y=y_{j},} since every x i {\displaystyle x_{i}} is associated with more than one y j , {\displaystyle y_{j},} and thus, for all x i , {\displaystyle x_{i},} p ( Y = y j | X = x i ) < 1. {\displaystyle p(Y=y_{j}|X=x_{i})<1.} However, at the low (binary) variable resolution, two bilateral implications become detectable: X = X 1 ↔ Y = Y 1 {\displaystyle X=X_{1}\leftrightarrow Y=Y_{1}} and X = X 2 ↔ Y = Y 2 {\displaystyle X=X_{2}\leftrightarrow Y=Y_{2}} , since every X 1 {\displaystyle X_{1}} occurs iff Y 1 {\displaystyle Y_{1}} and X 2 {\displaystyle X_{2}} occurs iff Y 2 . {\displaystyle Y_{2}.} Thus, a pattern recognition system scanning for implications of this kind would find them at the binary variable resolution, but would fail to find them at the higher quaternary variable resolution. ==== Issues and methods ==== It is not feasible to exhaustively test all possible discretization resolutions on all variables in order to see which combination of resolutions yields interesting or significant results. Instead, the feature space must be preprocessed (often by an entropy analysis of some kind) so that some guidance can be given as to how the discretization process should proceed. Moreover, one cannot generally achieve good results by naively analyzing and discretizing each variable independently, since this may obliterate the very interactions that we had hoped to discover. A sample of papers that address the problem of variable discretization in general, and multiple-variable discretization in particular, is as follows: Chiu, Wong & Cheung (1991), Bay (2001), Liu et al. (2002), Wang & Liu (1998), Zighed, Rabaséda & Rakotomalala (1998), Catlett (1991), Dougherty, Kohavi & Sahami (1995), Monti & Cooper (1999), Fayyad & Irani (1993), Chiu, Cheung & Wong (1990), Nguyen & Nguyen (1998), Grzymala-Busse & Stefanowski (2001), Ting (1994), Ludl & Widmer (2000), Pfahringer (1995), An & Cercone (1999), Chiu & Cheung (1989), Chmielewski & Grzymala-Busse (1996), Lee & Shin (1994), Liu & Wellman (2002), Liu & Wellman (2004). === Variable granulation (clustering/aggregation/transformation) === Variable granulation is a term that could describe a variety of techniques, most of which are aimed at reducing dimensionality, redundancy, and storage requirements. We briefly describe some of the ideas here, and present pointers to the literature. ==== Variable transformation ==== A number of classical methods, such as principal component analysis, multidimensional scaling, factor analysis, and structural equation modeling, and their relatives, fall under the genus of "variable transformation." Also in this category are more modern areas of study such as dimensionality reduction, projection pursuit, and independent component analysis. The common goal of these methods in general is to find a representation of the data in terms of new variables, which are a linear or nonlinear transformation of the original variables, and in which important stati
Admissible heuristic
In computer science, specifically in algorithms related to pathfinding, a heuristic function is said to be admissible if it never overestimates the cost of reaching the goal, i.e. the cost it estimates to reach the goal is not higher than the lowest possible cost from the current point in the path. In other words, it should act as a lower bound. It is related to the concept of consistent heuristics. While all consistent heuristics are admissible, not all admissible heuristics are consistent. == Search algorithms == An admissible heuristic is used to estimate the cost of reaching the goal state in an informed search algorithm. In order for a heuristic to be admissible to the search problem, the estimated cost must always be lower than or equal to the actual cost of reaching the goal state. The search algorithm uses the admissible heuristic to find an estimated optimal path to the goal state from the current node. For example, in A search the evaluation function (where n {\displaystyle n} is the current node) is: f ( n ) = g ( n ) + h ( n ) {\displaystyle f(n)=g(n)+h(n)} where f ( n ) {\displaystyle f(n)} = the evaluation function. g ( n ) {\displaystyle g(n)} = the cost from the start node to the current node h ( n ) {\displaystyle h(n)} = estimated cost from current node to goal. h ( n ) {\displaystyle h(n)} is calculated using the heuristic function. With a non-admissible heuristic, the A algorithm could overlook the optimal solution to a search problem due to an overestimation in f ( n ) {\displaystyle f(n)} . == Formulation == n {\displaystyle n} is a node h {\displaystyle h} is a heuristic h ( n ) {\displaystyle h(n)} is cost indicated by h {\displaystyle h} to reach a goal from n {\displaystyle n} h ∗ ( n ) {\displaystyle h^{}(n)} is the optimal cost to reach a goal from n {\displaystyle n} h ( n ) {\displaystyle h(n)} is admissible if, ∀ n {\displaystyle \forall n} h ( n ) ≤ h ∗ ( n ) {\displaystyle h(n)\leq h^{}(n)} == Construction == An admissible heuristic can be derived from a relaxed version of the problem, or by information from pattern databases that store exact solutions to subproblems of the problem, or by using inductive learning methods. == Examples == Two different examples of admissible heuristics apply to the fifteen puzzle problem: Hamming distance Manhattan distance The Hamming distance is the total number of misplaced tiles. It is clear that this heuristic is admissible since the total number of moves to order the tiles correctly is at least the number of misplaced tiles (each tile not in place must be moved at least once). The cost (number of moves) to the goal (an ordered puzzle) is at least the Hamming distance of the puzzle. The Manhattan distance of a puzzle is defined as: h ( n ) = ∑ all tiles d i s t a n c e ( tile, correct position ) {\displaystyle h(n)=\sum _{\text{all tiles}}{\mathit {distance}}({\text{tile, correct position}})} Consider the puzzle below in which the player wishes to move each tile such that the numbers are ordered. The Manhattan distance is an admissible heuristic in this case because every tile will have to be moved at least the number of spots in between itself and its correct position. The subscripts show the Manhattan distance for each tile. The total Manhattan distance for the shown puzzle is: h ( n ) = 3 + 1 + 0 + 1 + 2 + 3 + 3 + 4 + 3 + 2 + 4 + 4 + 4 + 1 + 1 = 36 {\displaystyle h(n)=3+1+0+1+2+3+3+4+3+2+4+4+4+1+1=36} == Optimality proof == If an admissible heuristic is used in an algorithm that, per iteration, progresses only the path of lowest evaluation (current cost + heuristic) of several candidate paths, terminates the moment its exploration reaches the goal and, crucially, closes all optimal paths before terminating (something that's possible with A search algorithm if special care isn't taken), then this algorithm can only terminate on an optimal path. To see why, consider the following proof by contradiction: Assume such an algorithm managed to terminate on a path T with a true cost Ttrue greater than the optimal path S with true cost Strue. This means that before terminating, the evaluated cost of T was less than or equal to the evaluated cost of S (or else S would have been picked). Denote these evaluated costs Teval and Seval respectively. The above can be summarized as follows, Strue < Ttrue Teval ≤ Seval If our heuristic is admissible it follows that at this penultimate step Teval = Ttrue because any increase on the true cost by the heuristic on T would be inadmissible and the heuristic cannot be negative. On the other hand, an admissible heuristic would require that Seval ≤ Strue which combined with the above inequalities gives us Teval < Ttrue and more specifically Teval ≠ Ttrue. As Teval and Ttrue cannot be both equal and unequal our assumption must have been false and so it must be impossible to terminate on a more costly than optimal path. As an example, let us say we have costs as follows:(the cost above/below a node is the heuristic, the cost at an edge is the actual cost) 0 10 0 100 0 START ---- O ----- GOAL | | 0| |100 | | O ------- O ------ O 100 1 100 1 100 So clearly we would start off visiting the top middle node, since the expected total cost, i.e. f ( n ) {\displaystyle f(n)} , is 10 + 0 = 10 {\displaystyle 10+0=10} . Then the goal would be a candidate, with f ( n ) {\displaystyle f(n)} equal to 10 + 100 + 0 = 110 {\displaystyle 10+100+0=110} . Then we would clearly pick the bottom nodes one after the other, followed by the updated goal, since they all have f ( n ) {\displaystyle f(n)} lower than the f ( n ) {\displaystyle f(n)} of the current goal, i.e. their f ( n ) {\displaystyle f(n)} is 100 , 101 , 102 , 102 {\displaystyle 100,101,102,102} . So even though the goal was a candidate, we could not pick it because there were still better paths out there. This way, an admissible heuristic can ensure optimality. However, note that although an admissible heuristic can guarantee final optimality, it is not necessarily efficient.
