22 key points
to bring trust to
AI-based decisions
Reasoning AI
Augmented Fuzzy Cognitive AI
XTRACTIS implements innovative mathematics based on the Theory of Fuzzy Relations of order N [Zalila 1993].
It is the result of over 270 scientist-years of high-level R&D in fuzzy mathematics and automatic reasoning.
This non-standard mathematics enables reasoning with continuous logics, which are more suitable than classic binary logic for modeling complex real-world problems, i.e., problems mixing imprecision, subjectivity, and epistemic uncertainty.
Knowledge-Generating AI
XTRACTIS automatically discovers knowledge hidden in data. The decision systems it produces are structured in fuzzy rules. A fuzzy rule is a fuzzy relation, i.e., a nonlinear equation relating the causes to the effect.
XTRACTIS reveals all the knowledge synthesized from the information included in the learning dataset. It allows professional experts to understand their processes and to enrich their knowledge.
Collective & Evolutionary AI
XTRACTIS robots infinitely perfect their induction (resp. abduction) strategies to discover increasingly efficient models (resp. increasingly satisfactory solutions) without human supervision, first in competition, then in cooperation.
Frugal & Adaptive AI
XTRACTIS uses evenly small or big data. It manages low-quality or low-quantity data without imputation, i.e., without introducing bias in data before processing.
When the volume of data is limited, it induces models with higher predictive capacity than the best open-source AI techniques. The predictive capacity is also higher when comparing the models from different techniques at iso-complexity (comparable model structure).
XTRACTIS also offers adaptive induction: the REVEAL server(s) are used in the field to induce new field-specific models as soon as sufficient new data is collected. These models are then regularly updated as the data evolves.
Human-Centric AI
Replicating Human Reasoning
XTRACTIS extends the three human reasoning modes in three software robots:
XTRACTIS REVEAL uses fuzzy induction to discover intelligible cause and effect models, as human scientists do thanks to the Experimental Scientific Method.
XTRACTIS PREDICT uses fuzzy deduction for its predictive analysis, calculating the predictions from the induced models, rationally and deterministically.
XTRACTIS OPTIMIZE uses fuzzy abduction for its prescriptive analysis, discovering the most optimal solutions to meet a nonlinear multi-objective request, under flexible constraints, from induced or analytical models.
Enabling Audit & Certification of AI Decision Systems
Users and experts can validate their models before pushing to end-use or audit them before submission to certification to comply with AI regulations for high-risk applications.
Enhancing Knowledge
& Augmenting Experts
XTRACTIS-induced models are fully auditable by the professional expert who confirms the correctness of the decision strategy of the AI system to be deployed. PREDICT rationally explains each decision it delivered: its deductive reasoning calculating each prediction is automatically recorded in a verifiable built-in report.
Highlighting Biases
& Deploying Ethical Transparent AI Systems
REVEAL induces rules that could confirm the presence of noise included in the reference data or could explain any conscious or unconscious bias that a decision-making process may contain. PREDICT refuses to deliver a prediction if it is highly uncertain of its decision (for offline systems).
Trusted AI
Robust Models
REVEAL induces highly predictive knowledge from data, generating top-performing decision models with accuracy levels at least equivalent to the best open-source AI techniques.
Each induced model undergoes an intensive validation and benchmarking process, ensuring its reliability under real-world operating conditions and its performance against leading competing methods.
Beyond predictive strength, REVEAL enhances data integrity by detecting noise and anomalies, identifying observations whose measured values significantly deviate from model predictions.
Intelligible & Explainable Models
XTRACTIS-induced models are natively transparent: they are structured as systems of fuzzy "IF…THEN" rules, operating without rule chaining and relying exclusively on original predictor variables (no synthetic variables are introduced).
Their internal decision-making logic is accessible and understandable, enabling every output to be clearly explained and traced across all possible cases.
Stable Models
XTRACTIS-induced models are inherently stable.
First, every prediction is mathematically bounded within intervals determined in advance by the structure of the rule system. Second, any slight variation in an input variable produces a gradual and proportionate variation in the output, ensuring smooth and controlled model behavior.
At the same time, strong nonlinearities inherent to the CPP under study are rigorously captured and appropriately managed when required.
Decremental Holistic Modeling
REVEAL initially considers the full set of available variables and their potential interactions, preserving weak signals that may carry decisive information.
