Search results for "algoritmi"

Johdatus peliteoriaan : kahden pelaajan nollasummapelien ratkaiseminen ja Nashin tasapainojen olemassaolo usean pelaajan yleisessä summapelissä

2013

Tämän tutkielman tarkoituksena on osoittaa, että jokaisella usean pelaajan yleisellä summapelillä on olemassa vähintään yksi Nashin tasapaino. Lisäksi osoitetaan, että kahden pelaajan nollasummapeleissä Nashin tasapainojen mukaiset pelaajien voittojen odotusarvojen suuruudet ovat yksikäsitteiset, ja näytetään kuinka kyseiset odotusarvot voidaan ratkaista lineaarisen optimoinnin avulla. Tutkielmassa määritellään yleiset summapelit kolmikkoina, jotka muodostuvat äärellisestä määrästä pelaajia, joista jokaiseen on liitetty äärellinen joukko. Näiden joukkojen alkioita kutsutaan pelaajien puhtaiksi strategioiksi. Kolmikon viimeisen jäsenen muodostaa jokaiselle pelaajalle erikseen määritelty kuva…

Mašīnmācīšanās metožu pielietojums pretinieku tendenču noteikšanai

2021

Darbā tiek pētīts, cik veiksmīgi ar mašīnmācīšanās metodēm var noteikt pretinieku tendences no salīdzinoši nelielas datu kopas. Darbā tiek pētīta kāršu spēle pokers. Uzdevums ir noteikt, vai pretiniekiem ir tendence pieņemt kādu lēmumu, pēc kā attiecīgi mēs varam paši mainīt savu stratēģiju atbilstoši noteiktajām tendencēm, tādā veidā iegūstot priekšrocību. Tiek apskatīts kādi spēlētāju tipi eksistē izspēlēs ar dažādiem spēlētāju skaitu izmantojot klasterēšanas algoritmus. Tālāk tiek izstrādāta mākslīgā intelekta pamatklase, kuru var viegli paplašināt tādā veidā definējot spēlētāju, kas spēlē pēc noteikta spēlētāja tipa tendencēm. Visbeidzot tiek novērtētas dažādas metodes un modeļi, kas āt…

La decisione amministrativa robotica

2022

Il tema dell’informatizzazione dell’attività amministrativa è stato oggetto di cicliche attenzioni da parte della letteratura giuridica. Negli ultimi anni, tuttavia, il dibattito in materia ha raggiunto un vero e proprio punto di svolta, che pare potersi giustificare in virtù di una riconsiderazione complessiva dell’importanza e del ruolo delle tecnologie digitali nell’attuale contesto economico e sociale. Nella moderna “Società dell’algoritmo” si assiste, in particolare, ad un utilizzo, sempre più frequente e variegato, di appositi strumenti informatici per compiere scelte e valutazioni in precedenza spettanti ai soli funzionari amministrativi, con l’obiettivo di perseguire, in tal modo, u…

Potere amministrativo e automazione decisionale: orientamenti tradizionali e prospettive future

2021

Il contributo analizza il possibile ambito di applicazione delle decisioni amministrative automatizzate. Dopo aver richiamato il tradizionale rapporto tra principio di legalità e forme di esercizio del potere pubblico, vengono esaminate le più rilevanti posizioni dottrinali formatesi in materia, al fine di chiarire quale effettivo ambito di applicazione possa essere oggi riconosciuto al fenomeno dell'automazione decisionale.

Intrusion detection applications using knowledge discovery and data mining

2014

Enhancing identification of causal effects by pruning

2018

Causal models communicate our assumptions about causes and effects in real-world phe- nomena. Often the interest lies in the identification of the effect of an action which means deriving an expression from the observed probability distribution for the interventional distribution resulting from the action. In many cases an identifiability algorithm may return a complicated expression that contains variables that are in fact unnecessary. In practice this can lead to additional computational burden and increased bias or inefficiency of estimates when dealing with measurement error or missing data. We present graphical criteria to detect variables which are redundant in identifying causal effe…

Improving identification algorithms in causal inference

2018

Causal models provide a formal approach to the study of causality. One of the most useful features of causal modeling is that it enables one to make causal claims about a phenomenon using observational data alone under suitable conditions. This feature enables the analysis of interventions that may be infeasible to conduct in the real world for practical or ethical reasons. The uncertainty associated with the variables of interest is taken into account by including a probability distribution in the causal model, making it is possible to study the effects of external interventions by examining how this distribution is changed by the action. The probability distribution of a specific variable i…

Explainable Fuzzy AI Challenge 2022 : Winner’s Approach to a Computationally Efficient and Explainable Solution

2022

An explainable artificial intelligence (XAI) agent is an autonomous agent that uses a fundamental XAI model at its core to perceive its environment and suggests actions to be performed. One of the significant challenges for these XAI agents is performing their operation efficiently, which is governed by the underlying inference and optimization system. Along similar lines, an Explainable Fuzzy AI Challenge (XFC 2022) competition was launched, whose principal objective was to develop a fully autonomous and optimized XAI algorithm that could play the Python arcade game “Asteroid Smasher”. This research first investigates inference models to implement an efficient (XAI) agent using rule-based …

Eksakto kvantu vaicājošo algoritmu sarežģītība nejaušām Būla funkcijām

2018

Ir pierādīts, ka nejaušai n-bitu Būla funkcijai optimālam kvantu vaicājošajam algoritmam ir nepieciešami aptuveni n/2 vaicājumi, ja algoritmam ir atļauts kļūdīties ar nelielu varbūtību, taču eksaktajiem algoritmiem šī sarežģītība nav zināma. Šajā darbā tiek pētītas polinomiālās metodes iespējas eksaktas kvantu vaicājumu sarežģītības apakšējas robežas pierādīšanai. Tiek apskatīti tādi polinomi, kuru kvadrātu summa pārstāv doto Būla funkciju. Pirmkārt, ar pusnoteiktās programmēšanas palīdzību tiek skaitliski parādīts priekš n<=8, ka nejaušai n-bitu Būla funkcijai pietiekami precīzi |(n+1)/2| pakāpes polinomi eksistē ar lielu varbūtību. Otrkārt, tiek pierādīts, ka gandrīz visas Būla funkcijas …

Improving Scalable K-Means++

2021

Two new initialization methods for K-means clustering are proposed. Both proposals are based on applying a divide-and-conquer approach for the K-means‖ type of an initialization strategy. The second proposal also uses multiple lower-dimensional subspaces produced by the random projection method for the initialization. The proposed methods are scalable and can be run in parallel, which make them suitable for initializing large-scale problems. In the experiments, comparison of the proposed methods to the K-means++ and K-means‖ methods is conducted using an extensive set of reference and synthetic large-scale datasets. Concerning the latter, a novel high-dimensional clustering data generation …