Artificial intimacy
Artificial intimacy is a form of human-AI interaction in which an individual will form social connections, emotional bonds, or intimate relationships with various forms of artificial intelligence, including chatbots, virtual assistants, and other artificial entities. Artificially intimate relationships include not only romances, but parasocial relationships with virtual AI characters and the use of griefbots trained on a dead or otherwise lost individual. Artificial intimacy can arise because humans are prone to anthropomorphism. Responses from these AI models are often designed to simulate human interaction. Individuals experiencing artificial intimacy may exhibit attachment, love and commitment to certain AI models, akin to the bonds typically shared between humans. == Causes == === Perceived responsiveness === Robin Dunbar famously proposed that due to emergence of larger groups of humans, vocal communication and language in humans evolved to replace grooming as a means of bonding, arguing that language was a more efficient way to maintain and strengthen social bonds across wider social settings and networks. Further research in this field leads many psychologists to agree that social cognition, affiliative bonding and language in humans are deeply connected. The interpersonal model of intimacy considers communication to be key in affiliative bonding, suggesting that intimacy develops and deepens through open communication between partners in relationship. Specifically, when individuals communicate emotions and perceive their partner as responsive and caring, feelings of closeness and connection are enhanced, building intimacy. Social penetration theory also aligns with the idea of communication being central to intimacy, by explaining how interpersonal relationships develop through gradual increases in self-disclosure. When the benefits of emotional bonding outweigh the costs of vulnerability, individuals will partake in self-disclosure, opening up to one another. Thereby, the literature can be used to provide a proximate explanation for the emergence of artificial intimacy to understand how the phenomenon occurs. Artificial entities are able to mimic interpersonal communication between humans, which in turn can simulate sensations of intimacy within human users though a perceived sense of responsiveness. The relationship between human and AI does not come with the cost of vulnerability or social rejection, which may make self-disclosure easier than with other humans. Altogether, these factors may lead to the experience of anthropomorphism and formation of affiliative relationships. Skjuve et al's interview study on Replika chatbot users further aligns with this explanation, finding that users' perception of chatbots as "accepting, understanding and non-judgmental" facilitated relationship development between the AI and users, and the act of self-disclosure possibly strengthened relationships. Another study on Replika users' reviews and survey results found users perceived chatbots as emotional supportive companions. This evidence further suggests that the perception of artificial entities as capable of empathy and responsiveness in communication facilitate the development of intimate relationships between users and AI. === Loneliness and coping with negative emotions === Research has suggested that humans evolved social bonds as a result of evolutionary pressures that favored cooperation, information exchange and transmission, and group living. Many studies stress the presence of social bonds to be important for human living: research by Baumeister and Leary suggests that humans have a basic psychological need to form and maintain "strong, stable interpersonal relationships", and that a lack of social bonds or sense of belonging leads to negative psychological and physical outcomes. Eisenberger et al's study on the neuroimaging of brain activity suggests that human brains process social rejection and exclusion similarly to physical pain. Furthermore, Song et al's study found that lonely individuals tend to seek more connections in mediated environments, such as online platforms like Facebook. This was suggested to be as a means to reduce their offline loneliness from a lack of in-person interaction, while also fulfilling a need to communicate. Leading on from this, an ultimate explanation for why humans seek the perceived sense of connection from artificial intimacy is to fulfil an evolutionary need for bonding and belonging. Xie et al's study found loneliness to be a driving factor in chatbot interaction. Herbener and Damholdt's study on Danish high school students found that students who sought emotional support or engaged in reciprocal conversations with chatbots were significantly more lonely than their peers, perceived themselves as having less social support, and used the chatbots to cope with negative emotions. The aforementioned notion that chatbots were perceived to have a positive effect on users' negative emotions is also further supported by other studies. Skjuve et al's study found that chatbot relationships may have a positive effect on users' wellbeing. De Freitas et al ran several studies on the effect of chatbots on loneliness, consistently finding evidence suggesting that interaction with chatbots reduces loneliness in users: It was found that existing chatbot users used AI to alleviate loneliness, having an AI companion consistently reduced loneliness over the course of a week, and reductions in loneliness could be explained by chatbot performance—and specifically whether it was able to make users feel heard. Overall the evidence suggests an innate need for bonding evokes feelings of loneliness in users, who turn to artificial intimacy as a low-cost method alleviate these emotions. While many users report positive experiences, some researchers caution that pursuing artificial intimacy may lead to reduced social motivation, social substitution effects, withdrawal from real-life relationships and difficulty discerning reality from fantasy, which may increase longer-term loneliness and isolation. The long-term psychological and societal impacts remain under active investigation.