It then automatically eliminates non-contributing variables through a decremental modeling process, allowing the intrinsic complexity of the CPP under study to emerge naturally.
Because the resulting models are inherently multifactorial, each prediction for a new case reflects a highly contextualized and personalized decision outcome.
Singular AI
General Purpose Behavioral AI
XTRACTIS is engineered for advanced nonlinear modeling of complex processes, ranging from human / cognitive-based decision-making to the dynamics of industrial, natural, and socio-economic systems.
The platform enables the rapid development of high-risk predictive applications across all sectors including Finance, Banking, Insurance, Healthcare, Pharma, Biotech, Sciences, Industry, Defense, Security, Cybersecurity, Legal, and Autonomous Systems; and across all strategic functions, from Executive Management, HR and Marketing to R&D and domain expertise.
EU-Sovereign AI
XTRACTIS features 100% French-developed, proprietary algorithms. Our core code is entirely independent of open-source licenses and is fully ITAR-free (Benchmark module excepted).
Assets sovereignty is guaranteed: our secure, private PaaS is hosted independently, ensuring total immunity from the Privacy Shield, the Patriot Act, the Cloud Act, and the Foreign Intelligence Surveillance Act.
Compliant AI for High-Risk Applications
XTRACTIS already defines the state-of-the-art of the AI Act European regulation relating to the deployment of high-risk AI applications and establishes even higher requirements of intelligibility, in addition to the robustness of critical decision systems. It also respects the WHO guiding principles for the use of AI in Health.
Reverse Engineering Capability
Through its unique reverse engineering capability, REVEAL can decipher the underlying decision logic of an opaque AI system by transforming it into a transparent XTRACTIS model having an equivalent predictive performance.
This enables organizations to regain full visibility over opaque systems, assess potential biases, and restore control over critical decision processes.
Strategic AI
XTRACTIS is the only AI worldwide that natively discovers operational knowledge from data without compromising predictive performance.
By combining intelligibility, robustness, and deployability, it provides its users with decisive technological, economic, and strategic advantages, including enhanced sovereignty over critical decision systems.
Easy to Use AI
No-Code Ready-to-Use Platform
XTRACTIS is fully accessible through an intuitive interface that requires no programming. All functionalities, including advanced benchmarking, are operated seamlessly without writing a single line of code.
Users do not need extensive Data Science expertise to generate, validate, and deploy high-performance decision models.
Scalable Induction and Abduction Speed
XTRACTIS scales seamlessly to address increasing problem complexity or to accelerate computational throughput by deploying additional REVEAL or OPTIMIZE reasoning robots.
The platform operates efficiently using standard CPU and RAM resources, with no reliance on GPU infrastructure. This architecture reduces hardware constraints, lowers operational costs, and supports a more energy-efficient computing footprint.
Access in Private PaaS
XTRACTIS is available as a secure Platform-as-a-Service (PaaS) environment, with dedicated physical servers installed at one of our hosting providers.
The infrastructure ensures the highest standards of data and model security, guaranteeing controlled access and operational integrity.
For organizations requiring full sovereignty, servers can be installed on-premises within the client’s facilities.
Prediction in Real-Time
at an extremely high frequency on basic CPU: up to 7.6 million predictions per second on an 8-core Intel i7 CPU @2.5GHz.
Easy Deployment
Special licenses to exploit models via API or embedded codes.
FAQ about Fuzzy AI Concepts
Fuzzy Theory or Fuzzy Mathematics proposes formally rigorous concepts, techniques, and methods to model and deal with multidimensional knowledge and fuzzy data, i.e., real-world data that include imprecision, uncertainty, and/or subjectivity. It is made up of several branches.
Fuzzy knowledge is information-rich: transforming it into binary knowledge at the beginning of the data processing induces a bias that inevitably affects the quality of the decision. Maintaining the fuzziness throughout the data processing and deciding only at the end of the process (final transition from a fuzzy decision to a binary decision) is much more adequate for accurate decisions.
In Fuzzy Theory, dual measures of Possibility and Necessity replace the measure of Probability when the decision maker must assess the occurrence of an event on which they have little historical data or poor-quality data (e.g., will I draw a reddish ball out of the bag?). This appears particularly in multi-criteria decision-making when information comes from human sensors (judgment, expert opinion).
Theory of Possibility is thus adapted to account for the epistemic uncertainty linked to the lack of information. Particularly, it allows the estimation of the occurrence of fuzzy events, when the Theory of Probability is rather linked to the stochastic uncertainty of precise but random event.
