Search results for "understanding"
showing 10 items of 108 documents
Compréhension de scènes urbaines basée sur la polarisation
2021
Humans possess an innate ability to interpret scenes under any condition. Computer Vision tends to mimic these capabilities by implementing intelligent algorithms to address complex understanding problems. In this regard, we are interested in understanding outdoor urban scenes in various weather conditions. This thesis specifically addresses the problems arising from the presence of specularity in the scenes. To this end, we aim to take advantage of polarization indices to define such surfaces in addition to traditional objects. In terms of understanding, we aim to introduce polarization to the fields of computer vision and deep learning.This thesis focuses on the following underlying chall…
GAIML: A New Language for Verbal and Graphical Interaction in Chatbots
2008
Natural and intuitive interaction between users and complex systems is a crucial research topic in human-computer interaction. A major direction is the definition and implementation of systems with natural language understanding capabilities. The interaction in natural language is often performed by means of systems called chatbots. A chatbot is a conversational agent with a proper knowledge base able to interact with users. Chatbots appearance can be very sophisticated with 3D avatars and speech processing modules. However the interaction between the system and the user is only performed through textual areas for inputs and replies. An interaction able to add to natural language also graph…
U.I.R.D.A. – Unbuilt Italian Rationalism Digital Archive
2018
For twenty years, the architecture of Italian rationalism through the digital modelling has been investigated. Very often, the production of a model and the consequent representation of tridimensional views, in many case studies, as outcome of the research on architecture have been considered. Actually, the digital model, intended as a critical tool, has to be conceived as a ‘starting point' for graphic analysis of architecture and not as the outcome. Indeed, it is associated to other graphics, sometimes not ‘deducted' from the model, useful for the understanding/translation of architecture. The construction of the model is not the construction of a simple image, operation, which is often c…
Extending the Tsetlin Machine With Integer-Weighted Clauses for Increased Interpretability
2020
Despite significant effort, building models that are both interpretable and accurate is an unresolved challenge for many pattern recognition problems. In general, rule-based and linear models lack accuracy, while deep learning interpretability is based on rough approximations of the underlying inference. Using a linear combination of conjunctive clauses in propositional logic, Tsetlin Machines (TMs) have shown competitive performance on diverse benchmarks. However, to do so, many clauses are needed, which impacts interpretability. Here, we address the accuracy-interpretability challenge in machine learning by equipping the TM clauses with integer weights. The resulting Integer Weighted TM (…
Using the Tsetlin Machine to Learn Human-Interpretable Rules for High-Accuracy Text Categorization With Medical Applications
2019
Medical applications challenge today's text categorization techniques by demanding both high accuracy and ease-of-interpretation. Although deep learning has provided a leap ahead in accuracy, this leap comes at the sacrifice of interpretability. To address this accuracy-interpretability challenge, we here introduce, for the first time, a text categorization approach that leverages the recently introduced Tsetlin Machine. In all brevity, we represent the terms of a text as propositional variables. From these, we capture categories using simple propositional formulae, such as: if "rash" and "reaction" and "penicillin" then Allergy. The Tsetlin Machine learns these formulae from a labelled tex…
2020
Domain-specific understanding of digitally represented graphs is necessary for successful learning within and across domains in higher education. Two recent studies conducted a cross-sectional analysis of graph understanding in different contexts (physics and finance), task concepts, and question types among students of physics, psychology, and economics. However, neither changes in graph processing nor changes in test scores over the course of one semester have been sufficiently researched so far. This eye-tracking replication study with a pretest-posttest design examines and contrasts changes in physics and economics students' understanding of linear physics and finance graphs. It analyze…
Integrazione di celle solari di terza generazione nel vetromattone per la realizzazione di pannelli traslucidi fotovoltaici. Analisi prestazione e st…
2013
L’articolo illustra i primi risultati ottenuti nell’ambito dell’analisi prestazionale del vetromattone fotovoltaico, un prodotto edilizio innovativo derivato dall’integrazione di celle fotovoltaiche di terza generazione (DSSC) nel vetromattone, ideato per la realizzazione di involucri traslucidi energeticamente effi cienti ed “attivi”, in grado di ridurre i consumi energetici degli edifi ci e di produrre, al contempo, energia verde. L’analisi è stata condotta su quattro differenti ipotesi di integrazione. Attraverso simulazioni numeriche si è effettuata una valutazione dell’energia assorbita dagli strati attivi oltre che delle prestazioni ottiche complessive del dispositivo. Lo studio anali…
RDF* Graph Database as Interlingua for the TextWorld Challenge
2019
This paper briefly describes the top-scoring submission to the First TextWorld Problems: A Reinforcement and Language Learning Challenge. To alleviate the partial observability problem, characteristic to the TextWorld games, we split the Agent into two independent components: Observer and Actor, communicating only via the Interlingua of the RDF* graph database. The RDF* graph database serves as the “world model” memory incrementally updated by the Observer via FrameNet informed Natural Language Understanding techniques and is used by the Actor for the efficient exploration and planning of the game Action sequences. We find that the deep-learning approach works best for the Observer componen…
Profesiju izpētes metodes priekšmetā “Dizains un tehnoloģijas” skolēnu sagatavošanai tālākizglītības izvēlei
2021
Darba autori diplomdarbā “Profesiju izpētes metodes priekšmetā “Dizains un tehnoloģijas” skolēnu sagatavošanai tālākizglītības izvēlei” izstrādāja un aprobēja trīs veida metodes, kas balstītas veiktajā literatūras izpētē. Teorētiskajā daļā ir apskatītas skolēnu tālākās izglītības izvēles, to statistika un kādi projekti tiek piedāvāti Latvijā un pasaulē, lai veicinātu skolēnu izpratni par profesiju specifiku, kas palīdz skolēniem pieņemt lēmumus, kāda profesija viņus interesē vairāk un ko izvēlēties tālāk studēt. Pētījuma daļā tika izstrādāta anketa, lai noteiktu skolēnu izpratni par dažādajām prasmēm un zināšanām, kas integrējas vienā profesijā, un to, kur var apgūt šīs profesijas. Anketas …