Astrostatistics
Astrostatistics is a discipline which spans astrophysics, statistical analysis and data mining. It is used to process the vast amount of data produced by automated scanning of the cosmos, to characterize complex datasets, and to link astronomical data to astrophysical theory. Many branches of statistics are involved in astronomical analysis including nonparametrics, multivariate regression and multivariate classification, time series analysis, and especially Bayesian inference. The field is closely related to astroinformatics.
Inductive bias
The inductive bias (also known as learning bias) of a learning algorithm is the set of assumptions that the learner uses to predict outputs of given inputs that it has not encountered. Inductive bias is anything which makes the algorithm learn one pattern instead of another pattern (e.g., step-functions in decision trees instead of continuous functions in linear regression models). Learning involves searching a space of solutions for a solution that provides a good explanation of the data. However, in many cases, there may be multiple equally appropriate solutions. An inductive bias allows a learning algorithm to prioritize one solution (or interpretation) over another, independently of the observed data. In machine learning, the aim is to construct algorithms that are able to learn to predict a certain target output. To achieve this, the learning algorithm is presented some training examples that demonstrate the intended relation of input and output values. Then the learner is supposed to approximate the correct output, even for examples that have not been shown during training. Without any additional assumptions, this problem cannot be solved since unseen situations might have an arbitrary output value. The kind of necessary assumptions about the nature of the target function are subsumed in the phrase inductive bias. A classical example of an inductive bias is Occam's razor, assuming that the simplest consistent hypothesis about the target function is actually the best. Here, consistent means that the hypothesis of the learner yields correct outputs for all of the examples that have been given to the algorithm. Approaches to a more formal definition of inductive bias are based on mathematical logic. Here, the inductive bias is a logical formula that, together with the training data, logically entails the hypothesis generated by the learner. However, this strict formalism fails in many practical cases in which the inductive bias can only be given as a rough description (e.g., in the case of artificial neural networks), or not at all. == Types == The following is a list of common inductive biases in machine learning algorithms. Maximum conditional independence: if the hypothesis can be cast in a Bayesian framework, try to maximize conditional independence. This is the bias used in the Naive Bayes classifier. Minimum cross-validation error: when trying to choose among hypotheses, select the hypothesis with the lowest cross-validation error. Although cross-validation may seem to be free of bias, the "no free lunch" theorems show that cross-validation must be biased, for example assuming that there is no information encoded in the ordering of the data. Maximum margin: when drawing a boundary between two classes, attempt to maximize the width of the boundary. This is the bias used in support vector machines. The assumption is that distinct classes tend to be separated by wide boundaries. Minimum description length: when forming a hypothesis, attempt to minimize the length of the description of the hypothesis. Minimum features: unless there is good evidence that a feature is useful, it should be deleted. This is the assumption behind feature selection algorithms. Nearest neighbors: assume that most of the cases in a small neighborhood in feature space belong to the same class. Given a case for which the class is unknown, guess that it belongs to the same class as the majority in its immediate neighborhood. This is the bias used in the k-nearest neighbors algorithm. The assumption is that cases that are near each other tend to belong to the same class. == Shift of bias == Although most learning algorithms have a static bias, some algorithms are designed to shift their bias as they acquire more data. This does not avoid bias, since the bias shifting process itself must have a bias.