Fuzzy Logic and Fuzzy Set theory are branches of Fuzzy Mathematics. They are used for the gradual and nuanced modeling of expert knowledge, by replicating the human reasoning while allowing the definition of fuzzy categories, i.e., with ill-defined boundaries.
By integrating both imprecision and uncertainty, it makes it possible to design decision-support systems that are more effective than conventional expert systems: experts will be even more confident of their assertions if they are authorized to be imprecise and will be all the more uncertain if they are forced to be precise.
It also offers a high-performance alternative approach for modeling complex processes and non-linear phenomena. Fuzzy Logic is the basis of Fuzzy Symbolic / Cognitive AI.
Fuzzy Arithmetic is a branch of Fuzzy Mathematics. It allows the modeling and processing of approximate numerical quantities. It enables the design of more accurate predictive analytical models that are more faithful to reality. It also allows solving complex Operational Research problems by introducing fuzzy constraints, i.e., which could be more or less satisfied.
The Fuzzy Relation of order N (FR-N) generalizes the concepts of scalar of [0,1] (FR-0), fuzzy set (FR-1), of fuzzy two-dimensional relation (FR-2) and extends them to an N-dimensional space. An FR-N thus defines a non-linear multi-dimensional equation.
FR-N Theory introduces infinite fuzzy logical operators of conjunction, disjunction, negation, implication, and anchor-composition. It shows how to create an infinity of fuzzy measures of possibility and necessity using the FR-N fusion composition operators. And thus how to create an infinity of fuzzy deductive, inductive and abductive reasoning algorithms.
This theory defines new original algebraic structures while exhibiting the corresponding maximum algebraic structures according to the operators used. FR-N Theory extends Fuzzy Logic, Fuzzy Set Theory and Theory of Possibility, and merges them into a single theory.
Compared to the other binary AI techniques, it thus allows a larger margin in modeling non-linear non-monotonous non-convex non-connected, and non-decomposable complex processes and phenomena.
An “IF…THEN” fuzzy rule is a non-linear equation relating the causes to the effect or a local non-linear model linking nuanced variables. Mathematically, it is defined by an FR-N, i.e., a non-linear multidimensional function relating N-1 interacting input variables to the output variable, thanks to fuzzy operators of conjunction, disjunction, negation and implication.
The fuzzy deductive inference of fuzzy rules is based on the anchor-composition of FR-N.
A fuzzy model/system is a collection of fuzzy rules covering the decision space. Any occurrence in this space leads to the simultaneous and gradual triggering of specific rules, then the interpolation of their decisions: local rules interact and cooperate to calculate the most appropriate final decision.
The more the model is composed of fuzzy rules and the more it uses input variables, the more it will succeed in accurately describing the behavior of a complex process. The feat of XTRACTIS is to find automatically the actual level of complexity of the process under study: when enough information is included in the dataset, XTRACTIS always succeeds in discovering the most robust AND compact model, i.e., the most intelligible model with the highest predictive and real performances.
Induction is the human reasoning mode that makes it possible to discover general laws (i.e., a model) from observing given facts about causes and their consequences.
Deduction is the human reasoning mode that finds the consequence of given causes from general laws.
Abduction is the human reasoning mode that searches for particular possible causes for a given consequence from general laws.
The model's robustness refers to its predictive performance or ability to make correct predictions for unknown situations (cases that are not part of the training set) or for noisy situations.
Not to be confused with the descriptive performance (descriptiveness), which is its ability to make correct predictions for known situations (cases of the training set).
An INTELLIGIBLE model is composed of an optimal finite number of pieces of knowledge: it is a white-box or transparent model. We can therefore understand the entire internal logic of its deductive reasoning for the infinity of possible cases.
An EXPLAINABLE model is a model whose decision can be locally justified for a specific case of prediction. It can be a black-box model.
An intelligible model is necessarily explainable, but the converse is false. Because they are intelligible, XTRACTIS models are also explainable.
XTRACTIS has 3 Machine Learning challengers among the non-linear AI techniques: Neural Networks, Boosted Trees, and Random Forests.
Despite their widespread use, these open-source AI techniques produce unintelligible models whose stability cannot be formally proved.
Conversely, XTRACTIS models are intelligible and formally stable due to the theoretical foundations of our algorithms. In addition, their robustness is at least equivalent to that of the models obtained from other AI techniques.
